stats: Update 04.gpu stats.
authorGabe Black <gabeblack@google.com>
Tue, 28 Mar 2017 23:55:31 +0000 (16:55 -0700)
committerGabe Black <gabeblack@google.com>
Wed, 5 Apr 2017 18:39:14 +0000 (18:39 +0000)
A new stat was added by the CL:

    commit b043dcf58ad766582aeab162fb855cc3fc95f2cf
    Author: Andreas Sandberg <andreas.sandberg@arm.com>
    Date:   Mon Feb 27 13:17:51 2017 +0000

        gpu-compute: Fix Python/C++ object hierarchy discrepancies

Change-Id: I665a7eb0bea19f379c5fbaaf4686fcbe8c008159
Reviewed-on: https://gem5-review.googlesource.com/2654
Maintainer: Jason Lowe-Power <jason@lowepower.com>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
tests/quick/se/04.gpu/ref/x86/linux/gpu-ruby-GPU_RfO/config.ini
tests/quick/se/04.gpu/ref/x86/linux/gpu-ruby-GPU_RfO/simerr
tests/quick/se/04.gpu/ref/x86/linux/gpu-ruby-GPU_RfO/simout
tests/quick/se/04.gpu/ref/x86/linux/gpu-ruby-GPU_RfO/stats.txt

index 2cb06890a51e9f75a2a8c4ac4f9823a22f3b5064..66d67b9514da405d11c63534c7755f462e7552e7 100644 (file)
@@ -20,6 +20,7 @@ exit_on_work_items=false
 init_param=0
 kernel=
 kernel_addr_check=true
+kvm_vm=Null
 load_addr_mask=1099511627775
 load_offset=0
 mem_mode=timing
@@ -325,6 +326,7 @@ progress_interval=0
 simpoint_start_insts=
 socket_id=0
 switched_out=false
+syscallRetryLatency=10000
 system=system
 tracer=system.cpu0.tracer
 workload=system.cpu0.workload
@@ -411,7 +413,7 @@ type=ExeTracer
 eventq_index=0
 
 [system.cpu0.workload]
-type=LiveProcess
+type=Process
 cmd=gpu-hello
 cwd=
 drivers=system.cpu2.cl_driver
@@ -424,10 +426,11 @@ executable=/usr/local/google/home/gabeblack/gem5/dist/m5/regression/test-progs/g
 gid=100
 input=cin
 kvmInSE=false
-max_stack_size=67108864
+maxStackSize=67108864
 output=cout
+pgid=100
 pid=100
-ppid=99
+ppid=0
 simpoint=0
 system=system
 uid=100
@@ -4791,7 +4794,6 @@ size=16384
 type=RubyGPUCoalescer
 assume_rfo=true
 clk_domain=system.clk_domain
-coreid=99
 dcache=system.tcp_cntrl0.L1cache
 dcache_hit_latency=1
 deadlock_threshold=500000
@@ -4799,7 +4801,6 @@ default_p_state=UNDEFINED
 eventq_index=0
 garnet_standalone=false
 icache=system.tcp_cntrl0.L1cache
-icache_hit_latency=1
 is_cpu_sequencer=false
 max_outstanding_requests=2048
 no_retry_on_stall=false
@@ -4948,7 +4949,6 @@ size=16384
 type=RubyGPUCoalescer
 assume_rfo=true
 clk_domain=system.clk_domain
-coreid=99
 dcache=system.tcp_cntrl1.L1cache
 dcache_hit_latency=1
 deadlock_threshold=500000
@@ -4956,7 +4956,6 @@ default_p_state=UNDEFINED
 eventq_index=0
 garnet_standalone=false
 icache=system.tcp_cntrl1.L1cache
-icache_hit_latency=1
 is_cpu_sequencer=false
 max_outstanding_requests=2048
 no_retry_on_stall=false
index 4afc5c2338566758eb2e9c069224347500758178..2aa21337c83778e4f9225f80466e1e5b5f5fafd1 100755 (executable)
@@ -3,4 +3,5 @@ warn: system.ruby.network adopting orphan SimObject param 'ext_links'
 warn: DRAM device capacity (8192 Mbytes) does not match the address range assigned (512 Mbytes)
 warn: Sockets disabled, not accepting gdb connections
 warn: ClockedObject: More than one power state change request encountered within the same simulation tick
+info: Entering event queue @ 0.  Starting simulation...
 warn: Replacement policy updates recently became the responsibility of SLICC state machines. Make sure to setMRU() near callbacks in .sm files!
index 23cce98ec66697cd2817853f6c8fda099d278f86..6c1fcd44945c4e2d25e1e246cf476ba22d7f987e 100755 (executable)
@@ -3,10 +3,10 @@ Redirecting stderr to build/HSAIL_X86/tests/opt/quick/se/04.gpu/x86/linux/gpu-ru
 gem5 Simulator System.  http://gem5.org
 gem5 is copyrighted software; use the --copyright option for details.
 
-gem5 compiled Mar 28 2017 14:30:03
-gem5 started Mar 28 2017 14:30:19
-gem5 executing on gabeblack-desktop.mtv.corp.google.com, pid 43422
-command line: /usr/local/google/home/gabeblack/gem5/gem5-public/build/HSAIL_X86/gem5.opt -d build/HSAIL_X86/tests/opt/quick/se/04.gpu/x86/linux/gpu-ruby-GPU_RfO -re /usr/local/google/home/gabeblack/gem5/gem5-public/tests/testing/../run.py quick/se/04.gpu/x86/linux/gpu-ruby-GPU_RfO
+gem5 compiled Mar 28 2017 16:47:29
+gem5 started Mar 28 2017 16:47:45
+gem5 executing on gabeblack-desktop.mtv.corp.google.com, pid 50774
+command line: /usr/local/google/home/gabeblack/gem5/gem5-public/build/HSAIL_X86/gem5.opt -d build/HSAIL_X86/tests/opt/quick/se/04.gpu/x86/linux/gpu-ruby-GPU_RfO --stats-file 'text://stats.txt?desc=False' -re /usr/local/google/home/gabeblack/gem5/gem5-public/tests/testing/../run.py quick/se/04.gpu/x86/linux/gpu-ruby-GPU_RfO
 
 Using GPU kernel code file(s) /usr/local/google/home/gabeblack/gem5/dist/m5/regression/test-progs/gpu-hello/bin/x86/linux/gpu-hello-kernel.asm
 Global frequency set at 1000000000000 ticks per second
@@ -16,7 +16,6 @@ Forcing maxCoalescedReqs to 32 (TLB assoc.)
 Forcing maxCoalescedReqs to 32 (TLB assoc.) 
 Forcing maxCoalescedReqs to 32 (TLB assoc.) 
 Forcing maxCoalescedReqs to 32 (TLB assoc.) 
-info: Entering event queue @ 0.  Starting simulation...
 keys = 0x7b2bc0, &keys = 0x798998, keys[0] = 23
 the gpu says:
 \7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fello\7fe
index 6d46bf652065308d30ccf2479297d5278d4cb0f2..ef3da5994b7597872add49ea0b899d5ba3a700ff 100644 (file)
 
 ---------- Begin Simulation Statistics ----------
-sim_seconds                                  0.000667                       # Number of seconds simulated
-sim_ticks                                   667407500                       # Number of ticks simulated
-final_tick                                  667407500                       # Number of ticks from beginning of simulation (restored from checkpoints and never reset)
-sim_freq                                 1000000000000                       # Frequency of simulated ticks
-host_inst_rate                                 176952                       # Simulator instruction rate (inst/s)
-host_op_rate                                   363878                       # Simulator op (including micro ops) rate (op/s)
-host_tick_rate                             1763538835                       # Simulator tick rate (ticks/s)
-host_mem_usage                                1336256                       # Number of bytes of host memory used
-host_seconds                                     0.38                       # Real time elapsed on the host
-sim_insts                                       66963                       # Number of instructions simulated
-sim_ops                                        137705                       # Number of ops (including micro ops) simulated
-system.voltage_domain.voltage                       1                       # Voltage in Volts
-system.clk_domain.clock                          1000                       # Clock period in ticks
-system.mem_ctrls.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.mem_ctrls.bytes_read::dir_cntrl0         99136                       # Number of bytes read from this memory
-system.mem_ctrls.bytes_read::total              99136                       # Number of bytes read from this memory
-system.mem_ctrls.num_reads::dir_cntrl0           1549                       # Number of read requests responded to by this memory
-system.mem_ctrls.num_reads::total                1549                       # Number of read requests responded to by this memory
-system.mem_ctrls.bw_read::dir_cntrl0        148538936                       # Total read bandwidth from this memory (bytes/s)
-system.mem_ctrls.bw_read::total             148538936                       # Total read bandwidth from this memory (bytes/s)
-system.mem_ctrls.bw_total::dir_cntrl0       148538936                       # Total bandwidth to/from this memory (bytes/s)
-system.mem_ctrls.bw_total::total            148538936                       # Total bandwidth to/from this memory (bytes/s)
-system.mem_ctrls.readReqs                        1549                       # Number of read requests accepted
-system.mem_ctrls.writeReqs                          0                       # Number of write requests accepted
-system.mem_ctrls.readBursts                      1549                       # Number of DRAM read bursts, including those serviced by the write queue
-system.mem_ctrls.writeBursts                        0                       # Number of DRAM write bursts, including those merged in the write queue
-system.mem_ctrls.bytesReadDRAM                  99136                       # Total number of bytes read from DRAM
-system.mem_ctrls.bytesReadWrQ                       0                       # Total number of bytes read from write queue
-system.mem_ctrls.bytesWritten                       0                       # Total number of bytes written to DRAM
-system.mem_ctrls.bytesReadSys                   99136                       # Total read bytes from the system interface side
-system.mem_ctrls.bytesWrittenSys                    0                       # Total written bytes from the system interface side
-system.mem_ctrls.servicedByWrQ                      0                       # Number of DRAM read bursts serviced by the write queue
-system.mem_ctrls.mergedWrBursts                     0                       # Number of DRAM write bursts merged with an existing one
-system.mem_ctrls.neitherReadNorWriteReqs            0                       # Number of requests that are neither read nor write
-system.mem_ctrls.perBankRdBursts::0               122                       # Per bank write bursts
-system.mem_ctrls.perBankRdBursts::1               192                       # Per bank write bursts
-system.mem_ctrls.perBankRdBursts::2                91                       # Per bank write bursts
-system.mem_ctrls.perBankRdBursts::3                44                       # Per bank write bursts
-system.mem_ctrls.perBankRdBursts::4                61                       # Per bank write bursts
-system.mem_ctrls.perBankRdBursts::5                79                       # Per bank write bursts
-system.mem_ctrls.perBankRdBursts::6                52                       # Per bank write bursts
-system.mem_ctrls.perBankRdBursts::7                42                       # Per bank write bursts
-system.mem_ctrls.perBankRdBursts::8                54                       # Per bank write bursts
-system.mem_ctrls.perBankRdBursts::9                56                       # Per bank write bursts
-system.mem_ctrls.perBankRdBursts::10              174                       # Per bank write bursts
-system.mem_ctrls.perBankRdBursts::11               90                       # Per bank write bursts
-system.mem_ctrls.perBankRdBursts::12              222                       # Per bank write bursts
-system.mem_ctrls.perBankRdBursts::13              125                       # Per bank write bursts
-system.mem_ctrls.perBankRdBursts::14               51                       # Per bank write bursts
-system.mem_ctrls.perBankRdBursts::15               94                       # Per bank write bursts
-system.mem_ctrls.perBankWrBursts::0                 0                       # Per bank write bursts
-system.mem_ctrls.perBankWrBursts::1                 0                       # Per bank write bursts
-system.mem_ctrls.perBankWrBursts::2                 0                       # Per bank write bursts
-system.mem_ctrls.perBankWrBursts::3                 0                       # Per bank write bursts
-system.mem_ctrls.perBankWrBursts::4                 0                       # Per bank write bursts
-system.mem_ctrls.perBankWrBursts::5                 0                       # Per bank write bursts
-system.mem_ctrls.perBankWrBursts::6                 0                       # Per bank write bursts
-system.mem_ctrls.perBankWrBursts::7                 0                       # Per bank write bursts
-system.mem_ctrls.perBankWrBursts::8                 0                       # Per bank write bursts
-system.mem_ctrls.perBankWrBursts::9                 0                       # Per bank write bursts
-system.mem_ctrls.perBankWrBursts::10                0                       # Per bank write bursts
-system.mem_ctrls.perBankWrBursts::11                0                       # Per bank write bursts
-system.mem_ctrls.perBankWrBursts::12                0                       # Per bank write bursts
-system.mem_ctrls.perBankWrBursts::13                0                       # Per bank write bursts
-system.mem_ctrls.perBankWrBursts::14                0                       # Per bank write bursts
-system.mem_ctrls.perBankWrBursts::15                0                       # Per bank write bursts
-system.mem_ctrls.numRdRetry                         0                       # Number of times read queue was full causing retry
-system.mem_ctrls.numWrRetry                         0                       # Number of times write queue was full causing retry
-system.mem_ctrls.totGap                     667174000                       # Total gap between requests
-system.mem_ctrls.readPktSize::0                     0                       # Read request sizes (log2)
-system.mem_ctrls.readPktSize::1                     0                       # Read request sizes (log2)
-system.mem_ctrls.readPktSize::2                     0                       # Read request sizes (log2)
-system.mem_ctrls.readPktSize::3                     0                       # Read request sizes (log2)
-system.mem_ctrls.readPktSize::4                     0                       # Read request sizes (log2)
-system.mem_ctrls.readPktSize::5                     0                       # Read request sizes (log2)
-system.mem_ctrls.readPktSize::6                  1549                       # Read request sizes (log2)
-system.mem_ctrls.writePktSize::0                    0                       # Write request sizes (log2)
-system.mem_ctrls.writePktSize::1                    0                       # Write request sizes (log2)
-system.mem_ctrls.writePktSize::2                    0                       # Write request sizes (log2)
-system.mem_ctrls.writePktSize::3                    0                       # Write request sizes (log2)
-system.mem_ctrls.writePktSize::4                    0                       # Write request sizes (log2)
-system.mem_ctrls.writePktSize::5                    0                       # Write request sizes (log2)
-system.mem_ctrls.writePktSize::6                    0                       # Write request sizes (log2)
-system.mem_ctrls.rdQLenPdf::0                    1540                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::1                       2                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::2                       1                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::3                       1                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::4                       2                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::5                       1                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::6                       1                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::7                       1                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::8                       0                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::9                       0                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::10                      0                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::11                      0                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::12                      0                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::13                      0                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::14                      0                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::15                      0                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::16                      0                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::17                      0                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::18                      0                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::19                      0                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::20                      0                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::21                      0                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::22                      0                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::23                      0                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::24                      0                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::25                      0                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::26                      0                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::27                      0                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::28                      0                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::29                      0                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::30                      0                       # What read queue length does an incoming req see
-system.mem_ctrls.rdQLenPdf::31                      0                       # What read queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::0                       0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::1                       0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::2                       0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::3                       0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::4                       0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::5                       0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::6                       0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::7                       0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::8                       0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::9                       0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::10                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::11                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::12                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::13                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::14                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::15                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::16                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::17                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::18                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::19                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::20                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::21                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::22                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::23                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::24                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::25                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::26                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::27                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::28                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::29                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::30                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::31                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::32                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::33                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::34                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::35                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::36                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::37                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::38                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::39                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::40                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::41                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::42                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::43                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::44                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::45                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::46                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::47                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::48                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::49                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::50                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::51                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::52                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::53                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::54                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::55                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::56                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::57                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::58                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::59                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::60                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::61                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::62                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.wrQLenPdf::63                      0                       # What write queue length does an incoming req see
-system.mem_ctrls.bytesPerActivate::samples          484                       # Bytes accessed per row activation
-system.mem_ctrls.bytesPerActivate::mean    203.371901                       # Bytes accessed per row activation
-system.mem_ctrls.bytesPerActivate::gmean   144.930715                       # Bytes accessed per row activation
-system.mem_ctrls.bytesPerActivate::stdev   194.713066                       # Bytes accessed per row activation
-system.mem_ctrls.bytesPerActivate::0-127          177     36.57%     36.57% # Bytes accessed per row activation
-system.mem_ctrls.bytesPerActivate::128-255          168     34.71%     71.28% # Bytes accessed per row activation
-system.mem_ctrls.bytesPerActivate::256-383           63     13.02%     84.30% # Bytes accessed per row activation
-system.mem_ctrls.bytesPerActivate::384-511           29      5.99%     90.29% # Bytes accessed per row activation
-system.mem_ctrls.bytesPerActivate::512-639           19      3.93%     94.21% # Bytes accessed per row activation
-system.mem_ctrls.bytesPerActivate::640-767           11      2.27%     96.49% # Bytes accessed per row activation
-system.mem_ctrls.bytesPerActivate::768-895           10      2.07%     98.55% # Bytes accessed per row activation
-system.mem_ctrls.bytesPerActivate::896-1023            2      0.41%     98.97% # Bytes accessed per row activation
-system.mem_ctrls.bytesPerActivate::1024-1151            5      1.03%    100.00% # Bytes accessed per row activation
-system.mem_ctrls.bytesPerActivate::total          484                       # Bytes accessed per row activation
-system.mem_ctrls.totQLat                     31625750                       # Total ticks spent queuing
-system.mem_ctrls.totMemAccLat                60669500                       # Total ticks spent from burst creation until serviced by the DRAM
-system.mem_ctrls.totBusLat                    7745000                       # Total ticks spent in databus transfers
-system.mem_ctrls.avgQLat                     20416.88                       # Average queueing delay per DRAM burst
-system.mem_ctrls.avgBusLat                    5000.00                       # Average bus latency per DRAM burst
-system.mem_ctrls.avgMemAccLat                39166.88                       # Average memory access latency per DRAM burst
-system.mem_ctrls.avgRdBW                       148.54                       # Average DRAM read bandwidth in MiByte/s
-system.mem_ctrls.avgWrBW                         0.00                       # Average achieved write bandwidth in MiByte/s
-system.mem_ctrls.avgRdBWSys                    148.54                       # Average system read bandwidth in MiByte/s
-system.mem_ctrls.avgWrBWSys                      0.00                       # Average system write bandwidth in MiByte/s
-system.mem_ctrls.peakBW                      12800.00                       # Theoretical peak bandwidth in MiByte/s
-system.mem_ctrls.busUtil                         1.16                       # Data bus utilization in percentage
-system.mem_ctrls.busUtilRead                     1.16                       # Data bus utilization in percentage for reads
-system.mem_ctrls.busUtilWrite                    0.00                       # Data bus utilization in percentage for writes
-system.mem_ctrls.avgRdQLen                       1.00                       # Average read queue length when enqueuing
-system.mem_ctrls.avgWrQLen                       0.00                       # Average write queue length when enqueuing
-system.mem_ctrls.readRowHits                     1060                       # Number of row buffer hits during reads
-system.mem_ctrls.writeRowHits                       0                       # Number of row buffer hits during writes
-system.mem_ctrls.readRowHitRate                 68.43                       # Row buffer hit rate for reads
-system.mem_ctrls.writeRowHitRate                  nan                       # Row buffer hit rate for writes
-system.mem_ctrls.avgGap                     430712.72                       # Average gap between requests
-system.mem_ctrls.pageHitRate                    68.43                       # Row buffer hit rate, read and write combined
-system.mem_ctrls_0.actEnergy                  1320900                       # Energy for activate commands per rank (pJ)
-system.mem_ctrls_0.preEnergy                   694485                       # Energy for precharge commands per rank (pJ)
-system.mem_ctrls_0.readEnergy                 4876620                       # Energy for read commands per rank (pJ)
-system.mem_ctrls_0.writeEnergy                      0                       # Energy for write commands per rank (pJ)
-system.mem_ctrls_0.refreshEnergy         51629760.000000                       # Energy for refresh commands per rank (pJ)
-system.mem_ctrls_0.actBackEnergy             18588840                       # Energy for active background per rank (pJ)
-system.mem_ctrls_0.preBackEnergy              1670400                       # Energy for precharge background per rank (pJ)
-system.mem_ctrls_0.actPowerDownEnergy       210561990                       # Energy for active power-down per rank (pJ)
-system.mem_ctrls_0.prePowerDownEnergy        42231360                       # Energy for precharge power-down per rank (pJ)
-system.mem_ctrls_0.selfRefreshEnergy         15446940                       # Energy for self refresh per rank (pJ)
-system.mem_ctrls_0.totalEnergy              347021295                       # Total energy per rank (pJ)
-system.mem_ctrls_0.averagePower            519.954143                       # Core power per rank (mW)
-system.mem_ctrls_0.totalIdleTime            622134250                       # Total Idle time Per DRAM Rank
-system.mem_ctrls_0.memoryStateTime::IDLE      2030000                       # Time in different power states
-system.mem_ctrls_0.memoryStateTime::REF      21876000                       # Time in different power states
-system.mem_ctrls_0.memoryStateTime::SREF     50557000                       # Time in different power states
-system.mem_ctrls_0.memoryStateTime::PRE_PDN    109975750                       # Time in different power states
-system.mem_ctrls_0.memoryStateTime::ACT      21192250                       # Time in different power states
-system.mem_ctrls_0.memoryStateTime::ACT_PDN    461776500                       # Time in different power states
-system.mem_ctrls_1.actEnergy                  2170560                       # Energy for activate commands per rank (pJ)
-system.mem_ctrls_1.preEnergy                  1142295                       # Energy for precharge commands per rank (pJ)
-system.mem_ctrls_1.readEnergy                 6183240                       # Energy for read commands per rank (pJ)
-system.mem_ctrls_1.writeEnergy                      0                       # Energy for write commands per rank (pJ)
-system.mem_ctrls_1.refreshEnergy         52244400.000000                       # Energy for refresh commands per rank (pJ)
-system.mem_ctrls_1.actBackEnergy             21584190                       # Energy for active background per rank (pJ)
-system.mem_ctrls_1.preBackEnergy              1299360                       # Energy for precharge background per rank (pJ)
-system.mem_ctrls_1.actPowerDownEnergy       243510840                       # Energy for active power-down per rank (pJ)
-system.mem_ctrls_1.prePowerDownEnergy        28002720                       # Energy for precharge power-down per rank (pJ)
-system.mem_ctrls_1.selfRefreshEnergy          2892540                       # Energy for self refresh per rank (pJ)
-system.mem_ctrls_1.totalEnergy              359030145                       # Total energy per rank (pJ)
-system.mem_ctrls_1.averagePower            537.947423                       # Core power per rank (mW)
-system.mem_ctrls_1.totalIdleTime            616133750                       # Total Idle time Per DRAM Rank
-system.mem_ctrls_1.memoryStateTime::IDLE       980000                       # Time in different power states
-system.mem_ctrls_1.memoryStateTime::REF      22106000                       # Time in different power states
-system.mem_ctrls_1.memoryStateTime::SREF      9751250                       # Time in different power states
-system.mem_ctrls_1.memoryStateTime::PRE_PDN     72913500                       # Time in different power states
-system.mem_ctrls_1.memoryStateTime::ACT      27618000                       # Time in different power states
-system.mem_ctrls_1.memoryStateTime::ACT_PDN    534038750                       # Time in different power states
-system.ruby.clk_domain.clock                      500                       # Clock period in ticks
-system.ruby.phys_mem.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.ruby.phys_mem.bytes_read::cpu0.inst       696760                       # Number of bytes read from this memory
-system.ruby.phys_mem.bytes_read::cpu0.data       119832                       # Number of bytes read from this memory
-system.ruby.phys_mem.bytes_read::cpu1.CUs0.ComputeUnit         2856                       # Number of bytes read from this memory
-system.ruby.phys_mem.bytes_read::cpu1.CUs1.ComputeUnit         2856                       # Number of bytes read from this memory
-system.ruby.phys_mem.bytes_read::total         822304                       # Number of bytes read from this memory
-system.ruby.phys_mem.bytes_inst_read::cpu0.inst       696760                       # Number of instructions bytes read from this memory
-system.ruby.phys_mem.bytes_inst_read::cpu1.CUs0.ComputeUnit         1576                       # Number of instructions bytes read from this memory
-system.ruby.phys_mem.bytes_inst_read::cpu1.CUs1.ComputeUnit         1576                       # Number of instructions bytes read from this memory
-system.ruby.phys_mem.bytes_inst_read::total       699912                       # Number of instructions bytes read from this memory
-system.ruby.phys_mem.bytes_written::cpu0.data        72767                       # Number of bytes written to this memory
-system.ruby.phys_mem.bytes_written::cpu1.CUs0.ComputeUnit          256                       # Number of bytes written to this memory
-system.ruby.phys_mem.bytes_written::cpu1.CUs1.ComputeUnit          256                       # Number of bytes written to this memory
-system.ruby.phys_mem.bytes_written::total        73279                       # Number of bytes written to this memory
-system.ruby.phys_mem.num_reads::cpu0.inst        87095                       # Number of read requests responded to by this memory
-system.ruby.phys_mem.num_reads::cpu0.data        16686                       # Number of read requests responded to by this memory
-system.ruby.phys_mem.num_reads::cpu1.CUs0.ComputeUnit          547                       # Number of read requests responded to by this memory
-system.ruby.phys_mem.num_reads::cpu1.CUs1.ComputeUnit          547                       # Number of read requests responded to by this memory
-system.ruby.phys_mem.num_reads::total          104875                       # Number of read requests responded to by this memory
-system.ruby.phys_mem.num_writes::cpu0.data        10422                       # Number of write requests responded to by this memory
-system.ruby.phys_mem.num_writes::cpu1.CUs0.ComputeUnit          256                       # Number of write requests responded to by this memory
-system.ruby.phys_mem.num_writes::cpu1.CUs1.ComputeUnit          256                       # Number of write requests responded to by this memory
-system.ruby.phys_mem.num_writes::total          10934                       # Number of write requests responded to by this memory
-system.ruby.phys_mem.bw_read::cpu0.inst    1043979877                       # Total read bandwidth from this memory (bytes/s)
-system.ruby.phys_mem.bw_read::cpu0.data     179548477                       # Total read bandwidth from this memory (bytes/s)
-system.ruby.phys_mem.bw_read::cpu1.CUs0.ComputeUnit      4279245                       # Total read bandwidth from this memory (bytes/s)
-system.ruby.phys_mem.bw_read::cpu1.CUs1.ComputeUnit      4279245                       # Total read bandwidth from this memory (bytes/s)
-system.ruby.phys_mem.bw_read::total        1232086843                       # Total read bandwidth from this memory (bytes/s)
-system.ruby.phys_mem.bw_inst_read::cpu0.inst   1043979877                       # Instruction read bandwidth from this memory (bytes/s)
-system.ruby.phys_mem.bw_inst_read::cpu1.CUs0.ComputeUnit      2361376                       # Instruction read bandwidth from this memory (bytes/s)
-system.ruby.phys_mem.bw_inst_read::cpu1.CUs1.ComputeUnit      2361376                       # Instruction read bandwidth from this memory (bytes/s)
-system.ruby.phys_mem.bw_inst_read::total   1048702629                       # Instruction read bandwidth from this memory (bytes/s)
-system.ruby.phys_mem.bw_write::cpu0.data    109029341                       # Write bandwidth from this memory (bytes/s)
-system.ruby.phys_mem.bw_write::cpu1.CUs0.ComputeUnit       383574                       # Write bandwidth from this memory (bytes/s)
-system.ruby.phys_mem.bw_write::cpu1.CUs1.ComputeUnit       383574                       # Write bandwidth from this memory (bytes/s)
-system.ruby.phys_mem.bw_write::total        109796489                       # Write bandwidth from this memory (bytes/s)
-system.ruby.phys_mem.bw_total::cpu0.inst   1043979877                       # Total bandwidth to/from this memory (bytes/s)
-system.ruby.phys_mem.bw_total::cpu0.data    288577818                       # Total bandwidth to/from this memory (bytes/s)
-system.ruby.phys_mem.bw_total::cpu1.CUs0.ComputeUnit      4662818                       # Total bandwidth to/from this memory (bytes/s)
-system.ruby.phys_mem.bw_total::cpu1.CUs1.ComputeUnit      4662818                       # Total bandwidth to/from this memory (bytes/s)
-system.ruby.phys_mem.bw_total::total       1341883332                       # Total bandwidth to/from this memory (bytes/s)
-system.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.ruby.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
+sim_seconds                                  0.000667                      
+sim_ticks                                   667407500                      
+final_tick                                  667407500                      
+sim_freq                                 1000000000000                      
+host_inst_rate                                 219740                      
+host_op_rate                                   451865                      
+host_tick_rate                             2189959227                      
+host_mem_usage                                1336836                      
+host_seconds                                     0.30                      
+sim_insts                                       66963                      
+sim_ops                                        137705                      
+system.voltage_domain.voltage                       1                      
+system.clk_domain.clock                          1000                      
+system.mem_ctrls.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.mem_ctrls.bytes_read::dir_cntrl0         99136                      
+system.mem_ctrls.bytes_read::total              99136                      
+system.mem_ctrls.num_reads::dir_cntrl0           1549                      
+system.mem_ctrls.num_reads::total                1549                      
+system.mem_ctrls.bw_read::dir_cntrl0        148538936                      
+system.mem_ctrls.bw_read::total             148538936                      
+system.mem_ctrls.bw_total::dir_cntrl0       148538936                      
+system.mem_ctrls.bw_total::total            148538936                      
+system.mem_ctrls.readReqs                        1549                      
+system.mem_ctrls.writeReqs                          0                      
+system.mem_ctrls.readBursts                      1549                      
+system.mem_ctrls.writeBursts                        0                      
+system.mem_ctrls.bytesReadDRAM                  99136                      
+system.mem_ctrls.bytesReadWrQ                       0                      
+system.mem_ctrls.bytesWritten                       0                      
+system.mem_ctrls.bytesReadSys                   99136                      
+system.mem_ctrls.bytesWrittenSys                    0                      
+system.mem_ctrls.servicedByWrQ                      0                      
+system.mem_ctrls.mergedWrBursts                     0                      
+system.mem_ctrls.neitherReadNorWriteReqs            0                      
+system.mem_ctrls.perBankRdBursts::0               122                      
+system.mem_ctrls.perBankRdBursts::1               192                      
+system.mem_ctrls.perBankRdBursts::2                91                      
+system.mem_ctrls.perBankRdBursts::3                44                      
+system.mem_ctrls.perBankRdBursts::4                61                      
+system.mem_ctrls.perBankRdBursts::5                79                      
+system.mem_ctrls.perBankRdBursts::6                52                      
+system.mem_ctrls.perBankRdBursts::7                42                      
+system.mem_ctrls.perBankRdBursts::8                54                      
+system.mem_ctrls.perBankRdBursts::9                56                      
+system.mem_ctrls.perBankRdBursts::10              174                      
+system.mem_ctrls.perBankRdBursts::11               90                      
+system.mem_ctrls.perBankRdBursts::12              222                      
+system.mem_ctrls.perBankRdBursts::13              125                      
+system.mem_ctrls.perBankRdBursts::14               51                      
+system.mem_ctrls.perBankRdBursts::15               94                      
+system.mem_ctrls.perBankWrBursts::0                 0                      
+system.mem_ctrls.perBankWrBursts::1                 0                      
+system.mem_ctrls.perBankWrBursts::2                 0                      
+system.mem_ctrls.perBankWrBursts::3                 0                      
+system.mem_ctrls.perBankWrBursts::4                 0                      
+system.mem_ctrls.perBankWrBursts::5                 0                      
+system.mem_ctrls.perBankWrBursts::6                 0                      
+system.mem_ctrls.perBankWrBursts::7                 0                      
+system.mem_ctrls.perBankWrBursts::8                 0                      
+system.mem_ctrls.perBankWrBursts::9                 0                      
+system.mem_ctrls.perBankWrBursts::10                0                      
+system.mem_ctrls.perBankWrBursts::11                0                      
+system.mem_ctrls.perBankWrBursts::12                0                      
+system.mem_ctrls.perBankWrBursts::13                0                      
+system.mem_ctrls.perBankWrBursts::14                0                      
+system.mem_ctrls.perBankWrBursts::15                0                      
+system.mem_ctrls.numRdRetry                         0                      
+system.mem_ctrls.numWrRetry                         0                      
+system.mem_ctrls.totGap                     667174000                      
+system.mem_ctrls.readPktSize::0                     0                      
+system.mem_ctrls.readPktSize::1                     0                      
+system.mem_ctrls.readPktSize::2                     0                      
+system.mem_ctrls.readPktSize::3                     0                      
+system.mem_ctrls.readPktSize::4                     0                      
+system.mem_ctrls.readPktSize::5                     0                      
+system.mem_ctrls.readPktSize::6                  1549                      
+system.mem_ctrls.writePktSize::0                    0                      
+system.mem_ctrls.writePktSize::1                    0                      
+system.mem_ctrls.writePktSize::2                    0                      
+system.mem_ctrls.writePktSize::3                    0                      
+system.mem_ctrls.writePktSize::4                    0                      
+system.mem_ctrls.writePktSize::5                    0                      
+system.mem_ctrls.writePktSize::6                    0                      
+system.mem_ctrls.rdQLenPdf::0                    1540                      
+system.mem_ctrls.rdQLenPdf::1                       2                      
+system.mem_ctrls.rdQLenPdf::2                       1                      
+system.mem_ctrls.rdQLenPdf::3                       1                      
+system.mem_ctrls.rdQLenPdf::4                       2                      
+system.mem_ctrls.rdQLenPdf::5                       1                      
+system.mem_ctrls.rdQLenPdf::6                       1                      
+system.mem_ctrls.rdQLenPdf::7                       1                      
+system.mem_ctrls.rdQLenPdf::8                       0                      
+system.mem_ctrls.rdQLenPdf::9                       0                      
+system.mem_ctrls.rdQLenPdf::10                      0                      
+system.mem_ctrls.rdQLenPdf::11                      0                      
+system.mem_ctrls.rdQLenPdf::12                      0                      
+system.mem_ctrls.rdQLenPdf::13                      0                      
+system.mem_ctrls.rdQLenPdf::14                      0                      
+system.mem_ctrls.rdQLenPdf::15                      0                      
+system.mem_ctrls.rdQLenPdf::16                      0                      
+system.mem_ctrls.rdQLenPdf::17                      0                      
+system.mem_ctrls.rdQLenPdf::18                      0                      
+system.mem_ctrls.rdQLenPdf::19                      0                      
+system.mem_ctrls.rdQLenPdf::20                      0                      
+system.mem_ctrls.rdQLenPdf::21                      0                      
+system.mem_ctrls.rdQLenPdf::22                      0                      
+system.mem_ctrls.rdQLenPdf::23                      0                      
+system.mem_ctrls.rdQLenPdf::24                      0                      
+system.mem_ctrls.rdQLenPdf::25                      0                      
+system.mem_ctrls.rdQLenPdf::26                      0                      
+system.mem_ctrls.rdQLenPdf::27                      0                      
+system.mem_ctrls.rdQLenPdf::28                      0                      
+system.mem_ctrls.rdQLenPdf::29                      0                      
+system.mem_ctrls.rdQLenPdf::30                      0                      
+system.mem_ctrls.rdQLenPdf::31                      0                      
+system.mem_ctrls.wrQLenPdf::0                       0                      
+system.mem_ctrls.wrQLenPdf::1                       0                      
+system.mem_ctrls.wrQLenPdf::2                       0                      
+system.mem_ctrls.wrQLenPdf::3                       0                      
+system.mem_ctrls.wrQLenPdf::4                       0                      
+system.mem_ctrls.wrQLenPdf::5                       0                      
+system.mem_ctrls.wrQLenPdf::6                       0                      
+system.mem_ctrls.wrQLenPdf::7                       0                      
+system.mem_ctrls.wrQLenPdf::8                       0                      
+system.mem_ctrls.wrQLenPdf::9                       0                      
+system.mem_ctrls.wrQLenPdf::10                      0                      
+system.mem_ctrls.wrQLenPdf::11                      0                      
+system.mem_ctrls.wrQLenPdf::12                      0                      
+system.mem_ctrls.wrQLenPdf::13                      0                      
+system.mem_ctrls.wrQLenPdf::14                      0                      
+system.mem_ctrls.wrQLenPdf::15                      0                      
+system.mem_ctrls.wrQLenPdf::16                      0                      
+system.mem_ctrls.wrQLenPdf::17                      0                      
+system.mem_ctrls.wrQLenPdf::18                      0                      
+system.mem_ctrls.wrQLenPdf::19                      0                      
+system.mem_ctrls.wrQLenPdf::20                      0                      
+system.mem_ctrls.wrQLenPdf::21                      0                      
+system.mem_ctrls.wrQLenPdf::22                      0                      
+system.mem_ctrls.wrQLenPdf::23                      0                      
+system.mem_ctrls.wrQLenPdf::24                      0                      
+system.mem_ctrls.wrQLenPdf::25                      0                      
+system.mem_ctrls.wrQLenPdf::26                      0                      
+system.mem_ctrls.wrQLenPdf::27                      0                      
+system.mem_ctrls.wrQLenPdf::28                      0                      
+system.mem_ctrls.wrQLenPdf::29                      0                      
+system.mem_ctrls.wrQLenPdf::30                      0                      
+system.mem_ctrls.wrQLenPdf::31                      0                      
+system.mem_ctrls.wrQLenPdf::32                      0                      
+system.mem_ctrls.wrQLenPdf::33                      0                      
+system.mem_ctrls.wrQLenPdf::34                      0                      
+system.mem_ctrls.wrQLenPdf::35                      0                      
+system.mem_ctrls.wrQLenPdf::36                      0                      
+system.mem_ctrls.wrQLenPdf::37                      0                      
+system.mem_ctrls.wrQLenPdf::38                      0                      
+system.mem_ctrls.wrQLenPdf::39                      0                      
+system.mem_ctrls.wrQLenPdf::40                      0                      
+system.mem_ctrls.wrQLenPdf::41                      0                      
+system.mem_ctrls.wrQLenPdf::42                      0                      
+system.mem_ctrls.wrQLenPdf::43                      0                      
+system.mem_ctrls.wrQLenPdf::44                      0                      
+system.mem_ctrls.wrQLenPdf::45                      0                      
+system.mem_ctrls.wrQLenPdf::46                      0                      
+system.mem_ctrls.wrQLenPdf::47                      0                      
+system.mem_ctrls.wrQLenPdf::48                      0                      
+system.mem_ctrls.wrQLenPdf::49                      0                      
+system.mem_ctrls.wrQLenPdf::50                      0                      
+system.mem_ctrls.wrQLenPdf::51                      0                      
+system.mem_ctrls.wrQLenPdf::52                      0                      
+system.mem_ctrls.wrQLenPdf::53                      0                      
+system.mem_ctrls.wrQLenPdf::54                      0                      
+system.mem_ctrls.wrQLenPdf::55                      0                      
+system.mem_ctrls.wrQLenPdf::56                      0                      
+system.mem_ctrls.wrQLenPdf::57                      0                      
+system.mem_ctrls.wrQLenPdf::58                      0                      
+system.mem_ctrls.wrQLenPdf::59                      0                      
+system.mem_ctrls.wrQLenPdf::60                      0                      
+system.mem_ctrls.wrQLenPdf::61                      0                      
+system.mem_ctrls.wrQLenPdf::62                      0                      
+system.mem_ctrls.wrQLenPdf::63                      0                      
+system.mem_ctrls.bytesPerActivate::samples          484                      
+system.mem_ctrls.bytesPerActivate::mean    203.371901                      
+system.mem_ctrls.bytesPerActivate::gmean   144.930715                      
+system.mem_ctrls.bytesPerActivate::stdev   194.713066                      
+system.mem_ctrls.bytesPerActivate::0-127          177     36.57%     36.57%
+system.mem_ctrls.bytesPerActivate::128-255          168     34.71%     71.28%
+system.mem_ctrls.bytesPerActivate::256-383           63     13.02%     84.30%
+system.mem_ctrls.bytesPerActivate::384-511           29      5.99%     90.29%
+system.mem_ctrls.bytesPerActivate::512-639           19      3.93%     94.21%
+system.mem_ctrls.bytesPerActivate::640-767           11      2.27%     96.49%
+system.mem_ctrls.bytesPerActivate::768-895           10      2.07%     98.55%
+system.mem_ctrls.bytesPerActivate::896-1023            2      0.41%     98.97%
+system.mem_ctrls.bytesPerActivate::1024-1151            5      1.03%    100.00%
+system.mem_ctrls.bytesPerActivate::total          484                      
+system.mem_ctrls.totQLat                     31625750                      
+system.mem_ctrls.totMemAccLat                60669500                      
+system.mem_ctrls.totBusLat                    7745000                      
+system.mem_ctrls.avgQLat                     20416.88                      
+system.mem_ctrls.avgBusLat                    5000.00                      
+system.mem_ctrls.avgMemAccLat                39166.88                      
+system.mem_ctrls.avgRdBW                       148.54                      
+system.mem_ctrls.avgWrBW                         0.00                      
+system.mem_ctrls.avgRdBWSys                    148.54                      
+system.mem_ctrls.avgWrBWSys                      0.00                      
+system.mem_ctrls.peakBW                      12800.00                      
+system.mem_ctrls.busUtil                         1.16                      
+system.mem_ctrls.busUtilRead                     1.16                      
+system.mem_ctrls.busUtilWrite                    0.00                      
+system.mem_ctrls.avgRdQLen                       1.00                      
+system.mem_ctrls.avgWrQLen                       0.00                      
+system.mem_ctrls.readRowHits                     1060                      
+system.mem_ctrls.writeRowHits                       0                      
+system.mem_ctrls.readRowHitRate                 68.43                      
+system.mem_ctrls.writeRowHitRate                  nan                      
+system.mem_ctrls.avgGap                     430712.72                      
+system.mem_ctrls.pageHitRate                    68.43                      
+system.mem_ctrls_0.actEnergy                  1320900                      
+system.mem_ctrls_0.preEnergy                   694485                      
+system.mem_ctrls_0.readEnergy                 4876620                      
+system.mem_ctrls_0.writeEnergy                      0                      
+system.mem_ctrls_0.refreshEnergy         51629760.000000                      
+system.mem_ctrls_0.actBackEnergy             18588840                      
+system.mem_ctrls_0.preBackEnergy              1670400                      
+system.mem_ctrls_0.actPowerDownEnergy       210561990                      
+system.mem_ctrls_0.prePowerDownEnergy        42231360                      
+system.mem_ctrls_0.selfRefreshEnergy         15446940                      
+system.mem_ctrls_0.totalEnergy              347021295                      
+system.mem_ctrls_0.averagePower            519.954143                      
+system.mem_ctrls_0.totalIdleTime            622134250                      
+system.mem_ctrls_0.memoryStateTime::IDLE      2030000                      
+system.mem_ctrls_0.memoryStateTime::REF      21876000                      
+system.mem_ctrls_0.memoryStateTime::SREF     50557000                      
+system.mem_ctrls_0.memoryStateTime::PRE_PDN    109975750                      
+system.mem_ctrls_0.memoryStateTime::ACT      21192250                      
+system.mem_ctrls_0.memoryStateTime::ACT_PDN    461776500                      
+system.mem_ctrls_1.actEnergy                  2170560                      
+system.mem_ctrls_1.preEnergy                  1142295                      
+system.mem_ctrls_1.readEnergy                 6183240                      
+system.mem_ctrls_1.writeEnergy                      0                      
+system.mem_ctrls_1.refreshEnergy         52244400.000000                      
+system.mem_ctrls_1.actBackEnergy             21584190                      
+system.mem_ctrls_1.preBackEnergy              1299360                      
+system.mem_ctrls_1.actPowerDownEnergy       243510840                      
+system.mem_ctrls_1.prePowerDownEnergy        28002720                      
+system.mem_ctrls_1.selfRefreshEnergy          2892540                      
+system.mem_ctrls_1.totalEnergy              359030145                      
+system.mem_ctrls_1.averagePower            537.947423                      
+system.mem_ctrls_1.totalIdleTime            616133750                      
+system.mem_ctrls_1.memoryStateTime::IDLE       980000                      
+system.mem_ctrls_1.memoryStateTime::REF      22106000                      
+system.mem_ctrls_1.memoryStateTime::SREF      9751250                      
+system.mem_ctrls_1.memoryStateTime::PRE_PDN     72913500                      
+system.mem_ctrls_1.memoryStateTime::ACT      27618000                      
+system.mem_ctrls_1.memoryStateTime::ACT_PDN    534038750                      
+system.ruby.clk_domain.clock                      500                      
+system.ruby.phys_mem.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.ruby.phys_mem.bytes_read::cpu0.inst       696760                      
+system.ruby.phys_mem.bytes_read::cpu0.data       119832                      
+system.ruby.phys_mem.bytes_read::cpu1.CUs0.ComputeUnit         2856                      
+system.ruby.phys_mem.bytes_read::cpu1.CUs1.ComputeUnit         2856                      
+system.ruby.phys_mem.bytes_read::total         822304                      
+system.ruby.phys_mem.bytes_inst_read::cpu0.inst       696760                      
+system.ruby.phys_mem.bytes_inst_read::cpu1.CUs0.ComputeUnit         1576                      
+system.ruby.phys_mem.bytes_inst_read::cpu1.CUs1.ComputeUnit         1576                      
+system.ruby.phys_mem.bytes_inst_read::total       699912                      
+system.ruby.phys_mem.bytes_written::cpu0.data        72767                      
+system.ruby.phys_mem.bytes_written::cpu1.CUs0.ComputeUnit          256                      
+system.ruby.phys_mem.bytes_written::cpu1.CUs1.ComputeUnit          256                      
+system.ruby.phys_mem.bytes_written::total        73279                      
+system.ruby.phys_mem.num_reads::cpu0.inst        87095                      
+system.ruby.phys_mem.num_reads::cpu0.data        16686                      
+system.ruby.phys_mem.num_reads::cpu1.CUs0.ComputeUnit          547                      
+system.ruby.phys_mem.num_reads::cpu1.CUs1.ComputeUnit          547                      
+system.ruby.phys_mem.num_reads::total          104875                      
+system.ruby.phys_mem.num_writes::cpu0.data        10422                      
+system.ruby.phys_mem.num_writes::cpu1.CUs0.ComputeUnit          256                      
+system.ruby.phys_mem.num_writes::cpu1.CUs1.ComputeUnit          256                      
+system.ruby.phys_mem.num_writes::total          10934                      
+system.ruby.phys_mem.bw_read::cpu0.inst    1043979877                      
+system.ruby.phys_mem.bw_read::cpu0.data     179548477                      
+system.ruby.phys_mem.bw_read::cpu1.CUs0.ComputeUnit      4279245                      
+system.ruby.phys_mem.bw_read::cpu1.CUs1.ComputeUnit      4279245                      
+system.ruby.phys_mem.bw_read::total        1232086843                      
+system.ruby.phys_mem.bw_inst_read::cpu0.inst   1043979877                      
+system.ruby.phys_mem.bw_inst_read::cpu1.CUs0.ComputeUnit      2361376                      
+system.ruby.phys_mem.bw_inst_read::cpu1.CUs1.ComputeUnit      2361376                      
+system.ruby.phys_mem.bw_inst_read::total   1048702629                      
+system.ruby.phys_mem.bw_write::cpu0.data    109029341                      
+system.ruby.phys_mem.bw_write::cpu1.CUs0.ComputeUnit       383574                      
+system.ruby.phys_mem.bw_write::cpu1.CUs1.ComputeUnit       383574                      
+system.ruby.phys_mem.bw_write::total        109796489                      
+system.ruby.phys_mem.bw_total::cpu0.inst   1043979877                      
+system.ruby.phys_mem.bw_total::cpu0.data    288577818                      
+system.ruby.phys_mem.bw_total::cpu1.CUs0.ComputeUnit      4662818                      
+system.ruby.phys_mem.bw_total::cpu1.CUs1.ComputeUnit      4662818                      
+system.ruby.phys_mem.bw_total::total       1341883332                      
+system.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.ruby.pwrStateResidencyTicks::UNDEFINED    667407500                      
 system.ruby.outstanding_req_hist_seqr::bucket_size            1                      
 system.ruby.outstanding_req_hist_seqr::max_bucket            9                      
 system.ruby.outstanding_req_hist_seqr::samples       114203                      
@@ -355,2424 +355,2425 @@ system.ruby.miss_latency_hist_coalsr     |          13     48.15%     48.15% |
 system.ruby.miss_latency_hist_coalsr::total           27                      
 system.ruby.L1Cache.incomplete_times_seqr       112609                      
 system.ruby.L2Cache.incomplete_times_seqr           59                      
-system.cp_cntrl0.L1D0cache.demand_hits              0                       # Number of cache demand hits
-system.cp_cntrl0.L1D0cache.demand_misses          506                       # Number of cache demand misses
-system.cp_cntrl0.L1D0cache.demand_accesses          506                       # Number of cache demand accesses
-system.cp_cntrl0.L1D0cache.num_data_array_reads        16155                       # number of data array reads
-system.cp_cntrl0.L1D0cache.num_data_array_writes        11985                       # number of data array writes
-system.cp_cntrl0.L1D0cache.num_tag_array_reads        27132                       # number of tag array reads
-system.cp_cntrl0.L1D0cache.num_tag_array_writes         1584                       # number of tag array writes
-system.cp_cntrl0.L1D1cache.demand_hits              0                       # Number of cache demand hits
-system.cp_cntrl0.L1D1cache.demand_misses            0                       # Number of cache demand misses
-system.cp_cntrl0.L1D1cache.demand_accesses            0                       # Number of cache demand accesses
-system.cp_cntrl0.L1Icache.demand_hits               0                       # Number of cache demand hits
-system.cp_cntrl0.L1Icache.demand_misses          1088                       # Number of cache demand misses
-system.cp_cntrl0.L1Icache.demand_accesses         1088                       # Number of cache demand accesses
-system.cp_cntrl0.L1Icache.num_data_array_reads        86007                       # number of data array reads
-system.cp_cntrl0.L1Icache.num_data_array_writes           54                       # number of data array writes
-system.cp_cntrl0.L1Icache.num_tag_array_reads        87684                       # number of tag array reads
-system.cp_cntrl0.L1Icache.num_tag_array_writes           54                       # number of tag array writes
-system.cp_cntrl0.L2cache.demand_hits                0                       # Number of cache demand hits
-system.cp_cntrl0.L2cache.demand_misses           1535                       # Number of cache demand misses
-system.cp_cntrl0.L2cache.demand_accesses         1535                       # Number of cache demand accesses
-system.cp_cntrl0.L2cache.num_data_array_reads          120                       # number of data array reads
-system.cp_cntrl0.L2cache.num_data_array_writes        11982                       # number of data array writes
-system.cp_cntrl0.L2cache.num_tag_array_reads        12057                       # number of tag array reads
-system.cp_cntrl0.L2cache.num_tag_array_writes         1649                       # number of tag array writes
-system.cp_cntrl0.mandatoryQueue.avg_buf_msgs     0.427713                       # Average number of messages in buffer
-system.cp_cntrl0.mandatoryQueue.avg_stall_time  1999.994007                       # Average number of cycles messages are stalled in this MB
-system.cp_cntrl0.probeToCore.avg_buf_msgs     0.000010                       # Average number of messages in buffer
-system.cp_cntrl0.probeToCore.avg_stall_time  3665.454806                       # Average number of cycles messages are stalled in this MB
-system.cp_cntrl0.requestFromCore.avg_buf_msgs     0.034499                       # Average number of messages in buffer
-system.cp_cntrl0.requestFromCore.avg_stall_time 14999.617925                       # Average number of cycles messages are stalled in this MB
-system.cp_cntrl0.responseFromCore.avg_buf_msgs     0.000315                       # Average number of messages in buffer
-system.cp_cntrl0.responseFromCore.avg_stall_time  1717.844815                       # Average number of cycles messages are stalled in this MB
-system.cp_cntrl0.responseToCore.avg_buf_msgs     0.001150                       # Average number of messages in buffer
-system.cp_cntrl0.responseToCore.avg_stall_time 31990.122976                       # Average number of cycles messages are stalled in this MB
-system.cp_cntrl0.sequencer.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.cp_cntrl0.sequencer1.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.cp_cntrl0.triggerQueue.avg_buf_msgs     0.001591                       # Average number of messages in buffer
-system.cp_cntrl0.triggerQueue.avg_stall_time 15959.959998                       # Average number of cycles messages are stalled in this MB
-system.cp_cntrl0.unblockFromCore.avg_buf_msgs     0.034499                       # Average number of messages in buffer
-system.cp_cntrl0.unblockFromCore.avg_stall_time 14995.033020                       # Average number of cycles messages are stalled in this MB
-system.cp_cntrl0.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.cpu0.clk_domain.clock                      500                       # Clock period in ticks
-system.cpu0.dtb.walker.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.cpu0.apic_clk_domain.clock                8000                       # Clock period in ticks
-system.cpu0.interrupts.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.cpu0.itb.walker.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.cpu0.workload.numSyscalls                   21                       # Number of system calls
-system.cpu0.numPwrStateTransitions                  2                       # Number of power state transitions
-system.cpu0.pwrStateClkGateDist::samples            1                       # Distribution of time spent in the clock gated state
-system.cpu0.pwrStateClkGateDist::mean         2095501                       # Distribution of time spent in the clock gated state
-system.cpu0.pwrStateClkGateDist::1000-5e+10            1    100.00%    100.00% # Distribution of time spent in the clock gated state
-system.cpu0.pwrStateClkGateDist::min_value      2095501                       # Distribution of time spent in the clock gated state
-system.cpu0.pwrStateClkGateDist::max_value      2095501                       # Distribution of time spent in the clock gated state
-system.cpu0.pwrStateClkGateDist::total              1                       # Distribution of time spent in the clock gated state
-system.cpu0.pwrStateResidencyTicks::ON      665311999                       # Cumulative time (in ticks) in various power states
-system.cpu0.pwrStateResidencyTicks::CLK_GATED      2095501                       # Cumulative time (in ticks) in various power states
-system.cpu0.numCycles                         1334815                       # number of cpu cycles simulated
-system.cpu0.numWorkItemsStarted                     0                       # number of work items this cpu started
-system.cpu0.numWorkItemsCompleted                   0                       # number of work items this cpu completed
-system.cpu0.committedInsts                      66963                       # Number of instructions committed
-system.cpu0.committedOps                       137705                       # Number of ops (including micro ops) committed
-system.cpu0.num_int_alu_accesses               136380                       # Number of integer alu accesses
-system.cpu0.num_fp_alu_accesses                  1279                       # Number of float alu accesses
-system.cpu0.num_func_calls                       3196                       # number of times a function call or return occured
-system.cpu0.num_conditional_control_insts        12151                       # number of instructions that are conditional controls
-system.cpu0.num_int_insts                      136380                       # number of integer instructions
-system.cpu0.num_fp_insts                         1279                       # number of float instructions
-system.cpu0.num_int_register_reads             257490                       # number of times the integer registers were read
-system.cpu0.num_int_register_writes            110039                       # number of times the integer registers were written
-system.cpu0.num_fp_register_reads                1981                       # number of times the floating registers were read
-system.cpu0.num_fp_register_writes                981                       # number of times the floating registers were written
-system.cpu0.num_cc_register_reads               78262                       # number of times the CC registers were read
-system.cpu0.num_cc_register_writes              42183                       # number of times the CC registers were written
-system.cpu0.num_mem_refs                        27198                       # number of memory refs
-system.cpu0.num_load_insts                      16684                       # Number of load instructions
-system.cpu0.num_store_insts                     10514                       # Number of store instructions
-system.cpu0.num_idle_cycles               4191.003994                       # Number of idle cycles
-system.cpu0.num_busy_cycles              1330623.996006                       # Number of busy cycles
-system.cpu0.not_idle_fraction                0.996860                       # Percentage of non-idle cycles
-system.cpu0.idle_fraction                    0.003140                       # Percentage of idle cycles
-system.cpu0.Branches                            16199                       # Number of branches fetched
-system.cpu0.op_class::No_OpClass                  615      0.45%      0.45% # Class of executed instruction
-system.cpu0.op_class::IntAlu                   108791     79.00%     79.45% # Class of executed instruction
-system.cpu0.op_class::IntMult                      13      0.01%     79.46% # Class of executed instruction
-system.cpu0.op_class::IntDiv                      138      0.10%     79.56% # Class of executed instruction
-system.cpu0.op_class::FloatAdd                    950      0.69%     80.25% # Class of executed instruction
-system.cpu0.op_class::FloatCmp                      0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::FloatCvt                      0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::FloatMult                     0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::FloatMultAcc                  0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::FloatDiv                      0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::FloatMisc                     0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::FloatSqrt                     0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::SimdAdd                       0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::SimdAddAcc                    0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::SimdAlu                       0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::SimdCmp                       0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::SimdCvt                       0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::SimdMisc                      0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::SimdMult                      0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::SimdMultAcc                   0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::SimdShift                     0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::SimdShiftAcc                  0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::SimdSqrt                      0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::SimdFloatAdd                  0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::SimdFloatAlu                  0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::SimdFloatCmp                  0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::SimdFloatCvt                  0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::SimdFloatDiv                  0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::SimdFloatMisc                 0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::SimdFloatMult                 0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::SimdFloatMultAcc              0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::SimdFloatSqrt                 0      0.00%     80.25% # Class of executed instruction
-system.cpu0.op_class::MemRead                   16382     11.90%     92.15% # Class of executed instruction
-system.cpu0.op_class::MemWrite                  10514      7.64%     99.78% # Class of executed instruction
-system.cpu0.op_class::FloatMemRead                302      0.22%    100.00% # Class of executed instruction
-system.cpu0.op_class::FloatMemWrite                 0      0.00%    100.00% # Class of executed instruction
-system.cpu0.op_class::IprAccess                     0      0.00%    100.00% # Class of executed instruction
-system.cpu0.op_class::InstPrefetch                  0      0.00%    100.00% # Class of executed instruction
-system.cpu0.op_class::total                    137705                       # Class of executed instruction
-system.cpu1.clk_domain.voltage_domain.voltage            1                       # Voltage in Volts
-system.cpu1.clk_domain.clock                     1000                       # Clock period in ticks
-system.cpu1.CUs0.localDataStore.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.cpu1.CUs0.wavefronts00.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts00.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts00.timesBlockedDueRAWDependencies          309                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::samples           39                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::mean     0.794872                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::stdev     0.863880                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::underflows            0      0.00%      0.00% # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::0-1           28     71.79%     71.79% # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::2-3           11     28.21%    100.00% # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::4            0      0.00%    100.00% # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::overflows            0      0.00%    100.00% # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::max_value            2                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::total           39                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts00.dst_reg_operand_dist::samples           39                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts00.dst_reg_operand_dist::mean     0.589744                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts00.dst_reg_operand_dist::stdev     0.498310                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts00.dst_reg_operand_dist::underflows            0      0.00%      0.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts00.dst_reg_operand_dist::0-1           39    100.00%    100.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts00.dst_reg_operand_dist::2-3            0      0.00%    100.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts00.dst_reg_operand_dist::overflows            0      0.00%    100.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts00.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts00.dst_reg_operand_dist::max_value            1                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts00.dst_reg_operand_dist::total           39                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts01.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts01.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts01.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts01.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts01.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts01.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts01.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts01.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts01.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts01.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts01.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts01.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts01.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts01.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts01.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts01.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts01.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts01.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts01.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts01.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts01.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts01.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts01.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts01.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts02.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts02.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts02.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts02.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts02.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts02.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts02.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts02.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts02.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts02.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts02.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts02.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts02.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts02.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts02.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts02.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts02.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts02.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts02.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts02.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts02.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts02.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts02.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts02.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts03.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts03.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts03.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts03.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts03.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts03.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts03.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts03.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts03.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts03.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts03.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts03.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts03.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts03.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts03.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts03.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts03.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts03.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts03.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts03.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts03.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts03.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts03.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts03.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts04.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts04.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts04.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts04.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts04.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts04.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts04.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts04.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts04.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts04.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts04.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts04.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts04.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts04.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts04.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts04.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts04.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts04.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts04.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts04.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts04.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts04.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts04.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts04.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts05.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts05.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts05.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts05.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts05.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts05.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts05.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts05.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts05.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts05.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts05.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts05.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts05.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts05.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts05.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts05.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts05.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts05.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts05.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts05.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts05.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts05.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts05.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts05.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts06.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts06.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts06.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts06.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts06.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts06.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts06.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts06.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts06.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts06.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts06.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts06.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts06.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts06.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts06.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts06.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts06.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts06.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts06.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts06.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts06.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts06.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts06.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts06.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts07.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts07.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts07.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts07.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts07.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts07.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts07.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts07.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts07.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts07.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts07.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts07.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts07.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts07.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts07.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts07.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts07.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts07.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts07.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts07.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts07.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts07.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts07.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts07.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts08.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts08.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts08.timesBlockedDueRAWDependencies          284                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::samples           34                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::mean     0.852941                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::stdev     0.857493                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::underflows            0      0.00%      0.00% # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::0-1           24     70.59%     70.59% # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::2-3           10     29.41%    100.00% # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::4            0      0.00%    100.00% # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::overflows            0      0.00%    100.00% # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::max_value            2                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::total           34                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts08.dst_reg_operand_dist::samples           34                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts08.dst_reg_operand_dist::mean     0.617647                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts08.dst_reg_operand_dist::stdev     0.493270                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts08.dst_reg_operand_dist::underflows            0      0.00%      0.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts08.dst_reg_operand_dist::0-1           34    100.00%    100.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts08.dst_reg_operand_dist::2-3            0      0.00%    100.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts08.dst_reg_operand_dist::overflows            0      0.00%    100.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts08.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts08.dst_reg_operand_dist::max_value            1                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts08.dst_reg_operand_dist::total           34                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts09.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts09.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts09.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts09.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts09.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts09.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts09.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts09.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts09.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts09.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts09.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts09.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts09.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts09.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts09.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts09.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts09.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts09.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts09.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts09.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts09.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts09.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts09.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts09.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts10.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts10.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts10.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts10.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts10.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts10.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts10.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts10.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts10.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts10.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts10.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts10.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts10.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts10.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts10.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts10.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts10.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts10.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts10.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts10.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts10.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts10.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts10.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts10.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts11.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts11.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts11.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts11.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts11.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts11.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts11.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts11.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts11.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts11.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts11.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts11.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts11.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts11.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts11.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts11.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts11.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts11.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts11.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts11.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts11.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts11.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts11.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts11.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts12.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts12.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts12.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts12.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts12.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts12.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts12.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts12.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts12.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts12.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts12.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts12.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts12.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts12.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts12.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts12.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts12.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts12.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts12.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts12.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts12.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts12.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts12.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts12.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts13.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts13.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts13.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts13.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts13.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts13.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts13.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts13.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts13.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts13.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts13.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts13.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts13.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts13.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts13.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts13.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts13.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts13.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts13.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts13.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts13.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts13.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts13.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts13.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts14.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts14.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts14.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts14.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts14.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts14.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts14.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts14.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts14.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts14.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts14.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts14.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts14.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts14.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts14.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts14.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts14.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts14.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts14.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts14.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts14.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts14.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts14.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts14.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts15.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts15.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts15.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts15.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts15.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts15.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts15.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts15.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts15.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts15.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts15.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts15.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts15.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts15.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts15.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts15.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts15.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts15.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts15.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts15.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts15.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts15.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts15.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts15.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts16.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts16.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts16.timesBlockedDueRAWDependencies          279                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::samples           34                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::mean     0.852941                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::stdev     0.857493                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::underflows            0      0.00%      0.00% # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::0-1           24     70.59%     70.59% # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::2-3           10     29.41%    100.00% # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::4            0      0.00%    100.00% # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::overflows            0      0.00%    100.00% # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::max_value            2                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::total           34                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts16.dst_reg_operand_dist::samples           34                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts16.dst_reg_operand_dist::mean     0.617647                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts16.dst_reg_operand_dist::stdev     0.493270                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts16.dst_reg_operand_dist::underflows            0      0.00%      0.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts16.dst_reg_operand_dist::0-1           34    100.00%    100.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts16.dst_reg_operand_dist::2-3            0      0.00%    100.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts16.dst_reg_operand_dist::overflows            0      0.00%    100.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts16.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts16.dst_reg_operand_dist::max_value            1                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts16.dst_reg_operand_dist::total           34                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts17.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts17.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts17.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts17.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts17.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts17.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts17.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts17.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts17.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts17.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts17.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts17.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts17.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts17.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts17.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts17.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts17.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts17.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts17.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts17.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts17.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts17.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts17.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts17.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts18.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts18.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts18.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts18.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts18.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts18.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts18.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts18.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts18.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts18.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts18.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts18.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts18.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts18.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts18.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts18.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts18.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts18.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts18.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts18.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts18.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts18.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts18.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts18.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts19.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts19.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts19.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts19.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts19.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts19.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts19.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts19.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts19.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts19.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts19.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts19.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts19.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts19.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts19.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts19.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts19.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts19.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts19.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts19.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts19.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts19.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts19.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts19.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts20.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts20.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts20.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts20.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts20.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts20.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts20.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts20.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts20.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts20.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts20.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts20.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts20.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts20.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts20.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts20.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts20.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts20.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts20.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts20.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts20.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts20.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts20.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts20.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts21.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts21.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts21.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts21.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts21.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts21.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts21.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts21.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts21.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts21.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts21.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts21.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts21.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts21.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts21.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts21.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts21.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts21.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts21.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts21.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts21.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts21.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts21.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts21.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts22.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts22.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts22.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts22.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts22.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts22.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts22.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts22.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts22.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts22.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts22.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts22.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts22.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts22.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts22.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts22.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts22.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts22.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts22.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts22.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts22.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts22.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts22.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts22.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts23.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts23.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts23.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts23.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts23.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts23.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts23.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts23.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts23.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts23.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts23.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts23.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts23.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts23.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts23.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts23.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts23.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts23.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts23.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts23.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts23.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts23.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts23.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts23.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts24.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts24.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts24.timesBlockedDueRAWDependencies          274                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::samples           34                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::mean     0.852941                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::stdev     0.857493                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::underflows            0      0.00%      0.00% # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::0-1           24     70.59%     70.59% # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::2-3           10     29.41%    100.00% # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::4            0      0.00%    100.00% # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::overflows            0      0.00%    100.00% # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::max_value            2                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::total           34                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts24.dst_reg_operand_dist::samples           34                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts24.dst_reg_operand_dist::mean     0.617647                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts24.dst_reg_operand_dist::stdev     0.493270                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts24.dst_reg_operand_dist::underflows            0      0.00%      0.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts24.dst_reg_operand_dist::0-1           34    100.00%    100.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts24.dst_reg_operand_dist::2-3            0      0.00%    100.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts24.dst_reg_operand_dist::overflows            0      0.00%    100.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts24.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts24.dst_reg_operand_dist::max_value            1                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts24.dst_reg_operand_dist::total           34                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts25.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts25.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts25.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts25.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts25.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts25.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts25.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts25.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts25.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts25.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts25.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts25.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts25.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts25.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts25.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts25.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts25.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts25.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts25.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts25.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts25.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts25.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts25.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts25.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts26.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts26.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts26.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts26.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts26.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts26.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts26.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts26.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts26.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts26.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts26.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts26.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts26.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts26.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts26.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts26.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts26.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts26.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts26.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts26.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts26.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts26.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts26.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts26.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts27.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts27.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts27.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts27.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts27.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts27.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts27.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts27.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts27.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts27.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts27.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts27.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts27.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts27.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts27.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts27.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts27.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts27.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts27.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts27.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts27.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts27.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts27.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts27.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts28.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts28.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts28.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts28.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts28.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts28.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts28.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts28.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts28.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts28.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts28.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts28.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts28.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts28.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts28.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts28.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts28.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts28.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts28.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts28.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts28.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts28.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts28.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts28.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts29.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts29.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts29.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts29.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts29.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts29.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts29.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts29.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts29.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts29.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts29.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts29.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts29.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts29.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts29.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts29.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts29.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts29.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts29.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts29.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts29.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts29.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts29.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts29.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts30.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts30.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts30.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts30.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts30.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts30.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts30.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts30.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts30.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts30.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts30.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts30.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts30.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts30.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts30.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts30.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts30.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts30.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts30.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts30.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts30.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts30.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts30.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts30.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts31.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs0.wavefronts31.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs0.wavefronts31.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs0.wavefronts31.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts31.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts31.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts31.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts31.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts31.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts31.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts31.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts31.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts31.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts31.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs0.wavefronts31.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts31.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts31.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts31.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts31.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts31.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts31.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts31.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts31.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.wavefronts31.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs0.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::samples           35                       # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::mean    11.257143                       # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::stdev     5.595917                       # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::underflows            0      0.00%      0.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::1            0      0.00%      0.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::2            4     11.43%     11.43% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::3            4     11.43%     22.86% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::4            1      2.86%     25.71% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::5            0      0.00%     25.71% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::6            0      0.00%     25.71% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::7            0      0.00%     25.71% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::8            0      0.00%     25.71% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::9            0      0.00%     25.71% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::10            4     11.43%     37.14% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::11            4     11.43%     48.57% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::12            0      0.00%     48.57% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::13            0      0.00%     48.57% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::14            1      2.86%     51.43% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::15            0      0.00%     51.43% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::16           17     48.57%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::17            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::18            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::19            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::20            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::21            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::22            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::23            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::24            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::25            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::26            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::27            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::28            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::29            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::30            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::31            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::32            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::overflows            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::min_value            2                       # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::max_value           16                       # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::total           35                       # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs0.ExecStage.num_cycles_with_no_issue         2741                       # number of cycles the CU issues nothing
-system.cpu1.CUs0.ExecStage.num_cycles_with_instr_issued           99                       # number of cycles the CU issued at least one instruction
-system.cpu1.CUs0.ExecStage.num_cycles_with_instrtype_issue::ALU0           30                       # Number of cycles at least one instruction of specific type issued
-system.cpu1.CUs0.ExecStage.num_cycles_with_instrtype_issue::ALU1           29                       # Number of cycles at least one instruction of specific type issued
-system.cpu1.CUs0.ExecStage.num_cycles_with_instrtype_issue::ALU2           29                       # Number of cycles at least one instruction of specific type issued
-system.cpu1.CUs0.ExecStage.num_cycles_with_instrtype_issue::ALU3           29                       # Number of cycles at least one instruction of specific type issued
-system.cpu1.CUs0.ExecStage.num_cycles_with_instrtype_issue::GM           18                       # Number of cycles at least one instruction of specific type issued
-system.cpu1.CUs0.ExecStage.num_cycles_with_instrtype_issue::LM            6                       # Number of cycles at least one instruction of specific type issued
-system.cpu1.CUs0.ExecStage.num_cycles_with_instr_type_no_issue::ALU0          625                       # Number of cycles no instruction of specific type issued
-system.cpu1.CUs0.ExecStage.num_cycles_with_instr_type_no_issue::ALU1          340                       # Number of cycles no instruction of specific type issued
-system.cpu1.CUs0.ExecStage.num_cycles_with_instr_type_no_issue::ALU2          338                       # Number of cycles no instruction of specific type issued
-system.cpu1.CUs0.ExecStage.num_cycles_with_instr_type_no_issue::ALU3          335                       # Number of cycles no instruction of specific type issued
-system.cpu1.CUs0.ExecStage.num_cycles_with_instr_type_no_issue::GM          404                       # Number of cycles no instruction of specific type issued
-system.cpu1.CUs0.ExecStage.num_cycles_with_instr_type_no_issue::LM           22                       # Number of cycles no instruction of specific type issued
-system.cpu1.CUs0.ExecStage.spc::samples          2840                       # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs0.ExecStage.spc::mean         0.049648                       # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs0.ExecStage.spc::stdev        0.277106                       # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs0.ExecStage.spc::underflows            0      0.00%      0.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs0.ExecStage.spc::0                2741     96.51%     96.51% # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs0.ExecStage.spc::1                  57      2.01%     98.52% # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs0.ExecStage.spc::2                  42      1.48%    100.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs0.ExecStage.spc::3                   0      0.00%    100.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs0.ExecStage.spc::4                   0      0.00%    100.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs0.ExecStage.spc::5                   0      0.00%    100.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs0.ExecStage.spc::6                   0      0.00%    100.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs0.ExecStage.spc::overflows            0      0.00%    100.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs0.ExecStage.spc::min_value            0                       # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs0.ExecStage.spc::max_value            2                       # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs0.ExecStage.spc::total            2840                       # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs0.ExecStage.num_transitions_active_to_idle           90                       # number of CU transitions from active to idle
-system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::samples           90                       # duration of idle periods in cycles
-system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::mean    29.322222                       # duration of idle periods in cycles
-system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::stdev   145.995831                       # duration of idle periods in cycles
-system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::underflows            0      0.00%      0.00% # duration of idle periods in cycles
-system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::0-4           76     84.44%     84.44% # duration of idle periods in cycles
-system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::5-9            7      7.78%     92.22% # duration of idle periods in cycles
-system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::10-14            0      0.00%     92.22% # duration of idle periods in cycles
-system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::15-19            0      0.00%     92.22% # duration of idle periods in cycles
-system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::20-24            0      0.00%     92.22% # duration of idle periods in cycles
-system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::25-29            1      1.11%     93.33% # duration of idle periods in cycles
-system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::30-34            0      0.00%     93.33% # duration of idle periods in cycles
-system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::35-39            0      0.00%     93.33% # duration of idle periods in cycles
-system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::40-44            0      0.00%     93.33% # duration of idle periods in cycles
-system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::45-49            0      0.00%     93.33% # duration of idle periods in cycles
-system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::50-54            0      0.00%     93.33% # duration of idle periods in cycles
-system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::55-59            0      0.00%     93.33% # duration of idle periods in cycles
-system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::60-64            0      0.00%     93.33% # duration of idle periods in cycles
-system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::65-69            0      0.00%     93.33% # duration of idle periods in cycles
-system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::70-74            0      0.00%     93.33% # duration of idle periods in cycles
-system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::75            0      0.00%     93.33% # duration of idle periods in cycles
-system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::overflows            6      6.67%    100.00% # duration of idle periods in cycles
-system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::min_value            1                       # duration of idle periods in cycles
-system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::max_value         1291                       # duration of idle periods in cycles
-system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::total           90                       # duration of idle periods in cycles
-system.cpu1.CUs0.GlobalMemPipeline.load_vrf_bank_conflict_cycles            0                       # total number of cycles GM data are delayed before updating the VRF
-system.cpu1.CUs0.LocalMemPipeline.load_vrf_bank_conflict_cycles            0                       # total number of cycles LDS data are delayed before updating the VRF
-system.cpu1.CUs0.valu_insts                        68                       # Number of vector ALU insts issued.
-system.cpu1.CUs0.valu_insts_per_wf                 17                       # The avg. number of vector ALU insts issued per-wavefront.
-system.cpu1.CUs0.salu_insts                         0                       # Number of scalar ALU insts issued.
-system.cpu1.CUs0.salu_insts_per_wf                  0                       # The avg. number of scalar ALU insts issued per-wavefront.
-system.cpu1.CUs0.inst_cycles_valu                  68                       # Number of cycles needed to execute VALU insts.
-system.cpu1.CUs0.inst_cycles_salu                   0                       # Number of cycles needed to execute SALU insts.
-system.cpu1.CUs0.thread_cycles_valu              3076                       # Number of thread cycles used to execute vector ALU ops. Similar to instCyclesVALU but multiplied by the number of active threads.
-system.cpu1.CUs0.valu_utilization           70.680147                       # Percentage of active vector ALU threads in a wave.
-system.cpu1.CUs0.lds_no_flat_insts                  6                       # Number of LDS insts issued, not including FLAT accesses that resolve to LDS.
-system.cpu1.CUs0.lds_no_flat_insts_per_wf     1.500000                       # The avg. number of LDS insts (not including FLAT accesses that resolve to LDS) per-wavefront.
-system.cpu1.CUs0.flat_vmem_insts                    0                       # The number of FLAT insts that resolve to vmem issued.
-system.cpu1.CUs0.flat_vmem_insts_per_wf             0                       # The average number of FLAT insts that resolve to vmem issued per-wavefront.
-system.cpu1.CUs0.flat_lds_insts                     0                       # The number of FLAT insts that resolve to LDS issued.
-system.cpu1.CUs0.flat_lds_insts_per_wf              0                       # The average number of FLAT insts that resolve to LDS issued per-wavefront.
-system.cpu1.CUs0.vector_mem_writes                  8                       # Number of vector mem write insts (excluding FLAT insts).
-system.cpu1.CUs0.vector_mem_writes_per_wf            2                       # The average number of vector mem write insts (excluding FLAT insts) per-wavefront.
-system.cpu1.CUs0.vector_mem_reads                  29                       # Number of vector mem read insts (excluding FLAT insts).
-system.cpu1.CUs0.vector_mem_reads_per_wf     7.250000                       # The avg. number of vector mem read insts (excluding FLAT insts) per-wavefront.
-system.cpu1.CUs0.scalar_mem_writes                  0                       # Number of scalar mem write insts.
-system.cpu1.CUs0.scalar_mem_writes_per_wf            0                       # The average number of scalar mem write insts per-wavefront.
-system.cpu1.CUs0.scalar_mem_reads                   0                       # Number of scalar mem read insts.
-system.cpu1.CUs0.scalar_mem_reads_per_wf            0                       # The average number of scalar mem read insts per-wavefront.
-system.cpu1.CUs0.tlb_requests                     769                       # number of uncoalesced requests
-system.cpu1.CUs0.tlb_cycles              -454892896000                       # total number of cycles for all uncoalesced requests
-system.cpu1.CUs0.avg_translation_latency -591538226.267880                       # Avg. translation latency for data translations
-system.cpu1.CUs0.TLB_hits_distribution::page_table          769                       # TLB hits distribution (0 for page table, x for Lx-TLB
-system.cpu1.CUs0.TLB_hits_distribution::L1_TLB            0                       # TLB hits distribution (0 for page table, x for Lx-TLB
-system.cpu1.CUs0.TLB_hits_distribution::L2_TLB            0                       # TLB hits distribution (0 for page table, x for Lx-TLB
-system.cpu1.CUs0.TLB_hits_distribution::L3_TLB            0                       # TLB hits distribution (0 for page table, x for Lx-TLB
-system.cpu1.CUs0.lds_bank_access_cnt               54                       # Total number of LDS bank accesses
-system.cpu1.CUs0.lds_bank_conflicts::samples            6                       # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::mean            8                       # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::stdev     6.196773                       # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::underflows            0      0.00%      0.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::0-1            2     33.33%     33.33% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::2-3            0      0.00%     33.33% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::4-5            0      0.00%     33.33% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::6-7            0      0.00%     33.33% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::8-9            0      0.00%     33.33% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::10-11            0      0.00%     33.33% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::12-13            4     66.67%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::14-15            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::16-17            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::18-19            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::20-21            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::22-23            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::24-25            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::26-27            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::28-29            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::30-31            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::32-33            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::34-35            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::36-37            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::38-39            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::40-41            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::42-43            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::44-45            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::46-47            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::48-49            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::50-51            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::52-53            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::54-55            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::56-57            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::58-59            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::60-61            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::62-63            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::64             0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::overflows            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::min_value            0                       # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::max_value           12                       # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.lds_bank_conflicts::total            6                       # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs0.page_divergence_dist::samples           17                       # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs0.page_divergence_dist::mean            1                       # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs0.page_divergence_dist::stdev            0                       # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs0.page_divergence_dist::underflows            0      0.00%      0.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs0.page_divergence_dist::1-4           17    100.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs0.page_divergence_dist::5-8            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs0.page_divergence_dist::9-12            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs0.page_divergence_dist::13-16            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs0.page_divergence_dist::17-20            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs0.page_divergence_dist::21-24            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs0.page_divergence_dist::25-28            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs0.page_divergence_dist::29-32            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs0.page_divergence_dist::33-36            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs0.page_divergence_dist::37-40            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs0.page_divergence_dist::41-44            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs0.page_divergence_dist::45-48            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs0.page_divergence_dist::49-52            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs0.page_divergence_dist::53-56            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs0.page_divergence_dist::57-60            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs0.page_divergence_dist::61-64            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs0.page_divergence_dist::overflows            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs0.page_divergence_dist::min_value            1                       # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs0.page_divergence_dist::max_value            1                       # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs0.page_divergence_dist::total           17                       # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs0.global_mem_instr_cnt              17                       # dynamic global memory instructions count
-system.cpu1.CUs0.local_mem_instr_cnt                6                       # dynamic local memory intruction count
-system.cpu1.CUs0.wg_blocked_due_lds_alloc            0                       # Workgroup blocked due to LDS capacity
-system.cpu1.CUs0.num_instr_executed               141                       # number of instructions executed
-system.cpu1.CUs0.inst_exec_rate::samples          141                       # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs0.inst_exec_rate::mean       71.028369                       # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs0.inst_exec_rate::stdev     225.061514                       # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs0.inst_exec_rate::underflows            0      0.00%      0.00% # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs0.inst_exec_rate::0-1                0      0.00%      0.00% # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs0.inst_exec_rate::2-3               12      8.51%      8.51% # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs0.inst_exec_rate::4-5               61     43.26%     51.77% # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs0.inst_exec_rate::6-7               32     22.70%     74.47% # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs0.inst_exec_rate::8-9                3      2.13%     76.60% # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs0.inst_exec_rate::10                 3      2.13%     78.72% # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs0.inst_exec_rate::overflows           30     21.28%    100.00% # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs0.inst_exec_rate::min_value            2                       # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs0.inst_exec_rate::max_value         1297                       # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs0.inst_exec_rate::total            141                       # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs0.num_vec_ops_executed            6769                       # number of vec ops executed (e.g. WF size/inst)
-system.cpu1.CUs0.num_total_cycles                2840                       # number of cycles the CU ran for
-system.cpu1.CUs0.vpc                         2.383451                       # Vector Operations per cycle (this CU only)
-system.cpu1.CUs0.ipc                         0.049648                       # Instructions per cycle (this CU only)
-system.cpu1.CUs0.warp_execution_dist::samples          141                       # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs0.warp_execution_dist::mean    48.007092                       # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs0.warp_execution_dist::stdev    23.719942                       # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs0.warp_execution_dist::underflows            0      0.00%      0.00% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs0.warp_execution_dist::1-4            5      3.55%      3.55% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs0.warp_execution_dist::5-8            0      0.00%      3.55% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs0.warp_execution_dist::9-12            0      0.00%      3.55% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs0.warp_execution_dist::13-16           36     25.53%     29.08% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs0.warp_execution_dist::17-20            0      0.00%     29.08% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs0.warp_execution_dist::21-24            0      0.00%     29.08% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs0.warp_execution_dist::25-28            0      0.00%     29.08% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs0.warp_execution_dist::29-32            0      0.00%     29.08% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs0.warp_execution_dist::33-36            0      0.00%     29.08% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs0.warp_execution_dist::37-40            0      0.00%     29.08% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs0.warp_execution_dist::41-44            0      0.00%     29.08% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs0.warp_execution_dist::45-48            0      0.00%     29.08% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs0.warp_execution_dist::49-52            8      5.67%     34.75% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs0.warp_execution_dist::53-56            0      0.00%     34.75% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs0.warp_execution_dist::57-60            0      0.00%     34.75% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs0.warp_execution_dist::61-64           92     65.25%    100.00% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs0.warp_execution_dist::overflows            0      0.00%    100.00% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs0.warp_execution_dist::min_value            1                       # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs0.warp_execution_dist::max_value           64                       # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs0.warp_execution_dist::total          141                       # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs0.gmem_lanes_execution_dist::samples           18                       # number of active lanes per global memory instruction
-system.cpu1.CUs0.gmem_lanes_execution_dist::mean    37.833333                       # number of active lanes per global memory instruction
-system.cpu1.CUs0.gmem_lanes_execution_dist::stdev    27.064737                       # number of active lanes per global memory instruction
-system.cpu1.CUs0.gmem_lanes_execution_dist::underflows            0      0.00%      0.00% # number of active lanes per global memory instruction
-system.cpu1.CUs0.gmem_lanes_execution_dist::1-4            1      5.56%      5.56% # number of active lanes per global memory instruction
-system.cpu1.CUs0.gmem_lanes_execution_dist::5-8            0      0.00%      5.56% # number of active lanes per global memory instruction
-system.cpu1.CUs0.gmem_lanes_execution_dist::9-12            0      0.00%      5.56% # number of active lanes per global memory instruction
-system.cpu1.CUs0.gmem_lanes_execution_dist::13-16            8     44.44%     50.00% # number of active lanes per global memory instruction
-system.cpu1.CUs0.gmem_lanes_execution_dist::17-20            0      0.00%     50.00% # number of active lanes per global memory instruction
-system.cpu1.CUs0.gmem_lanes_execution_dist::21-24            0      0.00%     50.00% # number of active lanes per global memory instruction
-system.cpu1.CUs0.gmem_lanes_execution_dist::25-28            0      0.00%     50.00% # number of active lanes per global memory instruction
-system.cpu1.CUs0.gmem_lanes_execution_dist::29-32            0      0.00%     50.00% # number of active lanes per global memory instruction
-system.cpu1.CUs0.gmem_lanes_execution_dist::33-36            0      0.00%     50.00% # number of active lanes per global memory instruction
-system.cpu1.CUs0.gmem_lanes_execution_dist::37-40            0      0.00%     50.00% # number of active lanes per global memory instruction
-system.cpu1.CUs0.gmem_lanes_execution_dist::41-44            0      0.00%     50.00% # number of active lanes per global memory instruction
-system.cpu1.CUs0.gmem_lanes_execution_dist::45-48            0      0.00%     50.00% # number of active lanes per global memory instruction
-system.cpu1.CUs0.gmem_lanes_execution_dist::49-52            0      0.00%     50.00% # number of active lanes per global memory instruction
-system.cpu1.CUs0.gmem_lanes_execution_dist::53-56            0      0.00%     50.00% # number of active lanes per global memory instruction
-system.cpu1.CUs0.gmem_lanes_execution_dist::57-60            0      0.00%     50.00% # number of active lanes per global memory instruction
-system.cpu1.CUs0.gmem_lanes_execution_dist::61-64            9     50.00%    100.00% # number of active lanes per global memory instruction
-system.cpu1.CUs0.gmem_lanes_execution_dist::overflows            0      0.00%    100.00% # number of active lanes per global memory instruction
-system.cpu1.CUs0.gmem_lanes_execution_dist::min_value            1                       # number of active lanes per global memory instruction
-system.cpu1.CUs0.gmem_lanes_execution_dist::max_value           64                       # number of active lanes per global memory instruction
-system.cpu1.CUs0.gmem_lanes_execution_dist::total           18                       # number of active lanes per global memory instruction
-system.cpu1.CUs0.lmem_lanes_execution_dist::samples            6                       # number of active lanes per local memory instruction
-system.cpu1.CUs0.lmem_lanes_execution_dist::mean    19.500000                       # number of active lanes per local memory instruction
-system.cpu1.CUs0.lmem_lanes_execution_dist::stdev    22.322634                       # number of active lanes per local memory instruction
-system.cpu1.CUs0.lmem_lanes_execution_dist::underflows            0      0.00%      0.00% # number of active lanes per local memory instruction
-system.cpu1.CUs0.lmem_lanes_execution_dist::1-4            1     16.67%     16.67% # number of active lanes per local memory instruction
-system.cpu1.CUs0.lmem_lanes_execution_dist::5-8            0      0.00%     16.67% # number of active lanes per local memory instruction
-system.cpu1.CUs0.lmem_lanes_execution_dist::9-12            0      0.00%     16.67% # number of active lanes per local memory instruction
-system.cpu1.CUs0.lmem_lanes_execution_dist::13-16            4     66.67%     83.33% # number of active lanes per local memory instruction
-system.cpu1.CUs0.lmem_lanes_execution_dist::17-20            0      0.00%     83.33% # number of active lanes per local memory instruction
-system.cpu1.CUs0.lmem_lanes_execution_dist::21-24            0      0.00%     83.33% # number of active lanes per local memory instruction
-system.cpu1.CUs0.lmem_lanes_execution_dist::25-28            0      0.00%     83.33% # number of active lanes per local memory instruction
-system.cpu1.CUs0.lmem_lanes_execution_dist::29-32            0      0.00%     83.33% # number of active lanes per local memory instruction
-system.cpu1.CUs0.lmem_lanes_execution_dist::33-36            0      0.00%     83.33% # number of active lanes per local memory instruction
-system.cpu1.CUs0.lmem_lanes_execution_dist::37-40            0      0.00%     83.33% # number of active lanes per local memory instruction
-system.cpu1.CUs0.lmem_lanes_execution_dist::41-44            0      0.00%     83.33% # number of active lanes per local memory instruction
-system.cpu1.CUs0.lmem_lanes_execution_dist::45-48            0      0.00%     83.33% # number of active lanes per local memory instruction
-system.cpu1.CUs0.lmem_lanes_execution_dist::49-52            0      0.00%     83.33% # number of active lanes per local memory instruction
-system.cpu1.CUs0.lmem_lanes_execution_dist::53-56            0      0.00%     83.33% # number of active lanes per local memory instruction
-system.cpu1.CUs0.lmem_lanes_execution_dist::57-60            0      0.00%     83.33% # number of active lanes per local memory instruction
-system.cpu1.CUs0.lmem_lanes_execution_dist::61-64            1     16.67%    100.00% # number of active lanes per local memory instruction
-system.cpu1.CUs0.lmem_lanes_execution_dist::overflows            0      0.00%    100.00% # number of active lanes per local memory instruction
-system.cpu1.CUs0.lmem_lanes_execution_dist::min_value            1                       # number of active lanes per local memory instruction
-system.cpu1.CUs0.lmem_lanes_execution_dist::max_value           64                       # number of active lanes per local memory instruction
-system.cpu1.CUs0.lmem_lanes_execution_dist::total            6                       # number of active lanes per local memory instruction
-system.cpu1.CUs0.num_alu_insts_executed           118                       # Number of dynamic non-GM memory insts executed
-system.cpu1.CUs0.times_wg_blocked_due_vgpr_alloc            0                       # Number of times WGs are blocked due to VGPR allocation per SIMD
-system.cpu1.CUs0.num_CAS_ops                        0                       # number of compare and swap operations
-system.cpu1.CUs0.num_failed_CAS_ops                 0                       # number of compare and swap operations that failed
-system.cpu1.CUs0.num_completed_wfs                  4                       # number of completed wavefronts
-system.cpu1.CUs1.localDataStore.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.cpu1.CUs1.wavefronts00.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts00.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts00.timesBlockedDueRAWDependencies          406                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::samples           39                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::mean     0.794872                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::stdev     0.863880                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::underflows            0      0.00%      0.00% # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::0-1           28     71.79%     71.79% # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::2-3           11     28.21%    100.00% # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::4            0      0.00%    100.00% # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::overflows            0      0.00%    100.00% # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::max_value            2                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::total           39                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts00.dst_reg_operand_dist::samples           39                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts00.dst_reg_operand_dist::mean     0.589744                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts00.dst_reg_operand_dist::stdev     0.498310                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts00.dst_reg_operand_dist::underflows            0      0.00%      0.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts00.dst_reg_operand_dist::0-1           39    100.00%    100.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts00.dst_reg_operand_dist::2-3            0      0.00%    100.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts00.dst_reg_operand_dist::overflows            0      0.00%    100.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts00.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts00.dst_reg_operand_dist::max_value            1                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts00.dst_reg_operand_dist::total           39                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts01.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts01.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts01.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts01.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts01.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts01.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts01.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts01.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts01.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts01.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts01.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts01.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts01.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts01.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts01.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts01.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts01.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts01.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts01.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts01.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts01.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts01.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts01.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts01.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts02.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts02.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts02.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts02.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts02.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts02.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts02.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts02.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts02.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts02.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts02.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts02.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts02.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts02.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts02.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts02.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts02.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts02.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts02.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts02.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts02.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts02.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts02.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts02.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts03.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts03.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts03.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts03.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts03.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts03.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts03.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts03.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts03.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts03.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts03.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts03.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts03.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts03.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts03.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts03.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts03.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts03.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts03.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts03.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts03.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts03.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts03.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts03.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts04.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts04.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts04.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts04.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts04.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts04.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts04.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts04.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts04.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts04.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts04.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts04.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts04.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts04.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts04.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts04.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts04.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts04.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts04.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts04.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts04.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts04.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts04.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts04.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts05.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts05.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts05.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts05.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts05.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts05.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts05.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts05.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts05.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts05.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts05.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts05.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts05.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts05.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts05.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts05.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts05.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts05.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts05.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts05.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts05.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts05.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts05.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts05.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts06.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts06.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts06.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts06.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts06.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts06.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts06.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts06.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts06.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts06.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts06.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts06.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts06.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts06.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts06.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts06.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts06.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts06.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts06.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts06.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts06.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts06.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts06.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts06.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts07.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts07.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts07.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts07.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts07.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts07.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts07.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts07.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts07.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts07.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts07.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts07.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts07.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts07.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts07.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts07.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts07.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts07.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts07.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts07.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts07.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts07.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts07.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts07.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts08.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts08.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts08.timesBlockedDueRAWDependencies          381                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::samples           34                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::mean     0.852941                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::stdev     0.857493                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::underflows            0      0.00%      0.00% # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::0-1           24     70.59%     70.59% # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::2-3           10     29.41%    100.00% # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::4            0      0.00%    100.00% # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::overflows            0      0.00%    100.00% # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::max_value            2                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::total           34                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts08.dst_reg_operand_dist::samples           34                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts08.dst_reg_operand_dist::mean     0.617647                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts08.dst_reg_operand_dist::stdev     0.493270                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts08.dst_reg_operand_dist::underflows            0      0.00%      0.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts08.dst_reg_operand_dist::0-1           34    100.00%    100.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts08.dst_reg_operand_dist::2-3            0      0.00%    100.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts08.dst_reg_operand_dist::overflows            0      0.00%    100.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts08.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts08.dst_reg_operand_dist::max_value            1                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts08.dst_reg_operand_dist::total           34                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts09.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts09.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts09.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts09.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts09.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts09.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts09.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts09.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts09.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts09.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts09.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts09.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts09.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts09.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts09.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts09.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts09.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts09.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts09.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts09.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts09.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts09.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts09.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts09.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts10.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts10.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts10.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts10.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts10.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts10.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts10.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts10.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts10.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts10.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts10.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts10.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts10.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts10.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts10.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts10.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts10.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts10.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts10.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts10.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts10.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts10.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts10.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts10.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts11.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts11.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts11.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts11.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts11.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts11.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts11.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts11.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts11.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts11.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts11.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts11.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts11.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts11.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts11.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts11.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts11.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts11.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts11.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts11.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts11.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts11.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts11.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts11.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts12.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts12.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts12.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts12.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts12.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts12.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts12.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts12.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts12.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts12.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts12.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts12.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts12.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts12.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts12.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts12.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts12.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts12.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts12.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts12.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts12.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts12.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts12.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts12.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts13.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts13.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts13.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts13.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts13.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts13.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts13.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts13.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts13.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts13.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts13.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts13.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts13.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts13.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts13.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts13.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts13.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts13.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts13.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts13.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts13.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts13.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts13.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts13.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts14.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts14.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts14.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts14.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts14.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts14.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts14.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts14.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts14.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts14.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts14.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts14.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts14.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts14.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts14.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts14.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts14.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts14.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts14.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts14.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts14.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts14.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts14.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts14.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts15.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts15.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts15.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts15.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts15.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts15.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts15.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts15.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts15.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts15.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts15.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts15.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts15.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts15.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts15.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts15.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts15.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts15.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts15.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts15.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts15.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts15.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts15.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts15.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts16.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts16.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts16.timesBlockedDueRAWDependencies          372                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::samples           34                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::mean     0.852941                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::stdev     0.857493                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::underflows            0      0.00%      0.00% # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::0-1           24     70.59%     70.59% # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::2-3           10     29.41%    100.00% # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::4            0      0.00%    100.00% # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::overflows            0      0.00%    100.00% # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::max_value            2                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::total           34                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts16.dst_reg_operand_dist::samples           34                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts16.dst_reg_operand_dist::mean     0.617647                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts16.dst_reg_operand_dist::stdev     0.493270                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts16.dst_reg_operand_dist::underflows            0      0.00%      0.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts16.dst_reg_operand_dist::0-1           34    100.00%    100.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts16.dst_reg_operand_dist::2-3            0      0.00%    100.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts16.dst_reg_operand_dist::overflows            0      0.00%    100.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts16.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts16.dst_reg_operand_dist::max_value            1                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts16.dst_reg_operand_dist::total           34                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts17.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts17.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts17.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts17.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts17.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts17.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts17.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts17.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts17.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts17.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts17.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts17.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts17.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts17.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts17.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts17.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts17.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts17.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts17.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts17.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts17.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts17.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts17.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts17.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts18.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts18.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts18.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts18.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts18.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts18.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts18.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts18.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts18.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts18.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts18.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts18.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts18.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts18.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts18.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts18.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts18.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts18.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts18.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts18.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts18.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts18.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts18.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts18.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts19.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts19.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts19.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts19.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts19.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts19.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts19.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts19.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts19.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts19.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts19.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts19.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts19.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts19.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts19.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts19.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts19.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts19.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts19.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts19.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts19.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts19.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts19.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts19.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts20.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts20.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts20.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts20.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts20.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts20.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts20.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts20.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts20.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts20.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts20.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts20.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts20.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts20.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts20.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts20.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts20.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts20.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts20.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts20.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts20.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts20.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts20.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts20.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts21.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts21.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts21.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts21.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts21.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts21.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts21.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts21.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts21.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts21.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts21.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts21.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts21.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts21.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts21.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts21.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts21.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts21.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts21.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts21.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts21.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts21.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts21.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts21.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts22.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts22.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts22.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts22.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts22.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts22.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts22.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts22.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts22.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts22.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts22.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts22.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts22.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts22.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts22.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts22.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts22.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts22.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts22.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts22.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts22.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts22.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts22.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts22.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts23.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts23.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts23.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts23.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts23.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts23.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts23.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts23.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts23.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts23.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts23.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts23.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts23.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts23.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts23.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts23.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts23.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts23.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts23.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts23.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts23.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts23.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts23.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts23.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts24.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts24.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts24.timesBlockedDueRAWDependencies          364                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::samples           34                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::mean     0.852941                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::stdev     0.857493                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::underflows            0      0.00%      0.00% # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::0-1           24     70.59%     70.59% # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::2-3           10     29.41%    100.00% # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::4            0      0.00%    100.00% # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::overflows            0      0.00%    100.00% # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::max_value            2                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::total           34                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts24.dst_reg_operand_dist::samples           34                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts24.dst_reg_operand_dist::mean     0.617647                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts24.dst_reg_operand_dist::stdev     0.493270                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts24.dst_reg_operand_dist::underflows            0      0.00%      0.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts24.dst_reg_operand_dist::0-1           34    100.00%    100.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts24.dst_reg_operand_dist::2-3            0      0.00%    100.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts24.dst_reg_operand_dist::overflows            0      0.00%    100.00% # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts24.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts24.dst_reg_operand_dist::max_value            1                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts24.dst_reg_operand_dist::total           34                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts25.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts25.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts25.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts25.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts25.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts25.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts25.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts25.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts25.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts25.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts25.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts25.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts25.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts25.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts25.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts25.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts25.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts25.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts25.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts25.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts25.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts25.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts25.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts25.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts26.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts26.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts26.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts26.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts26.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts26.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts26.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts26.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts26.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts26.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts26.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts26.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts26.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts26.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts26.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts26.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts26.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts26.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts26.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts26.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts26.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts26.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts26.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts26.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts27.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts27.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts27.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts27.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts27.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts27.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts27.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts27.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts27.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts27.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts27.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts27.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts27.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts27.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts27.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts27.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts27.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts27.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts27.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts27.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts27.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts27.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts27.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts27.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts28.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts28.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts28.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts28.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts28.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts28.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts28.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts28.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts28.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts28.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts28.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts28.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts28.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts28.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts28.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts28.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts28.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts28.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts28.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts28.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts28.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts28.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts28.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts28.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts29.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts29.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts29.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts29.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts29.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts29.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts29.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts29.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts29.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts29.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts29.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts29.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts29.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts29.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts29.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts29.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts29.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts29.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts29.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts29.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts29.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts29.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts29.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts29.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts30.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts30.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts30.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts30.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts30.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts30.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts30.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts30.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts30.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts30.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts30.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts30.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts30.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts30.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts30.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts30.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts30.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts30.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts30.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts30.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts30.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts30.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts30.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts30.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts31.timesBlockedDueVrfPortAvail            0                       # number of times instructions are blocked due to VRF port availability
-system.cpu1.CUs1.wavefronts31.timesBlockedDueWAXDependencies            0                       # number of times the wf's instructions are blocked due to WAW or WAR dependencies
-system.cpu1.CUs1.wavefronts31.timesBlockedDueRAWDependencies            0                       # number of times the wf's instructions are blocked due to RAW dependencies
-system.cpu1.CUs1.wavefronts31.src_reg_operand_dist::samples            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts31.src_reg_operand_dist::mean          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts31.src_reg_operand_dist::stdev          nan                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts31.src_reg_operand_dist::underflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts31.src_reg_operand_dist::0-1            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts31.src_reg_operand_dist::2-3            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts31.src_reg_operand_dist::4            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts31.src_reg_operand_dist::overflows            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts31.src_reg_operand_dist::min_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts31.src_reg_operand_dist::max_value            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts31.src_reg_operand_dist::total            0                       # number of executed instructions with N source register operands
-system.cpu1.CUs1.wavefronts31.dst_reg_operand_dist::samples            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts31.dst_reg_operand_dist::mean          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts31.dst_reg_operand_dist::stdev          nan                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts31.dst_reg_operand_dist::underflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts31.dst_reg_operand_dist::0-1            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts31.dst_reg_operand_dist::2-3            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts31.dst_reg_operand_dist::overflows            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts31.dst_reg_operand_dist::min_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts31.dst_reg_operand_dist::max_value            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.wavefronts31.dst_reg_operand_dist::total            0                       # number of executed instructions with N destination register operands
-system.cpu1.CUs1.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::samples           35                       # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::mean    11.257143                       # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::stdev     5.595917                       # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::underflows            0      0.00%      0.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::1            0      0.00%      0.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::2            4     11.43%     11.43% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::3            4     11.43%     22.86% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::4            1      2.86%     25.71% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::5            0      0.00%     25.71% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::6            0      0.00%     25.71% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::7            0      0.00%     25.71% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::8            0      0.00%     25.71% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::9            0      0.00%     25.71% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::10            4     11.43%     37.14% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::11            4     11.43%     48.57% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::12            0      0.00%     48.57% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::13            0      0.00%     48.57% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::14            1      2.86%     51.43% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::15            0      0.00%     51.43% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::16           17     48.57%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::17            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::18            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::19            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::20            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::21            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::22            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::23            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::24            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::25            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::26            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::27            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::28            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::29            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::30            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::31            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::32            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::overflows            0      0.00%    100.00% # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::min_value            2                       # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::max_value           16                       # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::total           35                       # For each instruction fetch request recieved record how many instructions you got from it
-system.cpu1.CUs1.ExecStage.num_cycles_with_no_issue         2740                       # number of cycles the CU issues nothing
-system.cpu1.CUs1.ExecStage.num_cycles_with_instr_issued          100                       # number of cycles the CU issued at least one instruction
-system.cpu1.CUs1.ExecStage.num_cycles_with_instrtype_issue::ALU0           30                       # Number of cycles at least one instruction of specific type issued
-system.cpu1.CUs1.ExecStage.num_cycles_with_instrtype_issue::ALU1           29                       # Number of cycles at least one instruction of specific type issued
-system.cpu1.CUs1.ExecStage.num_cycles_with_instrtype_issue::ALU2           29                       # Number of cycles at least one instruction of specific type issued
-system.cpu1.CUs1.ExecStage.num_cycles_with_instrtype_issue::ALU3           29                       # Number of cycles at least one instruction of specific type issued
-system.cpu1.CUs1.ExecStage.num_cycles_with_instrtype_issue::GM           18                       # Number of cycles at least one instruction of specific type issued
-system.cpu1.CUs1.ExecStage.num_cycles_with_instrtype_issue::LM            6                       # Number of cycles at least one instruction of specific type issued
-system.cpu1.CUs1.ExecStage.num_cycles_with_instr_type_no_issue::ALU0          795                       # Number of cycles no instruction of specific type issued
-system.cpu1.CUs1.ExecStage.num_cycles_with_instr_type_no_issue::ALU1          437                       # Number of cycles no instruction of specific type issued
-system.cpu1.CUs1.ExecStage.num_cycles_with_instr_type_no_issue::ALU2          431                       # Number of cycles no instruction of specific type issued
-system.cpu1.CUs1.ExecStage.num_cycles_with_instr_type_no_issue::ALU3          422                       # Number of cycles no instruction of specific type issued
-system.cpu1.CUs1.ExecStage.num_cycles_with_instr_type_no_issue::GM          408                       # Number of cycles no instruction of specific type issued
-system.cpu1.CUs1.ExecStage.num_cycles_with_instr_type_no_issue::LM           22                       # Number of cycles no instruction of specific type issued
-system.cpu1.CUs1.ExecStage.spc::samples          2840                       # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs1.ExecStage.spc::mean         0.049648                       # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs1.ExecStage.spc::stdev        0.275831                       # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs1.ExecStage.spc::underflows            0      0.00%      0.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs1.ExecStage.spc::0                2740     96.48%     96.48% # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs1.ExecStage.spc::1                  59      2.08%     98.56% # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs1.ExecStage.spc::2                  41      1.44%    100.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs1.ExecStage.spc::3                   0      0.00%    100.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs1.ExecStage.spc::4                   0      0.00%    100.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs1.ExecStage.spc::5                   0      0.00%    100.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs1.ExecStage.spc::6                   0      0.00%    100.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs1.ExecStage.spc::overflows            0      0.00%    100.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs1.ExecStage.spc::min_value            0                       # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs1.ExecStage.spc::max_value            2                       # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs1.ExecStage.spc::total            2840                       # Execution units active per cycle (Exec unit=SIMD,MemPipe)
-system.cpu1.CUs1.ExecStage.num_transitions_active_to_idle           91                       # number of CU transitions from active to idle
-system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::samples           91                       # duration of idle periods in cycles
-system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::mean    30.010989                       # duration of idle periods in cycles
-system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::stdev   148.108031                       # duration of idle periods in cycles
-system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::underflows            0      0.00%      0.00% # duration of idle periods in cycles
-system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::0-4           76     83.52%     83.52% # duration of idle periods in cycles
-system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::5-9            8      8.79%     92.31% # duration of idle periods in cycles
-system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::10-14            0      0.00%     92.31% # duration of idle periods in cycles
-system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::15-19            0      0.00%     92.31% # duration of idle periods in cycles
-system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::20-24            0      0.00%     92.31% # duration of idle periods in cycles
-system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::25-29            1      1.10%     93.41% # duration of idle periods in cycles
-system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::30-34            0      0.00%     93.41% # duration of idle periods in cycles
-system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::35-39            0      0.00%     93.41% # duration of idle periods in cycles
-system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::40-44            0      0.00%     93.41% # duration of idle periods in cycles
-system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::45-49            0      0.00%     93.41% # duration of idle periods in cycles
-system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::50-54            0      0.00%     93.41% # duration of idle periods in cycles
-system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::55-59            0      0.00%     93.41% # duration of idle periods in cycles
-system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::60-64            0      0.00%     93.41% # duration of idle periods in cycles
-system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::65-69            0      0.00%     93.41% # duration of idle periods in cycles
-system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::70-74            0      0.00%     93.41% # duration of idle periods in cycles
-system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::75            0      0.00%     93.41% # duration of idle periods in cycles
-system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::overflows            6      6.59%    100.00% # duration of idle periods in cycles
-system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::min_value            1                       # duration of idle periods in cycles
-system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::max_value         1299                       # duration of idle periods in cycles
-system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::total           91                       # duration of idle periods in cycles
-system.cpu1.CUs1.GlobalMemPipeline.load_vrf_bank_conflict_cycles            0                       # total number of cycles GM data are delayed before updating the VRF
-system.cpu1.CUs1.LocalMemPipeline.load_vrf_bank_conflict_cycles            0                       # total number of cycles LDS data are delayed before updating the VRF
-system.cpu1.CUs1.valu_insts                        68                       # Number of vector ALU insts issued.
-system.cpu1.CUs1.valu_insts_per_wf                 17                       # The avg. number of vector ALU insts issued per-wavefront.
-system.cpu1.CUs1.salu_insts                         0                       # Number of scalar ALU insts issued.
-system.cpu1.CUs1.salu_insts_per_wf                  0                       # The avg. number of scalar ALU insts issued per-wavefront.
-system.cpu1.CUs1.inst_cycles_valu                  68                       # Number of cycles needed to execute VALU insts.
-system.cpu1.CUs1.inst_cycles_salu                   0                       # Number of cycles needed to execute SALU insts.
-system.cpu1.CUs1.thread_cycles_valu              3071                       # Number of thread cycles used to execute vector ALU ops. Similar to instCyclesVALU but multiplied by the number of active threads.
-system.cpu1.CUs1.valu_utilization           70.565257                       # Percentage of active vector ALU threads in a wave.
-system.cpu1.CUs1.lds_no_flat_insts                  6                       # Number of LDS insts issued, not including FLAT accesses that resolve to LDS.
-system.cpu1.CUs1.lds_no_flat_insts_per_wf     1.500000                       # The avg. number of LDS insts (not including FLAT accesses that resolve to LDS) per-wavefront.
-system.cpu1.CUs1.flat_vmem_insts                    0                       # The number of FLAT insts that resolve to vmem issued.
-system.cpu1.CUs1.flat_vmem_insts_per_wf             0                       # The average number of FLAT insts that resolve to vmem issued per-wavefront.
-system.cpu1.CUs1.flat_lds_insts                     0                       # The number of FLAT insts that resolve to LDS issued.
-system.cpu1.CUs1.flat_lds_insts_per_wf              0                       # The average number of FLAT insts that resolve to LDS issued per-wavefront.
-system.cpu1.CUs1.vector_mem_writes                  8                       # Number of vector mem write insts (excluding FLAT insts).
-system.cpu1.CUs1.vector_mem_writes_per_wf            2                       # The average number of vector mem write insts (excluding FLAT insts) per-wavefront.
-system.cpu1.CUs1.vector_mem_reads                  29                       # Number of vector mem read insts (excluding FLAT insts).
-system.cpu1.CUs1.vector_mem_reads_per_wf     7.250000                       # The avg. number of vector mem read insts (excluding FLAT insts) per-wavefront.
-system.cpu1.CUs1.scalar_mem_writes                  0                       # Number of scalar mem write insts.
-system.cpu1.CUs1.scalar_mem_writes_per_wf            0                       # The average number of scalar mem write insts per-wavefront.
-system.cpu1.CUs1.scalar_mem_reads                   0                       # Number of scalar mem read insts.
-system.cpu1.CUs1.scalar_mem_reads_per_wf            0                       # The average number of scalar mem read insts per-wavefront.
-system.cpu1.CUs1.tlb_requests                     769                       # number of uncoalesced requests
-system.cpu1.CUs1.tlb_cycles              -454919630000                       # total number of cycles for all uncoalesced requests
-system.cpu1.CUs1.avg_translation_latency -591572990.897269                       # Avg. translation latency for data translations
-system.cpu1.CUs1.TLB_hits_distribution::page_table          769                       # TLB hits distribution (0 for page table, x for Lx-TLB
-system.cpu1.CUs1.TLB_hits_distribution::L1_TLB            0                       # TLB hits distribution (0 for page table, x for Lx-TLB
-system.cpu1.CUs1.TLB_hits_distribution::L2_TLB            0                       # TLB hits distribution (0 for page table, x for Lx-TLB
-system.cpu1.CUs1.TLB_hits_distribution::L3_TLB            0                       # TLB hits distribution (0 for page table, x for Lx-TLB
-system.cpu1.CUs1.lds_bank_access_cnt               53                       # Total number of LDS bank accesses
-system.cpu1.CUs1.lds_bank_conflicts::samples            6                       # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::mean     7.833333                       # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::stdev     6.080022                       # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::underflows            0      0.00%      0.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::0-1            2     33.33%     33.33% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::2-3            0      0.00%     33.33% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::4-5            0      0.00%     33.33% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::6-7            0      0.00%     33.33% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::8-9            0      0.00%     33.33% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::10-11            1     16.67%     50.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::12-13            3     50.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::14-15            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::16-17            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::18-19            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::20-21            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::22-23            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::24-25            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::26-27            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::28-29            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::30-31            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::32-33            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::34-35            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::36-37            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::38-39            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::40-41            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::42-43            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::44-45            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::46-47            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::48-49            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::50-51            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::52-53            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::54-55            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::56-57            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::58-59            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::60-61            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::62-63            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::64             0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::overflows            0      0.00%    100.00% # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::min_value            0                       # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::max_value           12                       # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.lds_bank_conflicts::total            6                       # Number of bank conflicts per LDS memory packet
-system.cpu1.CUs1.page_divergence_dist::samples           17                       # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs1.page_divergence_dist::mean            1                       # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs1.page_divergence_dist::stdev            0                       # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs1.page_divergence_dist::underflows            0      0.00%      0.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs1.page_divergence_dist::1-4           17    100.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs1.page_divergence_dist::5-8            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs1.page_divergence_dist::9-12            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs1.page_divergence_dist::13-16            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs1.page_divergence_dist::17-20            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs1.page_divergence_dist::21-24            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs1.page_divergence_dist::25-28            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs1.page_divergence_dist::29-32            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs1.page_divergence_dist::33-36            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs1.page_divergence_dist::37-40            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs1.page_divergence_dist::41-44            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs1.page_divergence_dist::45-48            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs1.page_divergence_dist::49-52            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs1.page_divergence_dist::53-56            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs1.page_divergence_dist::57-60            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs1.page_divergence_dist::61-64            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs1.page_divergence_dist::overflows            0      0.00%    100.00% # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs1.page_divergence_dist::min_value            1                       # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs1.page_divergence_dist::max_value            1                       # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs1.page_divergence_dist::total           17                       # pages touched per wf (over all mem. instr.)
-system.cpu1.CUs1.global_mem_instr_cnt              17                       # dynamic global memory instructions count
-system.cpu1.CUs1.local_mem_instr_cnt                6                       # dynamic local memory intruction count
-system.cpu1.CUs1.wg_blocked_due_lds_alloc            0                       # Workgroup blocked due to LDS capacity
-system.cpu1.CUs1.num_instr_executed               141                       # number of instructions executed
-system.cpu1.CUs1.inst_exec_rate::samples          141                       # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs1.inst_exec_rate::mean       72.113475                       # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs1.inst_exec_rate::stdev     228.065470                       # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs1.inst_exec_rate::underflows            0      0.00%      0.00% # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs1.inst_exec_rate::0-1                0      0.00%      0.00% # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs1.inst_exec_rate::2-3               13      9.22%      9.22% # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs1.inst_exec_rate::4-5               60     42.55%     51.77% # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs1.inst_exec_rate::6-7               34     24.11%     75.89% # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs1.inst_exec_rate::8-9                3      2.13%     78.01% # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs1.inst_exec_rate::10                 1      0.71%     78.72% # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs1.inst_exec_rate::overflows           30     21.28%    100.00% # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs1.inst_exec_rate::min_value            2                       # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs1.inst_exec_rate::max_value         1305                       # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs1.inst_exec_rate::total            141                       # Instruction Execution Rate: Number of executed vector instructions per cycle
-system.cpu1.CUs1.num_vec_ops_executed            6762                       # number of vec ops executed (e.g. WF size/inst)
-system.cpu1.CUs1.num_total_cycles                2840                       # number of cycles the CU ran for
-system.cpu1.CUs1.vpc                         2.380986                       # Vector Operations per cycle (this CU only)
-system.cpu1.CUs1.ipc                         0.049648                       # Instructions per cycle (this CU only)
-system.cpu1.CUs1.warp_execution_dist::samples          141                       # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs1.warp_execution_dist::mean    47.957447                       # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs1.warp_execution_dist::stdev    23.818022                       # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs1.warp_execution_dist::underflows            0      0.00%      0.00% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs1.warp_execution_dist::1-4            5      3.55%      3.55% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs1.warp_execution_dist::5-8            0      0.00%      3.55% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs1.warp_execution_dist::9-12            9      6.38%      9.93% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs1.warp_execution_dist::13-16           27     19.15%     29.08% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs1.warp_execution_dist::17-20            0      0.00%     29.08% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs1.warp_execution_dist::21-24            0      0.00%     29.08% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs1.warp_execution_dist::25-28            0      0.00%     29.08% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs1.warp_execution_dist::29-32            0      0.00%     29.08% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs1.warp_execution_dist::33-36            0      0.00%     29.08% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs1.warp_execution_dist::37-40            0      0.00%     29.08% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs1.warp_execution_dist::41-44            0      0.00%     29.08% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs1.warp_execution_dist::45-48            0      0.00%     29.08% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs1.warp_execution_dist::49-52            8      5.67%     34.75% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs1.warp_execution_dist::53-56            0      0.00%     34.75% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs1.warp_execution_dist::57-60            0      0.00%     34.75% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs1.warp_execution_dist::61-64           92     65.25%    100.00% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs1.warp_execution_dist::overflows            0      0.00%    100.00% # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs1.warp_execution_dist::min_value            1                       # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs1.warp_execution_dist::max_value           64                       # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs1.warp_execution_dist::total          141                       # number of lanes active per instruction (oval all instructions)
-system.cpu1.CUs1.gmem_lanes_execution_dist::samples           18                       # number of active lanes per global memory instruction
-system.cpu1.CUs1.gmem_lanes_execution_dist::mean    37.722222                       # number of active lanes per global memory instruction
-system.cpu1.CUs1.gmem_lanes_execution_dist::stdev    27.174394                       # number of active lanes per global memory instruction
-system.cpu1.CUs1.gmem_lanes_execution_dist::underflows            0      0.00%      0.00% # number of active lanes per global memory instruction
-system.cpu1.CUs1.gmem_lanes_execution_dist::1-4            1      5.56%      5.56% # number of active lanes per global memory instruction
-system.cpu1.CUs1.gmem_lanes_execution_dist::5-8            0      0.00%      5.56% # number of active lanes per global memory instruction
-system.cpu1.CUs1.gmem_lanes_execution_dist::9-12            2     11.11%     16.67% # number of active lanes per global memory instruction
-system.cpu1.CUs1.gmem_lanes_execution_dist::13-16            6     33.33%     50.00% # number of active lanes per global memory instruction
-system.cpu1.CUs1.gmem_lanes_execution_dist::17-20            0      0.00%     50.00% # number of active lanes per global memory instruction
-system.cpu1.CUs1.gmem_lanes_execution_dist::21-24            0      0.00%     50.00% # number of active lanes per global memory instruction
-system.cpu1.CUs1.gmem_lanes_execution_dist::25-28            0      0.00%     50.00% # number of active lanes per global memory instruction
-system.cpu1.CUs1.gmem_lanes_execution_dist::29-32            0      0.00%     50.00% # number of active lanes per global memory instruction
-system.cpu1.CUs1.gmem_lanes_execution_dist::33-36            0      0.00%     50.00% # number of active lanes per global memory instruction
-system.cpu1.CUs1.gmem_lanes_execution_dist::37-40            0      0.00%     50.00% # number of active lanes per global memory instruction
-system.cpu1.CUs1.gmem_lanes_execution_dist::41-44            0      0.00%     50.00% # number of active lanes per global memory instruction
-system.cpu1.CUs1.gmem_lanes_execution_dist::45-48            0      0.00%     50.00% # number of active lanes per global memory instruction
-system.cpu1.CUs1.gmem_lanes_execution_dist::49-52            0      0.00%     50.00% # number of active lanes per global memory instruction
-system.cpu1.CUs1.gmem_lanes_execution_dist::53-56            0      0.00%     50.00% # number of active lanes per global memory instruction
-system.cpu1.CUs1.gmem_lanes_execution_dist::57-60            0      0.00%     50.00% # number of active lanes per global memory instruction
-system.cpu1.CUs1.gmem_lanes_execution_dist::61-64            9     50.00%    100.00% # number of active lanes per global memory instruction
-system.cpu1.CUs1.gmem_lanes_execution_dist::overflows            0      0.00%    100.00% # number of active lanes per global memory instruction
-system.cpu1.CUs1.gmem_lanes_execution_dist::min_value            1                       # number of active lanes per global memory instruction
-system.cpu1.CUs1.gmem_lanes_execution_dist::max_value           64                       # number of active lanes per global memory instruction
-system.cpu1.CUs1.gmem_lanes_execution_dist::total           18                       # number of active lanes per global memory instruction
-system.cpu1.CUs1.lmem_lanes_execution_dist::samples            6                       # number of active lanes per local memory instruction
-system.cpu1.CUs1.lmem_lanes_execution_dist::mean    19.333333                       # number of active lanes per local memory instruction
-system.cpu1.CUs1.lmem_lanes_execution_dist::stdev    22.384518                       # number of active lanes per local memory instruction
-system.cpu1.CUs1.lmem_lanes_execution_dist::underflows            0      0.00%      0.00% # number of active lanes per local memory instruction
-system.cpu1.CUs1.lmem_lanes_execution_dist::1-4            1     16.67%     16.67% # number of active lanes per local memory instruction
-system.cpu1.CUs1.lmem_lanes_execution_dist::5-8            0      0.00%     16.67% # number of active lanes per local memory instruction
-system.cpu1.CUs1.lmem_lanes_execution_dist::9-12            1     16.67%     33.33% # number of active lanes per local memory instruction
-system.cpu1.CUs1.lmem_lanes_execution_dist::13-16            3     50.00%     83.33% # number of active lanes per local memory instruction
-system.cpu1.CUs1.lmem_lanes_execution_dist::17-20            0      0.00%     83.33% # number of active lanes per local memory instruction
-system.cpu1.CUs1.lmem_lanes_execution_dist::21-24            0      0.00%     83.33% # number of active lanes per local memory instruction
-system.cpu1.CUs1.lmem_lanes_execution_dist::25-28            0      0.00%     83.33% # number of active lanes per local memory instruction
-system.cpu1.CUs1.lmem_lanes_execution_dist::29-32            0      0.00%     83.33% # number of active lanes per local memory instruction
-system.cpu1.CUs1.lmem_lanes_execution_dist::33-36            0      0.00%     83.33% # number of active lanes per local memory instruction
-system.cpu1.CUs1.lmem_lanes_execution_dist::37-40            0      0.00%     83.33% # number of active lanes per local memory instruction
-system.cpu1.CUs1.lmem_lanes_execution_dist::41-44            0      0.00%     83.33% # number of active lanes per local memory instruction
-system.cpu1.CUs1.lmem_lanes_execution_dist::45-48            0      0.00%     83.33% # number of active lanes per local memory instruction
-system.cpu1.CUs1.lmem_lanes_execution_dist::49-52            0      0.00%     83.33% # number of active lanes per local memory instruction
-system.cpu1.CUs1.lmem_lanes_execution_dist::53-56            0      0.00%     83.33% # number of active lanes per local memory instruction
-system.cpu1.CUs1.lmem_lanes_execution_dist::57-60            0      0.00%     83.33% # number of active lanes per local memory instruction
-system.cpu1.CUs1.lmem_lanes_execution_dist::61-64            1     16.67%    100.00% # number of active lanes per local memory instruction
-system.cpu1.CUs1.lmem_lanes_execution_dist::overflows            0      0.00%    100.00% # number of active lanes per local memory instruction
-system.cpu1.CUs1.lmem_lanes_execution_dist::min_value            1                       # number of active lanes per local memory instruction
-system.cpu1.CUs1.lmem_lanes_execution_dist::max_value           64                       # number of active lanes per local memory instruction
-system.cpu1.CUs1.lmem_lanes_execution_dist::total            6                       # number of active lanes per local memory instruction
-system.cpu1.CUs1.num_alu_insts_executed           118                       # Number of dynamic non-GM memory insts executed
-system.cpu1.CUs1.times_wg_blocked_due_vgpr_alloc            0                       # Number of times WGs are blocked due to VGPR allocation per SIMD
-system.cpu1.CUs1.num_CAS_ops                        0                       # number of compare and swap operations
-system.cpu1.CUs1.num_failed_CAS_ops                 0                       # number of compare and swap operations that failed
-system.cpu1.CUs1.num_completed_wfs                  4                       # number of completed wavefronts
-system.cpu1.CUs0.ldsBus.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.cpu1.CUs1.ldsBus.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.cpu2.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.cpu2.num_kernel_launched                     1                       # number of kernel launched
-system.dir_cntrl0.L3CacheMemory.demand_hits            0                       # Number of cache demand hits
-system.dir_cntrl0.L3CacheMemory.demand_misses            0                       # Number of cache demand misses
-system.dir_cntrl0.L3CacheMemory.demand_accesses            0                       # Number of cache demand accesses
-system.dir_cntrl0.L3CacheMemory.num_data_array_writes         1549                       # number of data array writes
-system.dir_cntrl0.L3CacheMemory.num_tag_array_reads         1549                       # number of tag array reads
-system.dir_cntrl0.L3CacheMemory.num_tag_array_writes         1549                       # number of tag array writes
-system.dir_cntrl0.probeToCore.avg_buf_msgs     0.069628                       # Average number of messages in buffer
-system.dir_cntrl0.probeToCore.avg_stall_time 29997.797448                       # Average number of cycles messages are stalled in this MB
-system.dir_cntrl0.requestFromCores.avg_buf_msgs     0.001160                       # Average number of messages in buffer
-system.dir_cntrl0.requestFromCores.avg_stall_time 17271.531260                       # Average number of cycles messages are stalled in this MB
-system.dir_cntrl0.responseFromCores.avg_buf_msgs     0.001160                       # Average number of messages in buffer
-system.dir_cntrl0.responseFromCores.avg_stall_time 121679.841776                       # Average number of cycles messages are stalled in this MB
-system.dir_cntrl0.responseFromMemory.avg_buf_msgs     0.003110                       # Average number of messages in buffer
-system.dir_cntrl0.responseFromMemory.avg_stall_time   999.889123                       # Average number of cycles messages are stalled in this MB
-system.dir_cntrl0.responseToCore.avg_buf_msgs     0.069628                       # Average number of messages in buffer
-system.dir_cntrl0.responseToCore.avg_stall_time 29990.830190                       # Average number of cycles messages are stalled in this MB
-system.dir_cntrl0.triggerQueue.avg_buf_msgs     0.002321                       # Average number of messages in buffer
-system.dir_cntrl0.triggerQueue.avg_stall_time   999.739290                       # Average number of cycles messages are stalled in this MB
-system.dir_cntrl0.unblockFromCores.avg_buf_msgs     0.001160                       # Average number of messages in buffer
-system.dir_cntrl0.unblockFromCores.avg_stall_time 17249.343916                       # Average number of cycles messages are stalled in this MB
-system.dir_cntrl0.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.dispatcher_coalescer.clk_domain.voltage_domain.voltage            1                       # Voltage in Volts
-system.dispatcher_coalescer.clk_domain.clock         1000                       # Clock period in ticks
-system.dispatcher_coalescer.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.dispatcher_coalescer.uncoalesced_accesses            0                       # Number of uncoalesced TLB accesses
-system.dispatcher_coalescer.coalesced_accesses            0                       # Number of coalesced TLB accesses
-system.dispatcher_coalescer.queuing_cycles            0                       # Number of cycles spent in queue
-system.dispatcher_coalescer.local_queuing_cycles            0                       # Number of cycles spent in queue for all incoming reqs
-system.dispatcher_coalescer.local_latency          nan                       # Avg. latency over all incoming pkts
-system.dispatcher_tlb.clk_domain.voltage_domain.voltage            1                       # Voltage in Volts
-system.dispatcher_tlb.clk_domain.clock           1000                       # Clock period in ticks
-system.dispatcher_tlb.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.dispatcher_tlb.local_TLB_accesses            0                       # Number of TLB accesses
-system.dispatcher_tlb.local_TLB_hits                0                       # Number of TLB hits
-system.dispatcher_tlb.local_TLB_misses              0                       # Number of TLB misses
-system.dispatcher_tlb.local_TLB_miss_rate          nan                       # TLB miss rate
-system.dispatcher_tlb.global_TLB_accesses            0                       # Number of TLB accesses
-system.dispatcher_tlb.global_TLB_hits               0                       # Number of TLB hits
-system.dispatcher_tlb.global_TLB_misses             0                       # Number of TLB misses
-system.dispatcher_tlb.global_TLB_miss_rate          nan                       # TLB miss rate
-system.dispatcher_tlb.access_cycles                 0                       # Cycles spent accessing this TLB level
-system.dispatcher_tlb.page_table_cycles             0                       # Cycles spent accessing the page table
-system.dispatcher_tlb.unique_pages                  0                       # Number of unique pages touched
-system.dispatcher_tlb.local_cycles                  0                       # Number of cycles spent in queue for all incoming reqs
-system.dispatcher_tlb.local_latency               nan                       # Avg. latency over incoming coalesced reqs
-system.dispatcher_tlb.avg_reuse_distance            0                       # avg. reuse distance over all pages (in ticks)
-system.l1_coalescer0.clk_domain.voltage_domain.voltage            1                       # Voltage in Volts
-system.l1_coalescer0.clk_domain.clock            1000                       # Clock period in ticks
-system.l1_coalescer0.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.l1_coalescer0.uncoalesced_accesses          778                       # Number of uncoalesced TLB accesses
-system.l1_coalescer0.coalesced_accesses             0                       # Number of coalesced TLB accesses
-system.l1_coalescer0.queuing_cycles                 0                       # Number of cycles spent in queue
-system.l1_coalescer0.local_queuing_cycles            0                       # Number of cycles spent in queue for all incoming reqs
-system.l1_coalescer0.local_latency                  0                       # Avg. latency over all incoming pkts
-system.l1_coalescer1.clk_domain.voltage_domain.voltage            1                       # Voltage in Volts
-system.l1_coalescer1.clk_domain.clock            1000                       # Clock period in ticks
-system.l1_coalescer1.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.l1_coalescer1.uncoalesced_accesses          769                       # Number of uncoalesced TLB accesses
-system.l1_coalescer1.coalesced_accesses             0                       # Number of coalesced TLB accesses
-system.l1_coalescer1.queuing_cycles                 0                       # Number of cycles spent in queue
-system.l1_coalescer1.local_queuing_cycles            0                       # Number of cycles spent in queue for all incoming reqs
-system.l1_coalescer1.local_latency                  0                       # Avg. latency over all incoming pkts
-system.l1_tlb0.clk_domain.voltage_domain.voltage            1                       # Voltage in Volts
-system.l1_tlb0.clk_domain.clock                  1000                       # Clock period in ticks
-system.l1_tlb0.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.l1_tlb0.local_TLB_accesses                 778                       # Number of TLB accesses
-system.l1_tlb0.local_TLB_hits                     774                       # Number of TLB hits
-system.l1_tlb0.local_TLB_misses                     4                       # Number of TLB misses
-system.l1_tlb0.local_TLB_miss_rate           0.514139                       # TLB miss rate
-system.l1_tlb0.global_TLB_accesses                778                       # Number of TLB accesses
-system.l1_tlb0.global_TLB_hits                    774                       # Number of TLB hits
-system.l1_tlb0.global_TLB_misses                    4                       # Number of TLB misses
-system.l1_tlb0.global_TLB_miss_rate          0.514139                       # TLB miss rate
-system.l1_tlb0.access_cycles                        0                       # Cycles spent accessing this TLB level
-system.l1_tlb0.page_table_cycles                    0                       # Cycles spent accessing the page table
-system.l1_tlb0.unique_pages                         4                       # Number of unique pages touched
-system.l1_tlb0.local_cycles                         0                       # Number of cycles spent in queue for all incoming reqs
-system.l1_tlb0.local_latency                        0                       # Avg. latency over incoming coalesced reqs
-system.l1_tlb0.avg_reuse_distance                   0                       # avg. reuse distance over all pages (in ticks)
-system.l1_tlb1.clk_domain.voltage_domain.voltage            1                       # Voltage in Volts
-system.l1_tlb1.clk_domain.clock                  1000                       # Clock period in ticks
-system.l1_tlb1.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.l1_tlb1.local_TLB_accesses                 769                       # Number of TLB accesses
-system.l1_tlb1.local_TLB_hits                     766                       # Number of TLB hits
-system.l1_tlb1.local_TLB_misses                     3                       # Number of TLB misses
-system.l1_tlb1.local_TLB_miss_rate           0.390117                       # TLB miss rate
-system.l1_tlb1.global_TLB_accesses                769                       # Number of TLB accesses
-system.l1_tlb1.global_TLB_hits                    766                       # Number of TLB hits
-system.l1_tlb1.global_TLB_misses                    3                       # Number of TLB misses
-system.l1_tlb1.global_TLB_miss_rate          0.390117                       # TLB miss rate
-system.l1_tlb1.access_cycles                        0                       # Cycles spent accessing this TLB level
-system.l1_tlb1.page_table_cycles                    0                       # Cycles spent accessing the page table
-system.l1_tlb1.unique_pages                         3                       # Number of unique pages touched
-system.l1_tlb1.local_cycles                         0                       # Number of cycles spent in queue for all incoming reqs
-system.l1_tlb1.local_latency                        0                       # Avg. latency over incoming coalesced reqs
-system.l1_tlb1.avg_reuse_distance                   0                       # avg. reuse distance over all pages (in ticks)
-system.l2_coalescer.clk_domain.voltage_domain.voltage            1                       # Voltage in Volts
-system.l2_coalescer.clk_domain.clock             1000                       # Clock period in ticks
-system.l2_coalescer.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.l2_coalescer.uncoalesced_accesses            8                       # Number of uncoalesced TLB accesses
-system.l2_coalescer.coalesced_accesses              1                       # Number of coalesced TLB accesses
-system.l2_coalescer.queuing_cycles               8000                       # Number of cycles spent in queue
-system.l2_coalescer.local_queuing_cycles         1000                       # Number of cycles spent in queue for all incoming reqs
-system.l2_coalescer.local_latency                 125                       # Avg. latency over all incoming pkts
-system.l2_tlb.clk_domain.voltage_domain.voltage            1                       # Voltage in Volts
-system.l2_tlb.clk_domain.clock                   1000                       # Clock period in ticks
-system.l2_tlb.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.l2_tlb.local_TLB_accesses                    8                       # Number of TLB accesses
-system.l2_tlb.local_TLB_hits                        3                       # Number of TLB hits
-system.l2_tlb.local_TLB_misses                      5                       # Number of TLB misses
-system.l2_tlb.local_TLB_miss_rate           62.500000                       # TLB miss rate
-system.l2_tlb.global_TLB_accesses                  15                       # Number of TLB accesses
-system.l2_tlb.global_TLB_hits                       3                       # Number of TLB hits
-system.l2_tlb.global_TLB_misses                    12                       # Number of TLB misses
-system.l2_tlb.global_TLB_miss_rate                 80                       # TLB miss rate
-system.l2_tlb.access_cycles                    552008                       # Cycles spent accessing this TLB level
-system.l2_tlb.page_table_cycles                     0                       # Cycles spent accessing the page table
-system.l2_tlb.unique_pages                          5                       # Number of unique pages touched
-system.l2_tlb.local_cycles                      69001                       # Number of cycles spent in queue for all incoming reqs
-system.l2_tlb.local_latency               8625.125000                       # Avg. latency over incoming coalesced reqs
-system.l2_tlb.avg_reuse_distance                    0                       # avg. reuse distance over all pages (in ticks)
-system.l3_coalescer.clk_domain.voltage_domain.voltage            1                       # Voltage in Volts
-system.l3_coalescer.clk_domain.clock             1000                       # Clock period in ticks
-system.l3_coalescer.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.l3_coalescer.uncoalesced_accesses            5                       # Number of uncoalesced TLB accesses
-system.l3_coalescer.coalesced_accesses              1                       # Number of coalesced TLB accesses
-system.l3_coalescer.queuing_cycles               8000                       # Number of cycles spent in queue
-system.l3_coalescer.local_queuing_cycles         1000                       # Number of cycles spent in queue for all incoming reqs
-system.l3_coalescer.local_latency                 200                       # Avg. latency over all incoming pkts
-system.l3_tlb.clk_domain.voltage_domain.voltage            1                       # Voltage in Volts
-system.l3_tlb.clk_domain.clock                   1000                       # Clock period in ticks
-system.l3_tlb.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.l3_tlb.local_TLB_accesses                    5                       # Number of TLB accesses
-system.l3_tlb.local_TLB_hits                        0                       # Number of TLB hits
-system.l3_tlb.local_TLB_misses                      5                       # Number of TLB misses
-system.l3_tlb.local_TLB_miss_rate                 100                       # TLB miss rate
-system.l3_tlb.global_TLB_accesses                  12                       # Number of TLB accesses
-system.l3_tlb.global_TLB_hits                       0                       # Number of TLB hits
-system.l3_tlb.global_TLB_misses                    12                       # Number of TLB misses
-system.l3_tlb.global_TLB_miss_rate                100                       # TLB miss rate
-system.l3_tlb.access_cycles                   1200000                       # Cycles spent accessing this TLB level
-system.l3_tlb.page_table_cycles               6000000                       # Cycles spent accessing the page table
-system.l3_tlb.unique_pages                          5                       # Number of unique pages touched
-system.l3_tlb.local_cycles                     150000                       # Number of cycles spent in queue for all incoming reqs
-system.l3_tlb.local_latency                     30000                       # Avg. latency over incoming coalesced reqs
-system.l3_tlb.avg_reuse_distance                    0                       # avg. reuse distance over all pages (in ticks)
-system.piobus.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.piobus.trans_dist::WriteReq                 94                       # Transaction distribution
-system.piobus.trans_dist::WriteResp                94                       # Transaction distribution
-system.piobus.pkt_count_system.cp_cntrl0.sequencer.mem-master-port::system.cpu2.pio          188                       # Packet count per connected master and slave (bytes)
-system.piobus.pkt_count::total                    188                       # Packet count per connected master and slave (bytes)
-system.piobus.pkt_size_system.cp_cntrl0.sequencer.mem-master-port::system.cpu2.pio          748                       # Cumulative packet size per connected master and slave (bytes)
-system.piobus.pkt_size::total                     748                       # Cumulative packet size per connected master and slave (bytes)
-system.piobus.reqLayer0.occupancy              188000                       # Layer occupancy (ticks)
-system.piobus.reqLayer0.utilization               0.0                       # Layer utilization (%)
-system.piobus.respLayer0.occupancy              94000                       # Layer occupancy (ticks)
-system.piobus.respLayer0.utilization              0.0                       # Layer utilization (%)
-system.ruby.network.ext_links0.int_node.port_buffers00.avg_buf_msgs     0.001160                       # Average number of messages in buffer
-system.ruby.network.ext_links0.int_node.port_buffers00.avg_stall_time 16771.557856                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links0.int_node.port_buffers02.avg_buf_msgs     0.001160                       # Average number of messages in buffer
-system.ruby.network.ext_links0.int_node.port_buffers02.avg_stall_time 121180.062406                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links0.int_node.port_buffers04.avg_buf_msgs     0.001160                       # Average number of messages in buffer
-system.ruby.network.ext_links0.int_node.port_buffers04.avg_stall_time 16749.523342                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links0.int_node.port_buffers05.avg_buf_msgs     0.000010                       # Average number of messages in buffer
-system.ruby.network.ext_links0.int_node.port_buffers05.avg_stall_time  3493.705161                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links0.int_node.port_buffers07.avg_buf_msgs     0.001150                       # Average number of messages in buffer
-system.ruby.network.ext_links0.int_node.port_buffers07.avg_stall_time 30490.654510                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links0.int_node.port_buffers15.avg_buf_msgs     0.001150                       # Average number of messages in buffer
-system.ruby.network.ext_links0.int_node.port_buffers15.avg_stall_time 30497.737889                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links0.int_node.port_buffers17.avg_buf_msgs     0.000010                       # Average number of messages in buffer
-system.ruby.network.ext_links0.int_node.port_buffers17.avg_stall_time  3490.277719                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links0.int_node.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
+system.cp_cntrl0.L1D0cache.demand_hits              0                      
+system.cp_cntrl0.L1D0cache.demand_misses          506                      
+system.cp_cntrl0.L1D0cache.demand_accesses          506                      
+system.cp_cntrl0.L1D0cache.num_data_array_reads        16155                      
+system.cp_cntrl0.L1D0cache.num_data_array_writes        11985                      
+system.cp_cntrl0.L1D0cache.num_tag_array_reads        27132                      
+system.cp_cntrl0.L1D0cache.num_tag_array_writes         1584                      
+system.cp_cntrl0.L1D1cache.demand_hits              0                      
+system.cp_cntrl0.L1D1cache.demand_misses            0                      
+system.cp_cntrl0.L1D1cache.demand_accesses            0                      
+system.cp_cntrl0.L1Icache.demand_hits               0                      
+system.cp_cntrl0.L1Icache.demand_misses          1088                      
+system.cp_cntrl0.L1Icache.demand_accesses         1088                      
+system.cp_cntrl0.L1Icache.num_data_array_reads        86007                      
+system.cp_cntrl0.L1Icache.num_data_array_writes           54                      
+system.cp_cntrl0.L1Icache.num_tag_array_reads        87684                      
+system.cp_cntrl0.L1Icache.num_tag_array_writes           54                      
+system.cp_cntrl0.L2cache.demand_hits                0                      
+system.cp_cntrl0.L2cache.demand_misses           1535                      
+system.cp_cntrl0.L2cache.demand_accesses         1535                      
+system.cp_cntrl0.L2cache.num_data_array_reads          120                      
+system.cp_cntrl0.L2cache.num_data_array_writes        11982                      
+system.cp_cntrl0.L2cache.num_tag_array_reads        12057                      
+system.cp_cntrl0.L2cache.num_tag_array_writes         1649                      
+system.cp_cntrl0.mandatoryQueue.avg_buf_msgs     0.427713                      
+system.cp_cntrl0.mandatoryQueue.avg_stall_time  1999.994007                      
+system.cp_cntrl0.probeToCore.avg_buf_msgs     0.000010                      
+system.cp_cntrl0.probeToCore.avg_stall_time  3665.454806                      
+system.cp_cntrl0.requestFromCore.avg_buf_msgs     0.034499                      
+system.cp_cntrl0.requestFromCore.avg_stall_time 14999.617925                      
+system.cp_cntrl0.responseFromCore.avg_buf_msgs     0.000315                      
+system.cp_cntrl0.responseFromCore.avg_stall_time  1717.844815                      
+system.cp_cntrl0.responseToCore.avg_buf_msgs     0.001150                      
+system.cp_cntrl0.responseToCore.avg_stall_time 31990.122976                      
+system.cp_cntrl0.sequencer.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.cp_cntrl0.sequencer1.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.cp_cntrl0.triggerQueue.avg_buf_msgs     0.001591                      
+system.cp_cntrl0.triggerQueue.avg_stall_time 15959.959998                      
+system.cp_cntrl0.unblockFromCore.avg_buf_msgs     0.034499                      
+system.cp_cntrl0.unblockFromCore.avg_stall_time 14995.033020                      
+system.cp_cntrl0.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.cpu0.clk_domain.clock                      500                      
+system.cpu0.dtb.walker.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.cpu0.apic_clk_domain.clock                8000                      
+system.cpu0.interrupts.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.cpu0.itb.walker.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.cpu0.workload.numSyscalls                   21                      
+system.cpu0.numPwrStateTransitions                  2                      
+system.cpu0.pwrStateClkGateDist::samples            1                      
+system.cpu0.pwrStateClkGateDist::mean         2095501                      
+system.cpu0.pwrStateClkGateDist::1000-5e+10            1    100.00%    100.00%
+system.cpu0.pwrStateClkGateDist::min_value      2095501                      
+system.cpu0.pwrStateClkGateDist::max_value      2095501                      
+system.cpu0.pwrStateClkGateDist::total              1                      
+system.cpu0.pwrStateResidencyTicks::ON      665311999                      
+system.cpu0.pwrStateResidencyTicks::CLK_GATED      2095501                      
+system.cpu0.numCycles                         1334815                      
+system.cpu0.numWorkItemsStarted                     0                      
+system.cpu0.numWorkItemsCompleted                   0                      
+system.cpu0.committedInsts                      66963                      
+system.cpu0.committedOps                       137705                      
+system.cpu0.num_int_alu_accesses               136380                      
+system.cpu0.num_fp_alu_accesses                  1279                      
+system.cpu0.num_func_calls                       3196                      
+system.cpu0.num_conditional_control_insts        12151                      
+system.cpu0.num_int_insts                      136380                      
+system.cpu0.num_fp_insts                         1279                      
+system.cpu0.num_int_register_reads             257490                      
+system.cpu0.num_int_register_writes            110039                      
+system.cpu0.num_fp_register_reads                1981                      
+system.cpu0.num_fp_register_writes                981                      
+system.cpu0.num_cc_register_reads               78262                      
+system.cpu0.num_cc_register_writes              42183                      
+system.cpu0.num_mem_refs                        27198                      
+system.cpu0.num_load_insts                      16684                      
+system.cpu0.num_store_insts                     10514                      
+system.cpu0.num_idle_cycles               4191.003994                      
+system.cpu0.num_busy_cycles              1330623.996006                      
+system.cpu0.not_idle_fraction                0.996860                      
+system.cpu0.idle_fraction                    0.003140                      
+system.cpu0.Branches                            16199                      
+system.cpu0.op_class::No_OpClass                  615      0.45%      0.45%
+system.cpu0.op_class::IntAlu                   108791     79.00%     79.45%
+system.cpu0.op_class::IntMult                      13      0.01%     79.46%
+system.cpu0.op_class::IntDiv                      138      0.10%     79.56%
+system.cpu0.op_class::FloatAdd                    950      0.69%     80.25%
+system.cpu0.op_class::FloatCmp                      0      0.00%     80.25%
+system.cpu0.op_class::FloatCvt                      0      0.00%     80.25%
+system.cpu0.op_class::FloatMult                     0      0.00%     80.25%
+system.cpu0.op_class::FloatMultAcc                  0      0.00%     80.25%
+system.cpu0.op_class::FloatDiv                      0      0.00%     80.25%
+system.cpu0.op_class::FloatMisc                     0      0.00%     80.25%
+system.cpu0.op_class::FloatSqrt                     0      0.00%     80.25%
+system.cpu0.op_class::SimdAdd                       0      0.00%     80.25%
+system.cpu0.op_class::SimdAddAcc                    0      0.00%     80.25%
+system.cpu0.op_class::SimdAlu                       0      0.00%     80.25%
+system.cpu0.op_class::SimdCmp                       0      0.00%     80.25%
+system.cpu0.op_class::SimdCvt                       0      0.00%     80.25%
+system.cpu0.op_class::SimdMisc                      0      0.00%     80.25%
+system.cpu0.op_class::SimdMult                      0      0.00%     80.25%
+system.cpu0.op_class::SimdMultAcc                   0      0.00%     80.25%
+system.cpu0.op_class::SimdShift                     0      0.00%     80.25%
+system.cpu0.op_class::SimdShiftAcc                  0      0.00%     80.25%
+system.cpu0.op_class::SimdSqrt                      0      0.00%     80.25%
+system.cpu0.op_class::SimdFloatAdd                  0      0.00%     80.25%
+system.cpu0.op_class::SimdFloatAlu                  0      0.00%     80.25%
+system.cpu0.op_class::SimdFloatCmp                  0      0.00%     80.25%
+system.cpu0.op_class::SimdFloatCvt                  0      0.00%     80.25%
+system.cpu0.op_class::SimdFloatDiv                  0      0.00%     80.25%
+system.cpu0.op_class::SimdFloatMisc                 0      0.00%     80.25%
+system.cpu0.op_class::SimdFloatMult                 0      0.00%     80.25%
+system.cpu0.op_class::SimdFloatMultAcc              0      0.00%     80.25%
+system.cpu0.op_class::SimdFloatSqrt                 0      0.00%     80.25%
+system.cpu0.op_class::MemRead                   16382     11.90%     92.15%
+system.cpu0.op_class::MemWrite                  10514      7.64%     99.78%
+system.cpu0.op_class::FloatMemRead                302      0.22%    100.00%
+system.cpu0.op_class::FloatMemWrite                 0      0.00%    100.00%
+system.cpu0.op_class::IprAccess                     0      0.00%    100.00%
+system.cpu0.op_class::InstPrefetch                  0      0.00%    100.00%
+system.cpu0.op_class::total                    137705                      
+system.cpu1.clk_domain.voltage_domain.voltage            1                      
+system.cpu1.clk_domain.clock                     1000                      
+system.cpu1.CUs0.localDataStore.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.cpu1.CUs0.wavefronts00.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts00.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts00.timesBlockedDueRAWDependencies          309                      
+system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::samples           39                      
+system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::mean     0.794872                      
+system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::stdev     0.863880                      
+system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::underflows            0      0.00%      0.00%
+system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::0-1           28     71.79%     71.79%
+system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::2-3           11     28.21%    100.00%
+system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::4            0      0.00%    100.00%
+system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::overflows            0      0.00%    100.00%
+system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::max_value            2                      
+system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::total           39                      
+system.cpu1.CUs0.wavefronts00.dst_reg_operand_dist::samples           39                      
+system.cpu1.CUs0.wavefronts00.dst_reg_operand_dist::mean     0.589744                      
+system.cpu1.CUs0.wavefronts00.dst_reg_operand_dist::stdev     0.498310                      
+system.cpu1.CUs0.wavefronts00.dst_reg_operand_dist::underflows            0      0.00%      0.00%
+system.cpu1.CUs0.wavefronts00.dst_reg_operand_dist::0-1           39    100.00%    100.00%
+system.cpu1.CUs0.wavefronts00.dst_reg_operand_dist::2-3            0      0.00%    100.00%
+system.cpu1.CUs0.wavefronts00.dst_reg_operand_dist::overflows            0      0.00%    100.00%
+system.cpu1.CUs0.wavefronts00.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts00.dst_reg_operand_dist::max_value            1                      
+system.cpu1.CUs0.wavefronts00.dst_reg_operand_dist::total           39                      
+system.cpu1.CUs0.wavefronts01.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts01.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts01.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts01.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts01.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts01.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts01.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts01.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts01.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts01.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts01.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts01.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts01.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts01.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts01.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts01.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts01.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts01.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts01.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts01.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts01.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts01.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts01.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts01.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts02.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts02.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts02.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts02.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts02.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts02.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts02.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts02.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts02.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts02.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts02.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts02.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts02.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts02.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts02.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts02.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts02.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts02.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts02.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts02.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts02.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts02.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts02.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts02.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts03.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts03.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts03.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts03.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts03.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts03.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts03.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts03.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts03.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts03.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts03.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts03.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts03.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts03.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts03.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts03.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts03.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts03.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts03.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts03.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts03.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts03.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts03.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts03.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts04.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts04.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts04.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts04.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts04.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts04.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts04.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts04.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts04.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts04.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts04.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts04.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts04.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts04.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts04.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts04.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts04.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts04.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts04.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts04.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts04.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts04.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts04.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts04.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts05.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts05.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts05.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts05.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts05.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts05.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts05.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts05.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts05.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts05.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts05.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts05.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts05.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts05.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts05.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts05.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts05.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts05.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts05.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts05.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts05.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts05.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts05.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts05.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts06.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts06.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts06.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts06.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts06.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts06.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts06.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts06.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts06.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts06.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts06.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts06.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts06.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts06.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts06.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts06.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts06.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts06.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts06.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts06.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts06.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts06.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts06.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts06.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts07.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts07.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts07.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts07.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts07.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts07.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts07.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts07.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts07.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts07.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts07.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts07.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts07.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts07.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts07.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts07.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts07.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts07.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts07.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts07.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts07.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts07.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts07.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts07.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts08.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts08.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts08.timesBlockedDueRAWDependencies          284                      
+system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::samples           34                      
+system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::mean     0.852941                      
+system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::stdev     0.857493                      
+system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::underflows            0      0.00%      0.00%
+system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::0-1           24     70.59%     70.59%
+system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::2-3           10     29.41%    100.00%
+system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::4            0      0.00%    100.00%
+system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::overflows            0      0.00%    100.00%
+system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::max_value            2                      
+system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::total           34                      
+system.cpu1.CUs0.wavefronts08.dst_reg_operand_dist::samples           34                      
+system.cpu1.CUs0.wavefronts08.dst_reg_operand_dist::mean     0.617647                      
+system.cpu1.CUs0.wavefronts08.dst_reg_operand_dist::stdev     0.493270                      
+system.cpu1.CUs0.wavefronts08.dst_reg_operand_dist::underflows            0      0.00%      0.00%
+system.cpu1.CUs0.wavefronts08.dst_reg_operand_dist::0-1           34    100.00%    100.00%
+system.cpu1.CUs0.wavefronts08.dst_reg_operand_dist::2-3            0      0.00%    100.00%
+system.cpu1.CUs0.wavefronts08.dst_reg_operand_dist::overflows            0      0.00%    100.00%
+system.cpu1.CUs0.wavefronts08.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts08.dst_reg_operand_dist::max_value            1                      
+system.cpu1.CUs0.wavefronts08.dst_reg_operand_dist::total           34                      
+system.cpu1.CUs0.wavefronts09.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts09.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts09.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts09.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts09.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts09.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts09.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts09.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts09.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts09.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts09.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts09.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts09.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts09.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts09.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts09.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts09.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts09.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts09.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts09.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts09.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts09.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts09.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts09.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts10.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts10.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts10.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts10.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts10.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts10.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts10.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts10.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts10.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts10.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts10.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts10.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts10.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts10.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts10.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts10.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts10.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts10.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts10.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts10.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts10.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts10.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts10.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts10.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts11.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts11.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts11.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts11.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts11.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts11.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts11.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts11.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts11.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts11.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts11.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts11.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts11.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts11.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts11.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts11.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts11.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts11.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts11.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts11.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts11.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts11.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts11.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts11.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts12.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts12.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts12.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts12.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts12.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts12.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts12.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts12.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts12.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts12.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts12.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts12.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts12.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts12.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts12.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts12.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts12.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts12.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts12.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts12.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts12.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts12.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts12.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts12.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts13.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts13.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts13.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts13.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts13.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts13.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts13.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts13.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts13.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts13.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts13.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts13.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts13.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts13.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts13.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts13.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts13.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts13.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts13.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts13.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts13.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts13.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts13.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts13.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts14.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts14.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts14.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts14.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts14.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts14.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts14.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts14.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts14.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts14.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts14.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts14.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts14.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts14.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts14.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts14.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts14.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts14.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts14.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts14.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts14.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts14.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts14.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts14.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts15.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts15.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts15.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts15.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts15.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts15.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts15.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts15.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts15.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts15.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts15.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts15.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts15.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts15.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts15.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts15.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts15.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts15.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts15.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts15.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts15.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts15.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts15.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts15.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts16.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts16.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts16.timesBlockedDueRAWDependencies          279                      
+system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::samples           34                      
+system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::mean     0.852941                      
+system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::stdev     0.857493                      
+system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::underflows            0      0.00%      0.00%
+system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::0-1           24     70.59%     70.59%
+system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::2-3           10     29.41%    100.00%
+system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::4            0      0.00%    100.00%
+system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::overflows            0      0.00%    100.00%
+system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::max_value            2                      
+system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::total           34                      
+system.cpu1.CUs0.wavefronts16.dst_reg_operand_dist::samples           34                      
+system.cpu1.CUs0.wavefronts16.dst_reg_operand_dist::mean     0.617647                      
+system.cpu1.CUs0.wavefronts16.dst_reg_operand_dist::stdev     0.493270                      
+system.cpu1.CUs0.wavefronts16.dst_reg_operand_dist::underflows            0      0.00%      0.00%
+system.cpu1.CUs0.wavefronts16.dst_reg_operand_dist::0-1           34    100.00%    100.00%
+system.cpu1.CUs0.wavefronts16.dst_reg_operand_dist::2-3            0      0.00%    100.00%
+system.cpu1.CUs0.wavefronts16.dst_reg_operand_dist::overflows            0      0.00%    100.00%
+system.cpu1.CUs0.wavefronts16.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts16.dst_reg_operand_dist::max_value            1                      
+system.cpu1.CUs0.wavefronts16.dst_reg_operand_dist::total           34                      
+system.cpu1.CUs0.wavefronts17.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts17.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts17.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts17.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts17.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts17.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts17.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts17.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts17.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts17.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts17.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts17.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts17.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts17.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts17.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts17.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts17.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts17.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts17.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts17.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts17.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts17.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts17.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts17.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts18.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts18.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts18.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts18.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts18.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts18.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts18.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts18.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts18.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts18.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts18.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts18.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts18.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts18.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts18.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts18.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts18.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts18.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts18.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts18.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts18.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts18.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts18.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts18.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts19.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts19.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts19.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts19.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts19.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts19.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts19.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts19.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts19.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts19.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts19.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts19.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts19.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts19.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts19.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts19.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts19.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts19.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts19.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts19.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts19.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts19.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts19.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts19.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts20.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts20.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts20.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts20.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts20.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts20.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts20.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts20.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts20.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts20.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts20.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts20.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts20.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts20.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts20.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts20.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts20.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts20.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts20.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts20.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts20.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts20.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts20.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts20.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts21.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts21.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts21.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts21.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts21.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts21.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts21.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts21.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts21.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts21.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts21.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts21.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts21.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts21.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts21.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts21.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts21.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts21.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts21.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts21.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts21.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts21.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts21.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts21.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts22.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts22.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts22.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts22.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts22.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts22.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts22.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts22.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts22.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts22.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts22.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts22.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts22.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts22.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts22.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts22.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts22.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts22.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts22.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts22.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts22.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts22.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts22.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts22.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts23.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts23.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts23.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts23.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts23.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts23.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts23.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts23.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts23.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts23.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts23.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts23.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts23.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts23.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts23.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts23.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts23.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts23.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts23.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts23.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts23.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts23.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts23.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts23.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts24.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts24.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts24.timesBlockedDueRAWDependencies          274                      
+system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::samples           34                      
+system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::mean     0.852941                      
+system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::stdev     0.857493                      
+system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::underflows            0      0.00%      0.00%
+system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::0-1           24     70.59%     70.59%
+system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::2-3           10     29.41%    100.00%
+system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::4            0      0.00%    100.00%
+system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::overflows            0      0.00%    100.00%
+system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::max_value            2                      
+system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::total           34                      
+system.cpu1.CUs0.wavefronts24.dst_reg_operand_dist::samples           34                      
+system.cpu1.CUs0.wavefronts24.dst_reg_operand_dist::mean     0.617647                      
+system.cpu1.CUs0.wavefronts24.dst_reg_operand_dist::stdev     0.493270                      
+system.cpu1.CUs0.wavefronts24.dst_reg_operand_dist::underflows            0      0.00%      0.00%
+system.cpu1.CUs0.wavefronts24.dst_reg_operand_dist::0-1           34    100.00%    100.00%
+system.cpu1.CUs0.wavefronts24.dst_reg_operand_dist::2-3            0      0.00%    100.00%
+system.cpu1.CUs0.wavefronts24.dst_reg_operand_dist::overflows            0      0.00%    100.00%
+system.cpu1.CUs0.wavefronts24.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts24.dst_reg_operand_dist::max_value            1                      
+system.cpu1.CUs0.wavefronts24.dst_reg_operand_dist::total           34                      
+system.cpu1.CUs0.wavefronts25.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts25.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts25.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts25.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts25.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts25.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts25.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts25.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts25.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts25.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts25.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts25.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts25.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts25.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts25.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts25.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts25.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts25.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts25.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts25.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts25.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts25.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts25.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts25.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts26.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts26.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts26.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts26.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts26.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts26.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts26.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts26.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts26.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts26.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts26.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts26.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts26.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts26.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts26.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts26.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts26.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts26.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts26.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts26.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts26.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts26.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts26.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts26.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts27.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts27.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts27.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts27.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts27.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts27.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts27.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts27.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts27.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts27.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts27.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts27.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts27.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts27.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts27.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts27.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts27.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts27.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts27.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts27.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts27.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts27.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts27.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts27.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts28.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts28.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts28.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts28.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts28.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts28.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts28.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts28.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts28.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts28.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts28.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts28.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts28.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts28.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts28.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts28.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts28.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts28.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts28.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts28.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts28.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts28.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts28.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts28.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts29.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts29.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts29.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts29.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts29.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts29.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts29.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts29.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts29.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts29.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts29.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts29.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts29.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts29.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts29.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts29.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts29.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts29.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts29.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts29.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts29.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts29.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts29.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts29.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts30.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts30.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts30.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts30.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts30.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts30.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts30.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts30.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts30.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts30.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts30.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts30.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts30.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts30.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts30.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts30.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts30.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts30.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts30.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts30.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts30.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts30.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts30.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts30.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts31.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs0.wavefronts31.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs0.wavefronts31.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs0.wavefronts31.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts31.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts31.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts31.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts31.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts31.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts31.src_reg_operand_dist::4            0                      
+system.cpu1.CUs0.wavefronts31.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts31.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts31.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts31.src_reg_operand_dist::total            0                      
+system.cpu1.CUs0.wavefronts31.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs0.wavefronts31.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs0.wavefronts31.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs0.wavefronts31.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs0.wavefronts31.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs0.wavefronts31.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs0.wavefronts31.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs0.wavefronts31.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs0.wavefronts31.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs0.wavefronts31.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs0.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::samples           35                      
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::mean    11.257143                      
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::stdev     5.595917                      
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::underflows            0      0.00%      0.00%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::1            0      0.00%      0.00%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::2            4     11.43%     11.43%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::3            4     11.43%     22.86%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::4            1      2.86%     25.71%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::5            0      0.00%     25.71%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::6            0      0.00%     25.71%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::7            0      0.00%     25.71%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::8            0      0.00%     25.71%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::9            0      0.00%     25.71%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::10            4     11.43%     37.14%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::11            4     11.43%     48.57%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::12            0      0.00%     48.57%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::13            0      0.00%     48.57%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::14            1      2.86%     51.43%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::15            0      0.00%     51.43%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::16           17     48.57%    100.00%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::17            0      0.00%    100.00%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::18            0      0.00%    100.00%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::19            0      0.00%    100.00%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::20            0      0.00%    100.00%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::21            0      0.00%    100.00%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::22            0      0.00%    100.00%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::23            0      0.00%    100.00%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::24            0      0.00%    100.00%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::25            0      0.00%    100.00%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::26            0      0.00%    100.00%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::27            0      0.00%    100.00%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::28            0      0.00%    100.00%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::29            0      0.00%    100.00%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::30            0      0.00%    100.00%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::31            0      0.00%    100.00%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::32            0      0.00%    100.00%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::overflows            0      0.00%    100.00%
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::min_value            2                      
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::max_value           16                      
+system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::total           35                      
+system.cpu1.CUs0.ExecStage.num_cycles_with_no_issue         2741                      
+system.cpu1.CUs0.ExecStage.num_cycles_with_instr_issued           99                      
+system.cpu1.CUs0.ExecStage.num_cycles_with_instrtype_issue::ALU0           30                      
+system.cpu1.CUs0.ExecStage.num_cycles_with_instrtype_issue::ALU1           29                      
+system.cpu1.CUs0.ExecStage.num_cycles_with_instrtype_issue::ALU2           29                      
+system.cpu1.CUs0.ExecStage.num_cycles_with_instrtype_issue::ALU3           29                      
+system.cpu1.CUs0.ExecStage.num_cycles_with_instrtype_issue::GM           18                      
+system.cpu1.CUs0.ExecStage.num_cycles_with_instrtype_issue::LM            6                      
+system.cpu1.CUs0.ExecStage.num_cycles_with_instr_type_no_issue::ALU0          625                      
+system.cpu1.CUs0.ExecStage.num_cycles_with_instr_type_no_issue::ALU1          340                      
+system.cpu1.CUs0.ExecStage.num_cycles_with_instr_type_no_issue::ALU2          338                      
+system.cpu1.CUs0.ExecStage.num_cycles_with_instr_type_no_issue::ALU3          335                      
+system.cpu1.CUs0.ExecStage.num_cycles_with_instr_type_no_issue::GM          404                      
+system.cpu1.CUs0.ExecStage.num_cycles_with_instr_type_no_issue::LM           22                      
+system.cpu1.CUs0.ExecStage.spc::samples          2840                      
+system.cpu1.CUs0.ExecStage.spc::mean         0.049648                      
+system.cpu1.CUs0.ExecStage.spc::stdev        0.277106                      
+system.cpu1.CUs0.ExecStage.spc::underflows            0      0.00%      0.00%
+system.cpu1.CUs0.ExecStage.spc::0                2741     96.51%     96.51%
+system.cpu1.CUs0.ExecStage.spc::1                  57      2.01%     98.52%
+system.cpu1.CUs0.ExecStage.spc::2                  42      1.48%    100.00%
+system.cpu1.CUs0.ExecStage.spc::3                   0      0.00%    100.00%
+system.cpu1.CUs0.ExecStage.spc::4                   0      0.00%    100.00%
+system.cpu1.CUs0.ExecStage.spc::5                   0      0.00%    100.00%
+system.cpu1.CUs0.ExecStage.spc::6                   0      0.00%    100.00%
+system.cpu1.CUs0.ExecStage.spc::overflows            0      0.00%    100.00%
+system.cpu1.CUs0.ExecStage.spc::min_value            0                      
+system.cpu1.CUs0.ExecStage.spc::max_value            2                      
+system.cpu1.CUs0.ExecStage.spc::total            2840                      
+system.cpu1.CUs0.ExecStage.num_transitions_active_to_idle           90                      
+system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::samples           90                      
+system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::mean    29.322222                      
+system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::stdev   145.995831                      
+system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::underflows            0      0.00%      0.00%
+system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::0-4           76     84.44%     84.44%
+system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::5-9            7      7.78%     92.22%
+system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::10-14            0      0.00%     92.22%
+system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::15-19            0      0.00%     92.22%
+system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::20-24            0      0.00%     92.22%
+system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::25-29            1      1.11%     93.33%
+system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::30-34            0      0.00%     93.33%
+system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::35-39            0      0.00%     93.33%
+system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::40-44            0      0.00%     93.33%
+system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::45-49            0      0.00%     93.33%
+system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::50-54            0      0.00%     93.33%
+system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::55-59            0      0.00%     93.33%
+system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::60-64            0      0.00%     93.33%
+system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::65-69            0      0.00%     93.33%
+system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::70-74            0      0.00%     93.33%
+system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::75            0      0.00%     93.33%
+system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::overflows            6      6.67%    100.00%
+system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::min_value            1                      
+system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::max_value         1291                      
+system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::total           90                      
+system.cpu1.CUs0.GlobalMemPipeline.load_vrf_bank_conflict_cycles            0                      
+system.cpu1.CUs0.LocalMemPipeline.load_vrf_bank_conflict_cycles            0                      
+system.cpu1.CUs0.valu_insts                        68                      
+system.cpu1.CUs0.valu_insts_per_wf                 17                      
+system.cpu1.CUs0.salu_insts                         0                      
+system.cpu1.CUs0.salu_insts_per_wf                  0                      
+system.cpu1.CUs0.inst_cycles_valu                  68                      
+system.cpu1.CUs0.inst_cycles_salu                   0                      
+system.cpu1.CUs0.thread_cycles_valu              3076                      
+system.cpu1.CUs0.valu_utilization           70.680147                      
+system.cpu1.CUs0.lds_no_flat_insts                  6                      
+system.cpu1.CUs0.lds_no_flat_insts_per_wf     1.500000                      
+system.cpu1.CUs0.flat_vmem_insts                    0                      
+system.cpu1.CUs0.flat_vmem_insts_per_wf             0                      
+system.cpu1.CUs0.flat_lds_insts                     0                      
+system.cpu1.CUs0.flat_lds_insts_per_wf              0                      
+system.cpu1.CUs0.vector_mem_writes                  8                      
+system.cpu1.CUs0.vector_mem_writes_per_wf            2                      
+system.cpu1.CUs0.vector_mem_reads                  29                      
+system.cpu1.CUs0.vector_mem_reads_per_wf     7.250000                      
+system.cpu1.CUs0.scalar_mem_writes                  0                      
+system.cpu1.CUs0.scalar_mem_writes_per_wf            0                      
+system.cpu1.CUs0.scalar_mem_reads                   0                      
+system.cpu1.CUs0.scalar_mem_reads_per_wf            0                      
+system.cpu1.CUs0.tlb_requests                     769                      
+system.cpu1.CUs0.tlb_cycles              -454892896000                      
+system.cpu1.CUs0.avg_translation_latency -591538226.267880                      
+system.cpu1.CUs0.TLB_hits_distribution::page_table          769                      
+system.cpu1.CUs0.TLB_hits_distribution::L1_TLB            0                      
+system.cpu1.CUs0.TLB_hits_distribution::L2_TLB            0                      
+system.cpu1.CUs0.TLB_hits_distribution::L3_TLB            0                      
+system.cpu1.CUs0.lds_bank_access_cnt               54                      
+system.cpu1.CUs0.lds_bank_conflicts::samples            6                      
+system.cpu1.CUs0.lds_bank_conflicts::mean            8                      
+system.cpu1.CUs0.lds_bank_conflicts::stdev     6.196773                      
+system.cpu1.CUs0.lds_bank_conflicts::underflows            0      0.00%      0.00%
+system.cpu1.CUs0.lds_bank_conflicts::0-1            2     33.33%     33.33%
+system.cpu1.CUs0.lds_bank_conflicts::2-3            0      0.00%     33.33%
+system.cpu1.CUs0.lds_bank_conflicts::4-5            0      0.00%     33.33%
+system.cpu1.CUs0.lds_bank_conflicts::6-7            0      0.00%     33.33%
+system.cpu1.CUs0.lds_bank_conflicts::8-9            0      0.00%     33.33%
+system.cpu1.CUs0.lds_bank_conflicts::10-11            0      0.00%     33.33%
+system.cpu1.CUs0.lds_bank_conflicts::12-13            4     66.67%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::14-15            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::16-17            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::18-19            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::20-21            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::22-23            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::24-25            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::26-27            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::28-29            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::30-31            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::32-33            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::34-35            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::36-37            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::38-39            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::40-41            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::42-43            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::44-45            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::46-47            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::48-49            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::50-51            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::52-53            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::54-55            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::56-57            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::58-59            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::60-61            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::62-63            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::64             0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::overflows            0      0.00%    100.00%
+system.cpu1.CUs0.lds_bank_conflicts::min_value            0                      
+system.cpu1.CUs0.lds_bank_conflicts::max_value           12                      
+system.cpu1.CUs0.lds_bank_conflicts::total            6                      
+system.cpu1.CUs0.page_divergence_dist::samples           17                      
+system.cpu1.CUs0.page_divergence_dist::mean            1                      
+system.cpu1.CUs0.page_divergence_dist::stdev            0                      
+system.cpu1.CUs0.page_divergence_dist::underflows            0      0.00%      0.00%
+system.cpu1.CUs0.page_divergence_dist::1-4           17    100.00%    100.00%
+system.cpu1.CUs0.page_divergence_dist::5-8            0      0.00%    100.00%
+system.cpu1.CUs0.page_divergence_dist::9-12            0      0.00%    100.00%
+system.cpu1.CUs0.page_divergence_dist::13-16            0      0.00%    100.00%
+system.cpu1.CUs0.page_divergence_dist::17-20            0      0.00%    100.00%
+system.cpu1.CUs0.page_divergence_dist::21-24            0      0.00%    100.00%
+system.cpu1.CUs0.page_divergence_dist::25-28            0      0.00%    100.00%
+system.cpu1.CUs0.page_divergence_dist::29-32            0      0.00%    100.00%
+system.cpu1.CUs0.page_divergence_dist::33-36            0      0.00%    100.00%
+system.cpu1.CUs0.page_divergence_dist::37-40            0      0.00%    100.00%
+system.cpu1.CUs0.page_divergence_dist::41-44            0      0.00%    100.00%
+system.cpu1.CUs0.page_divergence_dist::45-48            0      0.00%    100.00%
+system.cpu1.CUs0.page_divergence_dist::49-52            0      0.00%    100.00%
+system.cpu1.CUs0.page_divergence_dist::53-56            0      0.00%    100.00%
+system.cpu1.CUs0.page_divergence_dist::57-60            0      0.00%    100.00%
+system.cpu1.CUs0.page_divergence_dist::61-64            0      0.00%    100.00%
+system.cpu1.CUs0.page_divergence_dist::overflows            0      0.00%    100.00%
+system.cpu1.CUs0.page_divergence_dist::min_value            1                      
+system.cpu1.CUs0.page_divergence_dist::max_value            1                      
+system.cpu1.CUs0.page_divergence_dist::total           17                      
+system.cpu1.CUs0.global_mem_instr_cnt              17                      
+system.cpu1.CUs0.local_mem_instr_cnt                6                      
+system.cpu1.CUs0.wg_blocked_due_lds_alloc            0                      
+system.cpu1.CUs0.num_instr_executed               141                      
+system.cpu1.CUs0.inst_exec_rate::samples          141                      
+system.cpu1.CUs0.inst_exec_rate::mean       71.028369                      
+system.cpu1.CUs0.inst_exec_rate::stdev     225.061514                      
+system.cpu1.CUs0.inst_exec_rate::underflows            0      0.00%      0.00%
+system.cpu1.CUs0.inst_exec_rate::0-1                0      0.00%      0.00%
+system.cpu1.CUs0.inst_exec_rate::2-3               12      8.51%      8.51%
+system.cpu1.CUs0.inst_exec_rate::4-5               61     43.26%     51.77%
+system.cpu1.CUs0.inst_exec_rate::6-7               32     22.70%     74.47%
+system.cpu1.CUs0.inst_exec_rate::8-9                3      2.13%     76.60%
+system.cpu1.CUs0.inst_exec_rate::10                 3      2.13%     78.72%
+system.cpu1.CUs0.inst_exec_rate::overflows           30     21.28%    100.00%
+system.cpu1.CUs0.inst_exec_rate::min_value            2                      
+system.cpu1.CUs0.inst_exec_rate::max_value         1297                      
+system.cpu1.CUs0.inst_exec_rate::total            141                      
+system.cpu1.CUs0.num_vec_ops_executed            6769                      
+system.cpu1.CUs0.num_total_cycles                2840                      
+system.cpu1.CUs0.vpc                         2.383451                      
+system.cpu1.CUs0.ipc                         0.049648                      
+system.cpu1.CUs0.warp_execution_dist::samples          141                      
+system.cpu1.CUs0.warp_execution_dist::mean    48.007092                      
+system.cpu1.CUs0.warp_execution_dist::stdev    23.719942                      
+system.cpu1.CUs0.warp_execution_dist::underflows            0      0.00%      0.00%
+system.cpu1.CUs0.warp_execution_dist::1-4            5      3.55%      3.55%
+system.cpu1.CUs0.warp_execution_dist::5-8            0      0.00%      3.55%
+system.cpu1.CUs0.warp_execution_dist::9-12            0      0.00%      3.55%
+system.cpu1.CUs0.warp_execution_dist::13-16           36     25.53%     29.08%
+system.cpu1.CUs0.warp_execution_dist::17-20            0      0.00%     29.08%
+system.cpu1.CUs0.warp_execution_dist::21-24            0      0.00%     29.08%
+system.cpu1.CUs0.warp_execution_dist::25-28            0      0.00%     29.08%
+system.cpu1.CUs0.warp_execution_dist::29-32            0      0.00%     29.08%
+system.cpu1.CUs0.warp_execution_dist::33-36            0      0.00%     29.08%
+system.cpu1.CUs0.warp_execution_dist::37-40            0      0.00%     29.08%
+system.cpu1.CUs0.warp_execution_dist::41-44            0      0.00%     29.08%
+system.cpu1.CUs0.warp_execution_dist::45-48            0      0.00%     29.08%
+system.cpu1.CUs0.warp_execution_dist::49-52            8      5.67%     34.75%
+system.cpu1.CUs0.warp_execution_dist::53-56            0      0.00%     34.75%
+system.cpu1.CUs0.warp_execution_dist::57-60            0      0.00%     34.75%
+system.cpu1.CUs0.warp_execution_dist::61-64           92     65.25%    100.00%
+system.cpu1.CUs0.warp_execution_dist::overflows            0      0.00%    100.00%
+system.cpu1.CUs0.warp_execution_dist::min_value            1                      
+system.cpu1.CUs0.warp_execution_dist::max_value           64                      
+system.cpu1.CUs0.warp_execution_dist::total          141                      
+system.cpu1.CUs0.gmem_lanes_execution_dist::samples           18                      
+system.cpu1.CUs0.gmem_lanes_execution_dist::mean    37.833333                      
+system.cpu1.CUs0.gmem_lanes_execution_dist::stdev    27.064737                      
+system.cpu1.CUs0.gmem_lanes_execution_dist::underflows            0      0.00%      0.00%
+system.cpu1.CUs0.gmem_lanes_execution_dist::1-4            1      5.56%      5.56%
+system.cpu1.CUs0.gmem_lanes_execution_dist::5-8            0      0.00%      5.56%
+system.cpu1.CUs0.gmem_lanes_execution_dist::9-12            0      0.00%      5.56%
+system.cpu1.CUs0.gmem_lanes_execution_dist::13-16            8     44.44%     50.00%
+system.cpu1.CUs0.gmem_lanes_execution_dist::17-20            0      0.00%     50.00%
+system.cpu1.CUs0.gmem_lanes_execution_dist::21-24            0      0.00%     50.00%
+system.cpu1.CUs0.gmem_lanes_execution_dist::25-28            0      0.00%     50.00%
+system.cpu1.CUs0.gmem_lanes_execution_dist::29-32            0      0.00%     50.00%
+system.cpu1.CUs0.gmem_lanes_execution_dist::33-36            0      0.00%     50.00%
+system.cpu1.CUs0.gmem_lanes_execution_dist::37-40            0      0.00%     50.00%
+system.cpu1.CUs0.gmem_lanes_execution_dist::41-44            0      0.00%     50.00%
+system.cpu1.CUs0.gmem_lanes_execution_dist::45-48            0      0.00%     50.00%
+system.cpu1.CUs0.gmem_lanes_execution_dist::49-52            0      0.00%     50.00%
+system.cpu1.CUs0.gmem_lanes_execution_dist::53-56            0      0.00%     50.00%
+system.cpu1.CUs0.gmem_lanes_execution_dist::57-60            0      0.00%     50.00%
+system.cpu1.CUs0.gmem_lanes_execution_dist::61-64            9     50.00%    100.00%
+system.cpu1.CUs0.gmem_lanes_execution_dist::overflows            0      0.00%    100.00%
+system.cpu1.CUs0.gmem_lanes_execution_dist::min_value            1                      
+system.cpu1.CUs0.gmem_lanes_execution_dist::max_value           64                      
+system.cpu1.CUs0.gmem_lanes_execution_dist::total           18                      
+system.cpu1.CUs0.lmem_lanes_execution_dist::samples            6                      
+system.cpu1.CUs0.lmem_lanes_execution_dist::mean    19.500000                      
+system.cpu1.CUs0.lmem_lanes_execution_dist::stdev    22.322634                      
+system.cpu1.CUs0.lmem_lanes_execution_dist::underflows            0      0.00%      0.00%
+system.cpu1.CUs0.lmem_lanes_execution_dist::1-4            1     16.67%     16.67%
+system.cpu1.CUs0.lmem_lanes_execution_dist::5-8            0      0.00%     16.67%
+system.cpu1.CUs0.lmem_lanes_execution_dist::9-12            0      0.00%     16.67%
+system.cpu1.CUs0.lmem_lanes_execution_dist::13-16            4     66.67%     83.33%
+system.cpu1.CUs0.lmem_lanes_execution_dist::17-20            0      0.00%     83.33%
+system.cpu1.CUs0.lmem_lanes_execution_dist::21-24            0      0.00%     83.33%
+system.cpu1.CUs0.lmem_lanes_execution_dist::25-28            0      0.00%     83.33%
+system.cpu1.CUs0.lmem_lanes_execution_dist::29-32            0      0.00%     83.33%
+system.cpu1.CUs0.lmem_lanes_execution_dist::33-36            0      0.00%     83.33%
+system.cpu1.CUs0.lmem_lanes_execution_dist::37-40            0      0.00%     83.33%
+system.cpu1.CUs0.lmem_lanes_execution_dist::41-44            0      0.00%     83.33%
+system.cpu1.CUs0.lmem_lanes_execution_dist::45-48            0      0.00%     83.33%
+system.cpu1.CUs0.lmem_lanes_execution_dist::49-52            0      0.00%     83.33%
+system.cpu1.CUs0.lmem_lanes_execution_dist::53-56            0      0.00%     83.33%
+system.cpu1.CUs0.lmem_lanes_execution_dist::57-60            0      0.00%     83.33%
+system.cpu1.CUs0.lmem_lanes_execution_dist::61-64            1     16.67%    100.00%
+system.cpu1.CUs0.lmem_lanes_execution_dist::overflows            0      0.00%    100.00%
+system.cpu1.CUs0.lmem_lanes_execution_dist::min_value            1                      
+system.cpu1.CUs0.lmem_lanes_execution_dist::max_value           64                      
+system.cpu1.CUs0.lmem_lanes_execution_dist::total            6                      
+system.cpu1.CUs0.num_alu_insts_executed           118                      
+system.cpu1.CUs0.times_wg_blocked_due_vgpr_alloc            0                      
+system.cpu1.CUs0.num_CAS_ops                        0                      
+system.cpu1.CUs0.num_failed_CAS_ops                 0                      
+system.cpu1.CUs0.num_completed_wfs                  4                      
+system.cpu1.CUs1.localDataStore.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.cpu1.CUs1.wavefronts00.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts00.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts00.timesBlockedDueRAWDependencies          406                      
+system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::samples           39                      
+system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::mean     0.794872                      
+system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::stdev     0.863880                      
+system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::underflows            0      0.00%      0.00%
+system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::0-1           28     71.79%     71.79%
+system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::2-3           11     28.21%    100.00%
+system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::4            0      0.00%    100.00%
+system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::overflows            0      0.00%    100.00%
+system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::max_value            2                      
+system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::total           39                      
+system.cpu1.CUs1.wavefronts00.dst_reg_operand_dist::samples           39                      
+system.cpu1.CUs1.wavefronts00.dst_reg_operand_dist::mean     0.589744                      
+system.cpu1.CUs1.wavefronts00.dst_reg_operand_dist::stdev     0.498310                      
+system.cpu1.CUs1.wavefronts00.dst_reg_operand_dist::underflows            0      0.00%      0.00%
+system.cpu1.CUs1.wavefronts00.dst_reg_operand_dist::0-1           39    100.00%    100.00%
+system.cpu1.CUs1.wavefronts00.dst_reg_operand_dist::2-3            0      0.00%    100.00%
+system.cpu1.CUs1.wavefronts00.dst_reg_operand_dist::overflows            0      0.00%    100.00%
+system.cpu1.CUs1.wavefronts00.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts00.dst_reg_operand_dist::max_value            1                      
+system.cpu1.CUs1.wavefronts00.dst_reg_operand_dist::total           39                      
+system.cpu1.CUs1.wavefronts01.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts01.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts01.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts01.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts01.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts01.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts01.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts01.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts01.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts01.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts01.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts01.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts01.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts01.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts01.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts01.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts01.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts01.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts01.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts01.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts01.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts01.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts01.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts01.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts02.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts02.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts02.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts02.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts02.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts02.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts02.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts02.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts02.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts02.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts02.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts02.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts02.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts02.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts02.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts02.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts02.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts02.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts02.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts02.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts02.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts02.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts02.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts02.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts03.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts03.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts03.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts03.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts03.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts03.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts03.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts03.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts03.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts03.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts03.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts03.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts03.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts03.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts03.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts03.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts03.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts03.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts03.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts03.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts03.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts03.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts03.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts03.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts04.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts04.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts04.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts04.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts04.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts04.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts04.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts04.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts04.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts04.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts04.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts04.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts04.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts04.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts04.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts04.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts04.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts04.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts04.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts04.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts04.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts04.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts04.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts04.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts05.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts05.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts05.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts05.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts05.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts05.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts05.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts05.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts05.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts05.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts05.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts05.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts05.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts05.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts05.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts05.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts05.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts05.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts05.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts05.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts05.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts05.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts05.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts05.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts06.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts06.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts06.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts06.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts06.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts06.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts06.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts06.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts06.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts06.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts06.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts06.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts06.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts06.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts06.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts06.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts06.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts06.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts06.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts06.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts06.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts06.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts06.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts06.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts07.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts07.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts07.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts07.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts07.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts07.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts07.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts07.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts07.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts07.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts07.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts07.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts07.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts07.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts07.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts07.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts07.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts07.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts07.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts07.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts07.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts07.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts07.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts07.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts08.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts08.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts08.timesBlockedDueRAWDependencies          381                      
+system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::samples           34                      
+system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::mean     0.852941                      
+system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::stdev     0.857493                      
+system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::underflows            0      0.00%      0.00%
+system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::0-1           24     70.59%     70.59%
+system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::2-3           10     29.41%    100.00%
+system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::4            0      0.00%    100.00%
+system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::overflows            0      0.00%    100.00%
+system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::max_value            2                      
+system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::total           34                      
+system.cpu1.CUs1.wavefronts08.dst_reg_operand_dist::samples           34                      
+system.cpu1.CUs1.wavefronts08.dst_reg_operand_dist::mean     0.617647                      
+system.cpu1.CUs1.wavefronts08.dst_reg_operand_dist::stdev     0.493270                      
+system.cpu1.CUs1.wavefronts08.dst_reg_operand_dist::underflows            0      0.00%      0.00%
+system.cpu1.CUs1.wavefronts08.dst_reg_operand_dist::0-1           34    100.00%    100.00%
+system.cpu1.CUs1.wavefronts08.dst_reg_operand_dist::2-3            0      0.00%    100.00%
+system.cpu1.CUs1.wavefronts08.dst_reg_operand_dist::overflows            0      0.00%    100.00%
+system.cpu1.CUs1.wavefronts08.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts08.dst_reg_operand_dist::max_value            1                      
+system.cpu1.CUs1.wavefronts08.dst_reg_operand_dist::total           34                      
+system.cpu1.CUs1.wavefronts09.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts09.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts09.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts09.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts09.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts09.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts09.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts09.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts09.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts09.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts09.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts09.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts09.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts09.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts09.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts09.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts09.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts09.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts09.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts09.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts09.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts09.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts09.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts09.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts10.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts10.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts10.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts10.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts10.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts10.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts10.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts10.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts10.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts10.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts10.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts10.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts10.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts10.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts10.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts10.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts10.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts10.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts10.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts10.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts10.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts10.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts10.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts10.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts11.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts11.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts11.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts11.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts11.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts11.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts11.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts11.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts11.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts11.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts11.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts11.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts11.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts11.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts11.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts11.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts11.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts11.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts11.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts11.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts11.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts11.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts11.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts11.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts12.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts12.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts12.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts12.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts12.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts12.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts12.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts12.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts12.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts12.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts12.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts12.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts12.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts12.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts12.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts12.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts12.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts12.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts12.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts12.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts12.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts12.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts12.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts12.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts13.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts13.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts13.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts13.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts13.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts13.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts13.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts13.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts13.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts13.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts13.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts13.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts13.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts13.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts13.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts13.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts13.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts13.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts13.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts13.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts13.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts13.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts13.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts13.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts14.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts14.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts14.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts14.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts14.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts14.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts14.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts14.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts14.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts14.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts14.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts14.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts14.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts14.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts14.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts14.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts14.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts14.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts14.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts14.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts14.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts14.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts14.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts14.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts15.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts15.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts15.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts15.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts15.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts15.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts15.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts15.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts15.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts15.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts15.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts15.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts15.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts15.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts15.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts15.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts15.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts15.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts15.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts15.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts15.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts15.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts15.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts15.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts16.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts16.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts16.timesBlockedDueRAWDependencies          372                      
+system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::samples           34                      
+system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::mean     0.852941                      
+system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::stdev     0.857493                      
+system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::underflows            0      0.00%      0.00%
+system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::0-1           24     70.59%     70.59%
+system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::2-3           10     29.41%    100.00%
+system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::4            0      0.00%    100.00%
+system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::overflows            0      0.00%    100.00%
+system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::max_value            2                      
+system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::total           34                      
+system.cpu1.CUs1.wavefronts16.dst_reg_operand_dist::samples           34                      
+system.cpu1.CUs1.wavefronts16.dst_reg_operand_dist::mean     0.617647                      
+system.cpu1.CUs1.wavefronts16.dst_reg_operand_dist::stdev     0.493270                      
+system.cpu1.CUs1.wavefronts16.dst_reg_operand_dist::underflows            0      0.00%      0.00%
+system.cpu1.CUs1.wavefronts16.dst_reg_operand_dist::0-1           34    100.00%    100.00%
+system.cpu1.CUs1.wavefronts16.dst_reg_operand_dist::2-3            0      0.00%    100.00%
+system.cpu1.CUs1.wavefronts16.dst_reg_operand_dist::overflows            0      0.00%    100.00%
+system.cpu1.CUs1.wavefronts16.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts16.dst_reg_operand_dist::max_value            1                      
+system.cpu1.CUs1.wavefronts16.dst_reg_operand_dist::total           34                      
+system.cpu1.CUs1.wavefronts17.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts17.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts17.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts17.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts17.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts17.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts17.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts17.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts17.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts17.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts17.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts17.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts17.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts17.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts17.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts17.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts17.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts17.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts17.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts17.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts17.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts17.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts17.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts17.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts18.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts18.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts18.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts18.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts18.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts18.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts18.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts18.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts18.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts18.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts18.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts18.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts18.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts18.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts18.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts18.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts18.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts18.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts18.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts18.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts18.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts18.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts18.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts18.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts19.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts19.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts19.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts19.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts19.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts19.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts19.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts19.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts19.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts19.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts19.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts19.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts19.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts19.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts19.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts19.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts19.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts19.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts19.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts19.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts19.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts19.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts19.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts19.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts20.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts20.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts20.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts20.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts20.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts20.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts20.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts20.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts20.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts20.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts20.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts20.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts20.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts20.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts20.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts20.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts20.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts20.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts20.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts20.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts20.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts20.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts20.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts20.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts21.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts21.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts21.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts21.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts21.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts21.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts21.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts21.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts21.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts21.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts21.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts21.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts21.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts21.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts21.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts21.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts21.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts21.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts21.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts21.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts21.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts21.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts21.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts21.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts22.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts22.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts22.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts22.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts22.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts22.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts22.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts22.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts22.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts22.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts22.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts22.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts22.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts22.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts22.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts22.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts22.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts22.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts22.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts22.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts22.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts22.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts22.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts22.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts23.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts23.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts23.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts23.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts23.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts23.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts23.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts23.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts23.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts23.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts23.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts23.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts23.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts23.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts23.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts23.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts23.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts23.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts23.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts23.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts23.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts23.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts23.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts23.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts24.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts24.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts24.timesBlockedDueRAWDependencies          364                      
+system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::samples           34                      
+system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::mean     0.852941                      
+system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::stdev     0.857493                      
+system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::underflows            0      0.00%      0.00%
+system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::0-1           24     70.59%     70.59%
+system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::2-3           10     29.41%    100.00%
+system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::4            0      0.00%    100.00%
+system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::overflows            0      0.00%    100.00%
+system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::max_value            2                      
+system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::total           34                      
+system.cpu1.CUs1.wavefronts24.dst_reg_operand_dist::samples           34                      
+system.cpu1.CUs1.wavefronts24.dst_reg_operand_dist::mean     0.617647                      
+system.cpu1.CUs1.wavefronts24.dst_reg_operand_dist::stdev     0.493270                      
+system.cpu1.CUs1.wavefronts24.dst_reg_operand_dist::underflows            0      0.00%      0.00%
+system.cpu1.CUs1.wavefronts24.dst_reg_operand_dist::0-1           34    100.00%    100.00%
+system.cpu1.CUs1.wavefronts24.dst_reg_operand_dist::2-3            0      0.00%    100.00%
+system.cpu1.CUs1.wavefronts24.dst_reg_operand_dist::overflows            0      0.00%    100.00%
+system.cpu1.CUs1.wavefronts24.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts24.dst_reg_operand_dist::max_value            1                      
+system.cpu1.CUs1.wavefronts24.dst_reg_operand_dist::total           34                      
+system.cpu1.CUs1.wavefronts25.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts25.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts25.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts25.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts25.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts25.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts25.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts25.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts25.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts25.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts25.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts25.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts25.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts25.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts25.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts25.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts25.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts25.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts25.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts25.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts25.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts25.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts25.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts25.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts26.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts26.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts26.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts26.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts26.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts26.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts26.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts26.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts26.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts26.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts26.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts26.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts26.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts26.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts26.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts26.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts26.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts26.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts26.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts26.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts26.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts26.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts26.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts26.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts27.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts27.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts27.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts27.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts27.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts27.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts27.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts27.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts27.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts27.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts27.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts27.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts27.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts27.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts27.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts27.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts27.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts27.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts27.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts27.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts27.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts27.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts27.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts27.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts28.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts28.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts28.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts28.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts28.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts28.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts28.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts28.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts28.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts28.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts28.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts28.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts28.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts28.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts28.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts28.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts28.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts28.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts28.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts28.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts28.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts28.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts28.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts28.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts29.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts29.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts29.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts29.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts29.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts29.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts29.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts29.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts29.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts29.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts29.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts29.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts29.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts29.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts29.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts29.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts29.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts29.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts29.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts29.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts29.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts29.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts29.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts29.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts30.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts30.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts30.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts30.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts30.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts30.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts30.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts30.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts30.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts30.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts30.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts30.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts30.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts30.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts30.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts30.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts30.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts30.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts30.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts30.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts30.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts30.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts30.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts30.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts31.timesBlockedDueVrfPortAvail            0                      
+system.cpu1.CUs1.wavefronts31.timesBlockedDueWAXDependencies            0                      
+system.cpu1.CUs1.wavefronts31.timesBlockedDueRAWDependencies            0                      
+system.cpu1.CUs1.wavefronts31.src_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts31.src_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts31.src_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts31.src_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts31.src_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts31.src_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts31.src_reg_operand_dist::4            0                      
+system.cpu1.CUs1.wavefronts31.src_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts31.src_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts31.src_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts31.src_reg_operand_dist::total            0                      
+system.cpu1.CUs1.wavefronts31.dst_reg_operand_dist::samples            0                      
+system.cpu1.CUs1.wavefronts31.dst_reg_operand_dist::mean          nan                      
+system.cpu1.CUs1.wavefronts31.dst_reg_operand_dist::stdev          nan                      
+system.cpu1.CUs1.wavefronts31.dst_reg_operand_dist::underflows            0                      
+system.cpu1.CUs1.wavefronts31.dst_reg_operand_dist::0-1            0                      
+system.cpu1.CUs1.wavefronts31.dst_reg_operand_dist::2-3            0                      
+system.cpu1.CUs1.wavefronts31.dst_reg_operand_dist::overflows            0                      
+system.cpu1.CUs1.wavefronts31.dst_reg_operand_dist::min_value            0                      
+system.cpu1.CUs1.wavefronts31.dst_reg_operand_dist::max_value            0                      
+system.cpu1.CUs1.wavefronts31.dst_reg_operand_dist::total            0                      
+system.cpu1.CUs1.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::samples           35                      
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::mean    11.257143                      
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::stdev     5.595917                      
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::underflows            0      0.00%      0.00%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::1            0      0.00%      0.00%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::2            4     11.43%     11.43%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::3            4     11.43%     22.86%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::4            1      2.86%     25.71%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::5            0      0.00%     25.71%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::6            0      0.00%     25.71%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::7            0      0.00%     25.71%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::8            0      0.00%     25.71%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::9            0      0.00%     25.71%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::10            4     11.43%     37.14%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::11            4     11.43%     48.57%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::12            0      0.00%     48.57%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::13            0      0.00%     48.57%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::14            1      2.86%     51.43%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::15            0      0.00%     51.43%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::16           17     48.57%    100.00%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::17            0      0.00%    100.00%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::18            0      0.00%    100.00%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::19            0      0.00%    100.00%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::20            0      0.00%    100.00%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::21            0      0.00%    100.00%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::22            0      0.00%    100.00%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::23            0      0.00%    100.00%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::24            0      0.00%    100.00%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::25            0      0.00%    100.00%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::26            0      0.00%    100.00%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::27            0      0.00%    100.00%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::28            0      0.00%    100.00%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::29            0      0.00%    100.00%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::30            0      0.00%    100.00%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::31            0      0.00%    100.00%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::32            0      0.00%    100.00%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::overflows            0      0.00%    100.00%
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::min_value            2                      
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::max_value           16                      
+system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::total           35                      
+system.cpu1.CUs1.ExecStage.num_cycles_with_no_issue         2740                      
+system.cpu1.CUs1.ExecStage.num_cycles_with_instr_issued          100                      
+system.cpu1.CUs1.ExecStage.num_cycles_with_instrtype_issue::ALU0           30                      
+system.cpu1.CUs1.ExecStage.num_cycles_with_instrtype_issue::ALU1           29                      
+system.cpu1.CUs1.ExecStage.num_cycles_with_instrtype_issue::ALU2           29                      
+system.cpu1.CUs1.ExecStage.num_cycles_with_instrtype_issue::ALU3           29                      
+system.cpu1.CUs1.ExecStage.num_cycles_with_instrtype_issue::GM           18                      
+system.cpu1.CUs1.ExecStage.num_cycles_with_instrtype_issue::LM            6                      
+system.cpu1.CUs1.ExecStage.num_cycles_with_instr_type_no_issue::ALU0          795                      
+system.cpu1.CUs1.ExecStage.num_cycles_with_instr_type_no_issue::ALU1          437                      
+system.cpu1.CUs1.ExecStage.num_cycles_with_instr_type_no_issue::ALU2          431                      
+system.cpu1.CUs1.ExecStage.num_cycles_with_instr_type_no_issue::ALU3          422                      
+system.cpu1.CUs1.ExecStage.num_cycles_with_instr_type_no_issue::GM          408                      
+system.cpu1.CUs1.ExecStage.num_cycles_with_instr_type_no_issue::LM           22                      
+system.cpu1.CUs1.ExecStage.spc::samples          2840                      
+system.cpu1.CUs1.ExecStage.spc::mean         0.049648                      
+system.cpu1.CUs1.ExecStage.spc::stdev        0.275831                      
+system.cpu1.CUs1.ExecStage.spc::underflows            0      0.00%      0.00%
+system.cpu1.CUs1.ExecStage.spc::0                2740     96.48%     96.48%
+system.cpu1.CUs1.ExecStage.spc::1                  59      2.08%     98.56%
+system.cpu1.CUs1.ExecStage.spc::2                  41      1.44%    100.00%
+system.cpu1.CUs1.ExecStage.spc::3                   0      0.00%    100.00%
+system.cpu1.CUs1.ExecStage.spc::4                   0      0.00%    100.00%
+system.cpu1.CUs1.ExecStage.spc::5                   0      0.00%    100.00%
+system.cpu1.CUs1.ExecStage.spc::6                   0      0.00%    100.00%
+system.cpu1.CUs1.ExecStage.spc::overflows            0      0.00%    100.00%
+system.cpu1.CUs1.ExecStage.spc::min_value            0                      
+system.cpu1.CUs1.ExecStage.spc::max_value            2                      
+system.cpu1.CUs1.ExecStage.spc::total            2840                      
+system.cpu1.CUs1.ExecStage.num_transitions_active_to_idle           91                      
+system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::samples           91                      
+system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::mean    30.010989                      
+system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::stdev   148.108031                      
+system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::underflows            0      0.00%      0.00%
+system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::0-4           76     83.52%     83.52%
+system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::5-9            8      8.79%     92.31%
+system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::10-14            0      0.00%     92.31%
+system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::15-19            0      0.00%     92.31%
+system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::20-24            0      0.00%     92.31%
+system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::25-29            1      1.10%     93.41%
+system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::30-34            0      0.00%     93.41%
+system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::35-39            0      0.00%     93.41%
+system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::40-44            0      0.00%     93.41%
+system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::45-49            0      0.00%     93.41%
+system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::50-54            0      0.00%     93.41%
+system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::55-59            0      0.00%     93.41%
+system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::60-64            0      0.00%     93.41%
+system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::65-69            0      0.00%     93.41%
+system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::70-74            0      0.00%     93.41%
+system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::75            0      0.00%     93.41%
+system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::overflows            6      6.59%    100.00%
+system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::min_value            1                      
+system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::max_value         1299                      
+system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::total           91                      
+system.cpu1.CUs1.GlobalMemPipeline.load_vrf_bank_conflict_cycles            0                      
+system.cpu1.CUs1.LocalMemPipeline.load_vrf_bank_conflict_cycles            0                      
+system.cpu1.CUs1.valu_insts                        68                      
+system.cpu1.CUs1.valu_insts_per_wf                 17                      
+system.cpu1.CUs1.salu_insts                         0                      
+system.cpu1.CUs1.salu_insts_per_wf                  0                      
+system.cpu1.CUs1.inst_cycles_valu                  68                      
+system.cpu1.CUs1.inst_cycles_salu                   0                      
+system.cpu1.CUs1.thread_cycles_valu              3071                      
+system.cpu1.CUs1.valu_utilization           70.565257                      
+system.cpu1.CUs1.lds_no_flat_insts                  6                      
+system.cpu1.CUs1.lds_no_flat_insts_per_wf     1.500000                      
+system.cpu1.CUs1.flat_vmem_insts                    0                      
+system.cpu1.CUs1.flat_vmem_insts_per_wf             0                      
+system.cpu1.CUs1.flat_lds_insts                     0                      
+system.cpu1.CUs1.flat_lds_insts_per_wf              0                      
+system.cpu1.CUs1.vector_mem_writes                  8                      
+system.cpu1.CUs1.vector_mem_writes_per_wf            2                      
+system.cpu1.CUs1.vector_mem_reads                  29                      
+system.cpu1.CUs1.vector_mem_reads_per_wf     7.250000                      
+system.cpu1.CUs1.scalar_mem_writes                  0                      
+system.cpu1.CUs1.scalar_mem_writes_per_wf            0                      
+system.cpu1.CUs1.scalar_mem_reads                   0                      
+system.cpu1.CUs1.scalar_mem_reads_per_wf            0                      
+system.cpu1.CUs1.tlb_requests                     769                      
+system.cpu1.CUs1.tlb_cycles              -454919630000                      
+system.cpu1.CUs1.avg_translation_latency -591572990.897269                      
+system.cpu1.CUs1.TLB_hits_distribution::page_table          769                      
+system.cpu1.CUs1.TLB_hits_distribution::L1_TLB            0                      
+system.cpu1.CUs1.TLB_hits_distribution::L2_TLB            0                      
+system.cpu1.CUs1.TLB_hits_distribution::L3_TLB            0                      
+system.cpu1.CUs1.lds_bank_access_cnt               53                      
+system.cpu1.CUs1.lds_bank_conflicts::samples            6                      
+system.cpu1.CUs1.lds_bank_conflicts::mean     7.833333                      
+system.cpu1.CUs1.lds_bank_conflicts::stdev     6.080022                      
+system.cpu1.CUs1.lds_bank_conflicts::underflows            0      0.00%      0.00%
+system.cpu1.CUs1.lds_bank_conflicts::0-1            2     33.33%     33.33%
+system.cpu1.CUs1.lds_bank_conflicts::2-3            0      0.00%     33.33%
+system.cpu1.CUs1.lds_bank_conflicts::4-5            0      0.00%     33.33%
+system.cpu1.CUs1.lds_bank_conflicts::6-7            0      0.00%     33.33%
+system.cpu1.CUs1.lds_bank_conflicts::8-9            0      0.00%     33.33%
+system.cpu1.CUs1.lds_bank_conflicts::10-11            1     16.67%     50.00%
+system.cpu1.CUs1.lds_bank_conflicts::12-13            3     50.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::14-15            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::16-17            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::18-19            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::20-21            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::22-23            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::24-25            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::26-27            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::28-29            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::30-31            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::32-33            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::34-35            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::36-37            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::38-39            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::40-41            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::42-43            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::44-45            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::46-47            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::48-49            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::50-51            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::52-53            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::54-55            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::56-57            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::58-59            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::60-61            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::62-63            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::64             0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::overflows            0      0.00%    100.00%
+system.cpu1.CUs1.lds_bank_conflicts::min_value            0                      
+system.cpu1.CUs1.lds_bank_conflicts::max_value           12                      
+system.cpu1.CUs1.lds_bank_conflicts::total            6                      
+system.cpu1.CUs1.page_divergence_dist::samples           17                      
+system.cpu1.CUs1.page_divergence_dist::mean            1                      
+system.cpu1.CUs1.page_divergence_dist::stdev            0                      
+system.cpu1.CUs1.page_divergence_dist::underflows            0      0.00%      0.00%
+system.cpu1.CUs1.page_divergence_dist::1-4           17    100.00%    100.00%
+system.cpu1.CUs1.page_divergence_dist::5-8            0      0.00%    100.00%
+system.cpu1.CUs1.page_divergence_dist::9-12            0      0.00%    100.00%
+system.cpu1.CUs1.page_divergence_dist::13-16            0      0.00%    100.00%
+system.cpu1.CUs1.page_divergence_dist::17-20            0      0.00%    100.00%
+system.cpu1.CUs1.page_divergence_dist::21-24            0      0.00%    100.00%
+system.cpu1.CUs1.page_divergence_dist::25-28            0      0.00%    100.00%
+system.cpu1.CUs1.page_divergence_dist::29-32            0      0.00%    100.00%
+system.cpu1.CUs1.page_divergence_dist::33-36            0      0.00%    100.00%
+system.cpu1.CUs1.page_divergence_dist::37-40            0      0.00%    100.00%
+system.cpu1.CUs1.page_divergence_dist::41-44            0      0.00%    100.00%
+system.cpu1.CUs1.page_divergence_dist::45-48            0      0.00%    100.00%
+system.cpu1.CUs1.page_divergence_dist::49-52            0      0.00%    100.00%
+system.cpu1.CUs1.page_divergence_dist::53-56            0      0.00%    100.00%
+system.cpu1.CUs1.page_divergence_dist::57-60            0      0.00%    100.00%
+system.cpu1.CUs1.page_divergence_dist::61-64            0      0.00%    100.00%
+system.cpu1.CUs1.page_divergence_dist::overflows            0      0.00%    100.00%
+system.cpu1.CUs1.page_divergence_dist::min_value            1                      
+system.cpu1.CUs1.page_divergence_dist::max_value            1                      
+system.cpu1.CUs1.page_divergence_dist::total           17                      
+system.cpu1.CUs1.global_mem_instr_cnt              17                      
+system.cpu1.CUs1.local_mem_instr_cnt                6                      
+system.cpu1.CUs1.wg_blocked_due_lds_alloc            0                      
+system.cpu1.CUs1.num_instr_executed               141                      
+system.cpu1.CUs1.inst_exec_rate::samples          141                      
+system.cpu1.CUs1.inst_exec_rate::mean       72.113475                      
+system.cpu1.CUs1.inst_exec_rate::stdev     228.065470                      
+system.cpu1.CUs1.inst_exec_rate::underflows            0      0.00%      0.00%
+system.cpu1.CUs1.inst_exec_rate::0-1                0      0.00%      0.00%
+system.cpu1.CUs1.inst_exec_rate::2-3               13      9.22%      9.22%
+system.cpu1.CUs1.inst_exec_rate::4-5               60     42.55%     51.77%
+system.cpu1.CUs1.inst_exec_rate::6-7               34     24.11%     75.89%
+system.cpu1.CUs1.inst_exec_rate::8-9                3      2.13%     78.01%
+system.cpu1.CUs1.inst_exec_rate::10                 1      0.71%     78.72%
+system.cpu1.CUs1.inst_exec_rate::overflows           30     21.28%    100.00%
+system.cpu1.CUs1.inst_exec_rate::min_value            2                      
+system.cpu1.CUs1.inst_exec_rate::max_value         1305                      
+system.cpu1.CUs1.inst_exec_rate::total            141                      
+system.cpu1.CUs1.num_vec_ops_executed            6762                      
+system.cpu1.CUs1.num_total_cycles                2840                      
+system.cpu1.CUs1.vpc                         2.380986                      
+system.cpu1.CUs1.ipc                         0.049648                      
+system.cpu1.CUs1.warp_execution_dist::samples          141                      
+system.cpu1.CUs1.warp_execution_dist::mean    47.957447                      
+system.cpu1.CUs1.warp_execution_dist::stdev    23.818022                      
+system.cpu1.CUs1.warp_execution_dist::underflows            0      0.00%      0.00%
+system.cpu1.CUs1.warp_execution_dist::1-4            5      3.55%      3.55%
+system.cpu1.CUs1.warp_execution_dist::5-8            0      0.00%      3.55%
+system.cpu1.CUs1.warp_execution_dist::9-12            9      6.38%      9.93%
+system.cpu1.CUs1.warp_execution_dist::13-16           27     19.15%     29.08%
+system.cpu1.CUs1.warp_execution_dist::17-20            0      0.00%     29.08%
+system.cpu1.CUs1.warp_execution_dist::21-24            0      0.00%     29.08%
+system.cpu1.CUs1.warp_execution_dist::25-28            0      0.00%     29.08%
+system.cpu1.CUs1.warp_execution_dist::29-32            0      0.00%     29.08%
+system.cpu1.CUs1.warp_execution_dist::33-36            0      0.00%     29.08%
+system.cpu1.CUs1.warp_execution_dist::37-40            0      0.00%     29.08%
+system.cpu1.CUs1.warp_execution_dist::41-44            0      0.00%     29.08%
+system.cpu1.CUs1.warp_execution_dist::45-48            0      0.00%     29.08%
+system.cpu1.CUs1.warp_execution_dist::49-52            8      5.67%     34.75%
+system.cpu1.CUs1.warp_execution_dist::53-56            0      0.00%     34.75%
+system.cpu1.CUs1.warp_execution_dist::57-60            0      0.00%     34.75%
+system.cpu1.CUs1.warp_execution_dist::61-64           92     65.25%    100.00%
+system.cpu1.CUs1.warp_execution_dist::overflows            0      0.00%    100.00%
+system.cpu1.CUs1.warp_execution_dist::min_value            1                      
+system.cpu1.CUs1.warp_execution_dist::max_value           64                      
+system.cpu1.CUs1.warp_execution_dist::total          141                      
+system.cpu1.CUs1.gmem_lanes_execution_dist::samples           18                      
+system.cpu1.CUs1.gmem_lanes_execution_dist::mean    37.722222                      
+system.cpu1.CUs1.gmem_lanes_execution_dist::stdev    27.174394                      
+system.cpu1.CUs1.gmem_lanes_execution_dist::underflows            0      0.00%      0.00%
+system.cpu1.CUs1.gmem_lanes_execution_dist::1-4            1      5.56%      5.56%
+system.cpu1.CUs1.gmem_lanes_execution_dist::5-8            0      0.00%      5.56%
+system.cpu1.CUs1.gmem_lanes_execution_dist::9-12            2     11.11%     16.67%
+system.cpu1.CUs1.gmem_lanes_execution_dist::13-16            6     33.33%     50.00%
+system.cpu1.CUs1.gmem_lanes_execution_dist::17-20            0      0.00%     50.00%
+system.cpu1.CUs1.gmem_lanes_execution_dist::21-24            0      0.00%     50.00%
+system.cpu1.CUs1.gmem_lanes_execution_dist::25-28            0      0.00%     50.00%
+system.cpu1.CUs1.gmem_lanes_execution_dist::29-32            0      0.00%     50.00%
+system.cpu1.CUs1.gmem_lanes_execution_dist::33-36            0      0.00%     50.00%
+system.cpu1.CUs1.gmem_lanes_execution_dist::37-40            0      0.00%     50.00%
+system.cpu1.CUs1.gmem_lanes_execution_dist::41-44            0      0.00%     50.00%
+system.cpu1.CUs1.gmem_lanes_execution_dist::45-48            0      0.00%     50.00%
+system.cpu1.CUs1.gmem_lanes_execution_dist::49-52            0      0.00%     50.00%
+system.cpu1.CUs1.gmem_lanes_execution_dist::53-56            0      0.00%     50.00%
+system.cpu1.CUs1.gmem_lanes_execution_dist::57-60            0      0.00%     50.00%
+system.cpu1.CUs1.gmem_lanes_execution_dist::61-64            9     50.00%    100.00%
+system.cpu1.CUs1.gmem_lanes_execution_dist::overflows            0      0.00%    100.00%
+system.cpu1.CUs1.gmem_lanes_execution_dist::min_value            1                      
+system.cpu1.CUs1.gmem_lanes_execution_dist::max_value           64                      
+system.cpu1.CUs1.gmem_lanes_execution_dist::total           18                      
+system.cpu1.CUs1.lmem_lanes_execution_dist::samples            6                      
+system.cpu1.CUs1.lmem_lanes_execution_dist::mean    19.333333                      
+system.cpu1.CUs1.lmem_lanes_execution_dist::stdev    22.384518                      
+system.cpu1.CUs1.lmem_lanes_execution_dist::underflows            0      0.00%      0.00%
+system.cpu1.CUs1.lmem_lanes_execution_dist::1-4            1     16.67%     16.67%
+system.cpu1.CUs1.lmem_lanes_execution_dist::5-8            0      0.00%     16.67%
+system.cpu1.CUs1.lmem_lanes_execution_dist::9-12            1     16.67%     33.33%
+system.cpu1.CUs1.lmem_lanes_execution_dist::13-16            3     50.00%     83.33%
+system.cpu1.CUs1.lmem_lanes_execution_dist::17-20            0      0.00%     83.33%
+system.cpu1.CUs1.lmem_lanes_execution_dist::21-24            0      0.00%     83.33%
+system.cpu1.CUs1.lmem_lanes_execution_dist::25-28            0      0.00%     83.33%
+system.cpu1.CUs1.lmem_lanes_execution_dist::29-32            0      0.00%     83.33%
+system.cpu1.CUs1.lmem_lanes_execution_dist::33-36            0      0.00%     83.33%
+system.cpu1.CUs1.lmem_lanes_execution_dist::37-40            0      0.00%     83.33%
+system.cpu1.CUs1.lmem_lanes_execution_dist::41-44            0      0.00%     83.33%
+system.cpu1.CUs1.lmem_lanes_execution_dist::45-48            0      0.00%     83.33%
+system.cpu1.CUs1.lmem_lanes_execution_dist::49-52            0      0.00%     83.33%
+system.cpu1.CUs1.lmem_lanes_execution_dist::53-56            0      0.00%     83.33%
+system.cpu1.CUs1.lmem_lanes_execution_dist::57-60            0      0.00%     83.33%
+system.cpu1.CUs1.lmem_lanes_execution_dist::61-64            1     16.67%    100.00%
+system.cpu1.CUs1.lmem_lanes_execution_dist::overflows            0      0.00%    100.00%
+system.cpu1.CUs1.lmem_lanes_execution_dist::min_value            1                      
+system.cpu1.CUs1.lmem_lanes_execution_dist::max_value           64                      
+system.cpu1.CUs1.lmem_lanes_execution_dist::total            6                      
+system.cpu1.CUs1.num_alu_insts_executed           118                      
+system.cpu1.CUs1.times_wg_blocked_due_vgpr_alloc            0                      
+system.cpu1.CUs1.num_CAS_ops                        0                      
+system.cpu1.CUs1.num_failed_CAS_ops                 0                      
+system.cpu1.CUs1.num_completed_wfs                  4                      
+system.cpu1.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.cpu1.CUs0.ldsBus.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.cpu1.CUs1.ldsBus.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.cpu2.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.cpu2.num_kernel_launched                     1                      
+system.dir_cntrl0.L3CacheMemory.demand_hits            0                      
+system.dir_cntrl0.L3CacheMemory.demand_misses            0                      
+system.dir_cntrl0.L3CacheMemory.demand_accesses            0                      
+system.dir_cntrl0.L3CacheMemory.num_data_array_writes         1549                      
+system.dir_cntrl0.L3CacheMemory.num_tag_array_reads         1549                      
+system.dir_cntrl0.L3CacheMemory.num_tag_array_writes         1549                      
+system.dir_cntrl0.probeToCore.avg_buf_msgs     0.069628                      
+system.dir_cntrl0.probeToCore.avg_stall_time 29997.797448                      
+system.dir_cntrl0.requestFromCores.avg_buf_msgs     0.001160                      
+system.dir_cntrl0.requestFromCores.avg_stall_time 17271.531260                      
+system.dir_cntrl0.responseFromCores.avg_buf_msgs     0.001160                      
+system.dir_cntrl0.responseFromCores.avg_stall_time 121679.841776                      
+system.dir_cntrl0.responseFromMemory.avg_buf_msgs     0.003110                      
+system.dir_cntrl0.responseFromMemory.avg_stall_time   999.889123                      
+system.dir_cntrl0.responseToCore.avg_buf_msgs     0.069628                      
+system.dir_cntrl0.responseToCore.avg_stall_time 29990.830190                      
+system.dir_cntrl0.triggerQueue.avg_buf_msgs     0.002321                      
+system.dir_cntrl0.triggerQueue.avg_stall_time   999.739290                      
+system.dir_cntrl0.unblockFromCores.avg_buf_msgs     0.001160                      
+system.dir_cntrl0.unblockFromCores.avg_stall_time 17249.343916                      
+system.dir_cntrl0.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.dispatcher_coalescer.clk_domain.voltage_domain.voltage            1                      
+system.dispatcher_coalescer.clk_domain.clock         1000                      
+system.dispatcher_coalescer.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.dispatcher_coalescer.uncoalesced_accesses            0                      
+system.dispatcher_coalescer.coalesced_accesses            0                      
+system.dispatcher_coalescer.queuing_cycles            0                      
+system.dispatcher_coalescer.local_queuing_cycles            0                      
+system.dispatcher_coalescer.local_latency          nan                      
+system.dispatcher_tlb.clk_domain.voltage_domain.voltage            1                      
+system.dispatcher_tlb.clk_domain.clock           1000                      
+system.dispatcher_tlb.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.dispatcher_tlb.local_TLB_accesses            0                      
+system.dispatcher_tlb.local_TLB_hits                0                      
+system.dispatcher_tlb.local_TLB_misses              0                      
+system.dispatcher_tlb.local_TLB_miss_rate          nan                      
+system.dispatcher_tlb.global_TLB_accesses            0                      
+system.dispatcher_tlb.global_TLB_hits               0                      
+system.dispatcher_tlb.global_TLB_misses             0                      
+system.dispatcher_tlb.global_TLB_miss_rate          nan                      
+system.dispatcher_tlb.access_cycles                 0                      
+system.dispatcher_tlb.page_table_cycles             0                      
+system.dispatcher_tlb.unique_pages                  0                      
+system.dispatcher_tlb.local_cycles                  0                      
+system.dispatcher_tlb.local_latency               nan                      
+system.dispatcher_tlb.avg_reuse_distance            0                      
+system.l1_coalescer0.clk_domain.voltage_domain.voltage            1                      
+system.l1_coalescer0.clk_domain.clock            1000                      
+system.l1_coalescer0.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.l1_coalescer0.uncoalesced_accesses          778                      
+system.l1_coalescer0.coalesced_accesses             0                      
+system.l1_coalescer0.queuing_cycles                 0                      
+system.l1_coalescer0.local_queuing_cycles            0                      
+system.l1_coalescer0.local_latency                  0                      
+system.l1_coalescer1.clk_domain.voltage_domain.voltage            1                      
+system.l1_coalescer1.clk_domain.clock            1000                      
+system.l1_coalescer1.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.l1_coalescer1.uncoalesced_accesses          769                      
+system.l1_coalescer1.coalesced_accesses             0                      
+system.l1_coalescer1.queuing_cycles                 0                      
+system.l1_coalescer1.local_queuing_cycles            0                      
+system.l1_coalescer1.local_latency                  0                      
+system.l1_tlb0.clk_domain.voltage_domain.voltage            1                      
+system.l1_tlb0.clk_domain.clock                  1000                      
+system.l1_tlb0.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.l1_tlb0.local_TLB_accesses                 778                      
+system.l1_tlb0.local_TLB_hits                     774                      
+system.l1_tlb0.local_TLB_misses                     4                      
+system.l1_tlb0.local_TLB_miss_rate           0.514139                      
+system.l1_tlb0.global_TLB_accesses                778                      
+system.l1_tlb0.global_TLB_hits                    774                      
+system.l1_tlb0.global_TLB_misses                    4                      
+system.l1_tlb0.global_TLB_miss_rate          0.514139                      
+system.l1_tlb0.access_cycles                        0                      
+system.l1_tlb0.page_table_cycles                    0                      
+system.l1_tlb0.unique_pages                         4                      
+system.l1_tlb0.local_cycles                         0                      
+system.l1_tlb0.local_latency                        0                      
+system.l1_tlb0.avg_reuse_distance                   0                      
+system.l1_tlb1.clk_domain.voltage_domain.voltage            1                      
+system.l1_tlb1.clk_domain.clock                  1000                      
+system.l1_tlb1.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.l1_tlb1.local_TLB_accesses                 769                      
+system.l1_tlb1.local_TLB_hits                     766                      
+system.l1_tlb1.local_TLB_misses                     3                      
+system.l1_tlb1.local_TLB_miss_rate           0.390117                      
+system.l1_tlb1.global_TLB_accesses                769                      
+system.l1_tlb1.global_TLB_hits                    766                      
+system.l1_tlb1.global_TLB_misses                    3                      
+system.l1_tlb1.global_TLB_miss_rate          0.390117                      
+system.l1_tlb1.access_cycles                        0                      
+system.l1_tlb1.page_table_cycles                    0                      
+system.l1_tlb1.unique_pages                         3                      
+system.l1_tlb1.local_cycles                         0                      
+system.l1_tlb1.local_latency                        0                      
+system.l1_tlb1.avg_reuse_distance                   0                      
+system.l2_coalescer.clk_domain.voltage_domain.voltage            1                      
+system.l2_coalescer.clk_domain.clock             1000                      
+system.l2_coalescer.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.l2_coalescer.uncoalesced_accesses            8                      
+system.l2_coalescer.coalesced_accesses              1                      
+system.l2_coalescer.queuing_cycles               8000                      
+system.l2_coalescer.local_queuing_cycles         1000                      
+system.l2_coalescer.local_latency                 125                      
+system.l2_tlb.clk_domain.voltage_domain.voltage            1                      
+system.l2_tlb.clk_domain.clock                   1000                      
+system.l2_tlb.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.l2_tlb.local_TLB_accesses                    8                      
+system.l2_tlb.local_TLB_hits                        3                      
+system.l2_tlb.local_TLB_misses                      5                      
+system.l2_tlb.local_TLB_miss_rate           62.500000                      
+system.l2_tlb.global_TLB_accesses                  15                      
+system.l2_tlb.global_TLB_hits                       3                      
+system.l2_tlb.global_TLB_misses                    12                      
+system.l2_tlb.global_TLB_miss_rate                 80                      
+system.l2_tlb.access_cycles                    552008                      
+system.l2_tlb.page_table_cycles                     0                      
+system.l2_tlb.unique_pages                          5                      
+system.l2_tlb.local_cycles                      69001                      
+system.l2_tlb.local_latency               8625.125000                      
+system.l2_tlb.avg_reuse_distance                    0                      
+system.l3_coalescer.clk_domain.voltage_domain.voltage            1                      
+system.l3_coalescer.clk_domain.clock             1000                      
+system.l3_coalescer.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.l3_coalescer.uncoalesced_accesses            5                      
+system.l3_coalescer.coalesced_accesses              1                      
+system.l3_coalescer.queuing_cycles               8000                      
+system.l3_coalescer.local_queuing_cycles         1000                      
+system.l3_coalescer.local_latency                 200                      
+system.l3_tlb.clk_domain.voltage_domain.voltage            1                      
+system.l3_tlb.clk_domain.clock                   1000                      
+system.l3_tlb.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.l3_tlb.local_TLB_accesses                    5                      
+system.l3_tlb.local_TLB_hits                        0                      
+system.l3_tlb.local_TLB_misses                      5                      
+system.l3_tlb.local_TLB_miss_rate                 100                      
+system.l3_tlb.global_TLB_accesses                  12                      
+system.l3_tlb.global_TLB_hits                       0                      
+system.l3_tlb.global_TLB_misses                    12                      
+system.l3_tlb.global_TLB_miss_rate                100                      
+system.l3_tlb.access_cycles                   1200000                      
+system.l3_tlb.page_table_cycles               6000000                      
+system.l3_tlb.unique_pages                          5                      
+system.l3_tlb.local_cycles                     150000                      
+system.l3_tlb.local_latency                     30000                      
+system.l3_tlb.avg_reuse_distance                    0                      
+system.piobus.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.piobus.trans_dist::WriteReq                 94                      
+system.piobus.trans_dist::WriteResp                94                      
+system.piobus.pkt_count_system.cp_cntrl0.sequencer.mem-master-port::system.cpu2.pio          188                      
+system.piobus.pkt_count::total                    188                      
+system.piobus.pkt_size_system.cp_cntrl0.sequencer.mem-master-port::system.cpu2.pio          748                      
+system.piobus.pkt_size::total                     748                      
+system.piobus.reqLayer0.occupancy              188000                      
+system.piobus.reqLayer0.utilization               0.0                      
+system.piobus.respLayer0.occupancy              94000                      
+system.piobus.respLayer0.utilization              0.0                      
+system.ruby.network.ext_links0.int_node.port_buffers00.avg_buf_msgs     0.001160                      
+system.ruby.network.ext_links0.int_node.port_buffers00.avg_stall_time 16771.557856                      
+system.ruby.network.ext_links0.int_node.port_buffers02.avg_buf_msgs     0.001160                      
+system.ruby.network.ext_links0.int_node.port_buffers02.avg_stall_time 121180.062406                      
+system.ruby.network.ext_links0.int_node.port_buffers04.avg_buf_msgs     0.001160                      
+system.ruby.network.ext_links0.int_node.port_buffers04.avg_stall_time 16749.523342                      
+system.ruby.network.ext_links0.int_node.port_buffers05.avg_buf_msgs     0.000010                      
+system.ruby.network.ext_links0.int_node.port_buffers05.avg_stall_time  3493.705161                      
+system.ruby.network.ext_links0.int_node.port_buffers07.avg_buf_msgs     0.001150                      
+system.ruby.network.ext_links0.int_node.port_buffers07.avg_stall_time 30490.654510                      
+system.ruby.network.ext_links0.int_node.port_buffers15.avg_buf_msgs     0.001150                      
+system.ruby.network.ext_links0.int_node.port_buffers15.avg_stall_time 30497.737889                      
+system.ruby.network.ext_links0.int_node.port_buffers17.avg_buf_msgs     0.000010                      
+system.ruby.network.ext_links0.int_node.port_buffers17.avg_stall_time  3490.277719                      
+system.ruby.network.ext_links0.int_node.pwrStateResidencyTicks::UNDEFINED    667407500                      
 system.ruby.network.ext_links0.int_node.percent_links_utilized     0.007895                      
 system.ruby.network.ext_links0.int_node.msg_count.Control::0         1549                      
 system.ruby.network.ext_links0.int_node.msg_count.Request_Control::0         1549                      
@@ -2784,17 +2785,17 @@ system.ruby.network.ext_links0.int_node.msg_bytes.Request_Control::0        1239
 system.ruby.network.ext_links0.int_node.msg_bytes.Response_Data::2       112392                      
 system.ruby.network.ext_links0.int_node.msg_bytes.Response_Control::2        12296                      
 system.ruby.network.ext_links0.int_node.msg_bytes.Unblock_Control::4        12392                      
-system.ruby.network.ext_links1.int_node.port_buffers00.avg_buf_msgs     0.000010                       # Average number of messages in buffer
-system.ruby.network.ext_links1.int_node.port_buffers00.avg_stall_time  3608.205673                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links1.int_node.port_buffers02.avg_buf_msgs     0.001150                       # Average number of messages in buffer
-system.ruby.network.ext_links1.int_node.port_buffers02.avg_stall_time 31490.300903                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links1.int_node.port_buffers03.avg_buf_msgs     0.001150                       # Average number of messages in buffer
-system.ruby.network.ext_links1.int_node.port_buffers03.avg_stall_time 15499.593577                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links1.int_node.port_buffers05.avg_buf_msgs     0.000010                       # Average number of messages in buffer
-system.ruby.network.ext_links1.int_node.port_buffers05.avg_stall_time  1775.094697                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links1.int_node.port_buffers07.avg_buf_msgs     0.001150                       # Average number of messages in buffer
-system.ruby.network.ext_links1.int_node.port_buffers07.avg_stall_time 15494.855841                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links1.int_node.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
+system.ruby.network.ext_links1.int_node.port_buffers00.avg_buf_msgs     0.000010                      
+system.ruby.network.ext_links1.int_node.port_buffers00.avg_stall_time  3608.205673                      
+system.ruby.network.ext_links1.int_node.port_buffers02.avg_buf_msgs     0.001150                      
+system.ruby.network.ext_links1.int_node.port_buffers02.avg_stall_time 31490.300903                      
+system.ruby.network.ext_links1.int_node.port_buffers03.avg_buf_msgs     0.001150                      
+system.ruby.network.ext_links1.int_node.port_buffers03.avg_stall_time 15499.593577                      
+system.ruby.network.ext_links1.int_node.port_buffers05.avg_buf_msgs     0.000010                      
+system.ruby.network.ext_links1.int_node.port_buffers05.avg_stall_time  1775.094697                      
+system.ruby.network.ext_links1.int_node.port_buffers07.avg_buf_msgs     0.001150                      
+system.ruby.network.ext_links1.int_node.port_buffers07.avg_stall_time 15494.855841                      
+system.ruby.network.ext_links1.int_node.pwrStateResidencyTicks::UNDEFINED    667407500                      
 system.ruby.network.ext_links1.int_node.percent_links_utilized     0.009908                      
 system.ruby.network.ext_links1.int_node.msg_count.Control::0           14                      
 system.ruby.network.ext_links1.int_node.msg_count.Request_Control::0         1535                      
@@ -2806,72 +2807,72 @@ system.ruby.network.ext_links1.int_node.msg_bytes.Request_Control::0        1228
 system.ruby.network.ext_links1.int_node.msg_bytes.Response_Data::2       110664                      
 system.ruby.network.ext_links1.int_node.msg_bytes.Response_Control::2           96                      
 system.ruby.network.ext_links1.int_node.msg_bytes.Unblock_Control::4        12280                      
-system.tcp_cntrl0.L1cache.demand_hits               0                       # Number of cache demand hits
-system.tcp_cntrl0.L1cache.demand_misses             0                       # Number of cache demand misses
-system.tcp_cntrl0.L1cache.demand_accesses            0                       # Number of cache demand accesses
-system.tcp_cntrl0.L1cache.num_data_array_reads            8                       # number of data array reads
-system.tcp_cntrl0.L1cache.num_data_array_writes           11                       # number of data array writes
-system.tcp_cntrl0.L1cache.num_tag_array_reads           26                       # number of tag array reads
-system.tcp_cntrl0.L1cache.num_tag_array_writes           18                       # number of tag array writes
-system.tcp_cntrl0.L1cache.num_data_array_stalls            6                       # number of stalls caused by data array
-system.tcp_cntrl0.coalescer.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.tcp_cntrl0.coalescer.gpu_tcp_ld_hits            2                       # loads that hit in the TCP
-system.tcp_cntrl0.coalescer.gpu_tcp_ld_transfers            0                       # TCP to TCP load transfers
-system.tcp_cntrl0.coalescer.gpu_tcc_ld_hits            0                       # loads that hit in the TCC
-system.tcp_cntrl0.coalescer.gpu_ld_misses            2                       # loads that miss in the GPU
-system.tcp_cntrl0.coalescer.gpu_tcp_st_hits            4                       # stores that hit in the TCP
-system.tcp_cntrl0.coalescer.gpu_tcp_st_transfers            0                       # TCP to TCP store transfers
-system.tcp_cntrl0.coalescer.gpu_tcc_st_hits            0                       # stores that hit in the TCC
-system.tcp_cntrl0.coalescer.gpu_st_misses            5                       # stores that miss in the GPU
-system.tcp_cntrl0.coalescer.cp_tcp_ld_hits            0                       # loads that hit in the TCP
-system.tcp_cntrl0.coalescer.cp_tcp_ld_transfers            0                       # TCP to TCP load transfers
-system.tcp_cntrl0.coalescer.cp_tcc_ld_hits            0                       # loads that hit in the TCC
-system.tcp_cntrl0.coalescer.cp_ld_misses            0                       # loads that miss in the GPU
-system.tcp_cntrl0.coalescer.cp_tcp_st_hits            0                       # stores that hit in the TCP
-system.tcp_cntrl0.coalescer.cp_tcp_st_transfers            0                       # TCP to TCP store transfers
-system.tcp_cntrl0.coalescer.cp_tcc_st_hits            0                       # stores that hit in the TCC
-system.tcp_cntrl0.coalescer.cp_st_misses            0                       # stores that miss in the GPU
-system.tcp_cntrl0.mandatoryQueue.avg_buf_msgs     0.000018                       # Average number of messages in buffer
-system.tcp_cntrl0.mandatoryQueue.avg_stall_time     0.500256                       # Average number of cycles messages are stalled in this MB
-system.tcp_cntrl0.probeToTCP.avg_buf_msgs     0.000006                       # Average number of messages in buffer
-system.tcp_cntrl0.probeToTCP.avg_stall_time   680.485319                       # Average number of cycles messages are stalled in this MB
-system.tcp_cntrl0.requestFromTCP.avg_buf_msgs     0.000430                       # Average number of messages in buffer
-system.tcp_cntrl0.requestFromTCP.avg_stall_time  4552.451142                       # Average number of cycles messages are stalled in this MB
-system.tcp_cntrl0.responseFromTCP.avg_buf_msgs     0.000479                       # Average number of messages in buffer
-system.tcp_cntrl0.responseFromTCP.avg_stall_time  4534.171455                       # Average number of cycles messages are stalled in this MB
-system.tcp_cntrl0.responseToTCP.avg_buf_msgs     0.000005                       # Average number of messages in buffer
-system.tcp_cntrl0.responseToTCP.avg_stall_time   226.969283                       # Average number of cycles messages are stalled in this MB
-system.tcp_cntrl0.sequencer.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.tcp_cntrl0.unblockFromCore.avg_buf_msgs     0.000420                       # Average number of messages in buffer
-system.tcp_cntrl0.unblockFromCore.avg_stall_time  4536.988325                       # Average number of cycles messages are stalled in this MB
-system.tcp_cntrl0.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.ruby.network.ext_links2.int_node.port_buffers01.avg_buf_msgs     0.000006                       # Average number of messages in buffer
-system.ruby.network.ext_links2.int_node.port_buffers01.avg_stall_time   623.782329                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links2.int_node.port_buffers03.avg_buf_msgs     0.000005                       # Average number of messages in buffer
-system.ruby.network.ext_links2.int_node.port_buffers03.avg_stall_time   170.228086                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links2.int_node.port_buffers05.avg_buf_msgs     0.000004                       # Average number of messages in buffer
-system.ruby.network.ext_links2.int_node.port_buffers05.avg_stall_time   555.902511                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links2.int_node.port_buffers07.avg_buf_msgs     0.000005                       # Average number of messages in buffer
-system.ruby.network.ext_links2.int_node.port_buffers07.avg_stall_time   170.023563                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links2.int_node.port_buffers12.avg_buf_msgs     0.001150                       # Average number of messages in buffer
-system.ruby.network.ext_links2.int_node.port_buffers12.avg_stall_time 31497.616524                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links2.int_node.port_buffers13.avg_buf_msgs     0.000013                       # Average number of messages in buffer
-system.ruby.network.ext_links2.int_node.port_buffers13.avg_stall_time  4687.243604                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links2.int_node.port_buffers14.avg_buf_msgs     0.000010                       # Average number of messages in buffer
-system.ruby.network.ext_links2.int_node.port_buffers14.avg_stall_time  3604.665857                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links2.int_node.port_buffers15.avg_buf_msgs     0.000010                       # Average number of messages in buffer
-system.ruby.network.ext_links2.int_node.port_buffers15.avg_stall_time  4590.818257                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links2.int_node.port_buffers17.avg_buf_msgs     0.000013                       # Average number of messages in buffer
-system.ruby.network.ext_links2.int_node.port_buffers17.avg_stall_time  4671.127513                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links2.int_node.port_buffers21.avg_buf_msgs     0.000002                       # Average number of messages in buffer
-system.ruby.network.ext_links2.int_node.port_buffers21.avg_stall_time   171.646260                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links2.int_node.port_buffers22.avg_buf_msgs     0.000010                       # Average number of messages in buffer
-system.ruby.network.ext_links2.int_node.port_buffers22.avg_stall_time 13808.776657                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links2.int_node.port_buffers24.avg_buf_msgs     0.001150                       # Average number of messages in buffer
-system.ruby.network.ext_links2.int_node.port_buffers24.avg_stall_time 120469.035784                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links2.int_node.port_buffers26.avg_buf_msgs     0.000010                       # Average number of messages in buffer
-system.ruby.network.ext_links2.int_node.port_buffers26.avg_stall_time 13752.445255                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.ext_links2.int_node.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
+system.tcp_cntrl0.L1cache.demand_hits               0                      
+system.tcp_cntrl0.L1cache.demand_misses             0                      
+system.tcp_cntrl0.L1cache.demand_accesses            0                      
+system.tcp_cntrl0.L1cache.num_data_array_reads            8                      
+system.tcp_cntrl0.L1cache.num_data_array_writes           11                      
+system.tcp_cntrl0.L1cache.num_tag_array_reads           26                      
+system.tcp_cntrl0.L1cache.num_tag_array_writes           18                      
+system.tcp_cntrl0.L1cache.num_data_array_stalls            6                      
+system.tcp_cntrl0.coalescer.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.tcp_cntrl0.coalescer.gpu_tcp_ld_hits            2                      
+system.tcp_cntrl0.coalescer.gpu_tcp_ld_transfers            0                      
+system.tcp_cntrl0.coalescer.gpu_tcc_ld_hits            0                      
+system.tcp_cntrl0.coalescer.gpu_ld_misses            2                      
+system.tcp_cntrl0.coalescer.gpu_tcp_st_hits            4                      
+system.tcp_cntrl0.coalescer.gpu_tcp_st_transfers            0                      
+system.tcp_cntrl0.coalescer.gpu_tcc_st_hits            0                      
+system.tcp_cntrl0.coalescer.gpu_st_misses            5                      
+system.tcp_cntrl0.coalescer.cp_tcp_ld_hits            0                      
+system.tcp_cntrl0.coalescer.cp_tcp_ld_transfers            0                      
+system.tcp_cntrl0.coalescer.cp_tcc_ld_hits            0                      
+system.tcp_cntrl0.coalescer.cp_ld_misses            0                      
+system.tcp_cntrl0.coalescer.cp_tcp_st_hits            0                      
+system.tcp_cntrl0.coalescer.cp_tcp_st_transfers            0                      
+system.tcp_cntrl0.coalescer.cp_tcc_st_hits            0                      
+system.tcp_cntrl0.coalescer.cp_st_misses            0                      
+system.tcp_cntrl0.mandatoryQueue.avg_buf_msgs     0.000018                      
+system.tcp_cntrl0.mandatoryQueue.avg_stall_time     0.500256                      
+system.tcp_cntrl0.probeToTCP.avg_buf_msgs     0.000006                      
+system.tcp_cntrl0.probeToTCP.avg_stall_time   680.485319                      
+system.tcp_cntrl0.requestFromTCP.avg_buf_msgs     0.000430                      
+system.tcp_cntrl0.requestFromTCP.avg_stall_time  4552.451142                      
+system.tcp_cntrl0.responseFromTCP.avg_buf_msgs     0.000479                      
+system.tcp_cntrl0.responseFromTCP.avg_stall_time  4534.171455                      
+system.tcp_cntrl0.responseToTCP.avg_buf_msgs     0.000005                      
+system.tcp_cntrl0.responseToTCP.avg_stall_time   226.969283                      
+system.tcp_cntrl0.sequencer.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.tcp_cntrl0.unblockFromCore.avg_buf_msgs     0.000420                      
+system.tcp_cntrl0.unblockFromCore.avg_stall_time  4536.988325                      
+system.tcp_cntrl0.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.ruby.network.ext_links2.int_node.port_buffers01.avg_buf_msgs     0.000006                      
+system.ruby.network.ext_links2.int_node.port_buffers01.avg_stall_time   623.782329                      
+system.ruby.network.ext_links2.int_node.port_buffers03.avg_buf_msgs     0.000005                      
+system.ruby.network.ext_links2.int_node.port_buffers03.avg_stall_time   170.228086                      
+system.ruby.network.ext_links2.int_node.port_buffers05.avg_buf_msgs     0.000004                      
+system.ruby.network.ext_links2.int_node.port_buffers05.avg_stall_time   555.902511                      
+system.ruby.network.ext_links2.int_node.port_buffers07.avg_buf_msgs     0.000005                      
+system.ruby.network.ext_links2.int_node.port_buffers07.avg_stall_time   170.023563                      
+system.ruby.network.ext_links2.int_node.port_buffers12.avg_buf_msgs     0.001150                      
+system.ruby.network.ext_links2.int_node.port_buffers12.avg_stall_time 31497.616524                      
+system.ruby.network.ext_links2.int_node.port_buffers13.avg_buf_msgs     0.000013                      
+system.ruby.network.ext_links2.int_node.port_buffers13.avg_stall_time  4687.243604                      
+system.ruby.network.ext_links2.int_node.port_buffers14.avg_buf_msgs     0.000010                      
+system.ruby.network.ext_links2.int_node.port_buffers14.avg_stall_time  3604.665857                      
+system.ruby.network.ext_links2.int_node.port_buffers15.avg_buf_msgs     0.000010                      
+system.ruby.network.ext_links2.int_node.port_buffers15.avg_stall_time  4590.818257                      
+system.ruby.network.ext_links2.int_node.port_buffers17.avg_buf_msgs     0.000013                      
+system.ruby.network.ext_links2.int_node.port_buffers17.avg_stall_time  4671.127513                      
+system.ruby.network.ext_links2.int_node.port_buffers21.avg_buf_msgs     0.000002                      
+system.ruby.network.ext_links2.int_node.port_buffers21.avg_stall_time   171.646260                      
+system.ruby.network.ext_links2.int_node.port_buffers22.avg_buf_msgs     0.000010                      
+system.ruby.network.ext_links2.int_node.port_buffers22.avg_stall_time 13808.776657                      
+system.ruby.network.ext_links2.int_node.port_buffers24.avg_buf_msgs     0.001150                      
+system.ruby.network.ext_links2.int_node.port_buffers24.avg_stall_time 120469.035784                      
+system.ruby.network.ext_links2.int_node.port_buffers26.avg_buf_msgs     0.000010                      
+system.ruby.network.ext_links2.int_node.port_buffers26.avg_stall_time 13752.445255                      
+system.ruby.network.ext_links2.int_node.pwrStateResidencyTicks::UNDEFINED    667407500                      
 system.ruby.network.ext_links2.int_node.percent_links_utilized     0.000708                      
 system.ruby.network.ext_links2.int_node.msg_count.Control::0         1535                      
 system.ruby.network.ext_links2.int_node.msg_count.Control::1           14                      
@@ -2891,118 +2892,118 @@ system.ruby.network.ext_links2.int_node.msg_bytes.Response_Data::3         2232
 system.ruby.network.ext_links2.int_node.msg_bytes.Response_Control::2        12200                      
 system.ruby.network.ext_links2.int_node.msg_bytes.Unblock_Control::4          112                      
 system.ruby.network.ext_links2.int_node.msg_bytes.Unblock_Control::5          136                      
-system.tcp_cntrl1.L1cache.demand_hits               0                       # Number of cache demand hits
-system.tcp_cntrl1.L1cache.demand_misses             0                       # Number of cache demand misses
-system.tcp_cntrl1.L1cache.demand_accesses            0                       # Number of cache demand accesses
-system.tcp_cntrl1.L1cache.num_data_array_reads            8                       # number of data array reads
-system.tcp_cntrl1.L1cache.num_data_array_writes           11                       # number of data array writes
-system.tcp_cntrl1.L1cache.num_tag_array_reads           25                       # number of tag array reads
-system.tcp_cntrl1.L1cache.num_tag_array_writes           18                       # number of tag array writes
-system.tcp_cntrl1.L1cache.num_tag_array_stalls            2                       # number of stalls caused by tag array
-system.tcp_cntrl1.L1cache.num_data_array_stalls            6                       # number of stalls caused by data array
-system.tcp_cntrl1.coalescer.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.tcp_cntrl1.coalescer.gpu_tcp_ld_hits            3                       # loads that hit in the TCP
-system.tcp_cntrl1.coalescer.gpu_tcp_ld_transfers            2                       # TCP to TCP load transfers
-system.tcp_cntrl1.coalescer.gpu_tcc_ld_hits            0                       # loads that hit in the TCC
-system.tcp_cntrl1.coalescer.gpu_ld_misses            0                       # loads that miss in the GPU
-system.tcp_cntrl1.coalescer.gpu_tcp_st_hits            4                       # stores that hit in the TCP
-system.tcp_cntrl1.coalescer.gpu_tcp_st_transfers            1                       # TCP to TCP store transfers
-system.tcp_cntrl1.coalescer.gpu_tcc_st_hits            0                       # stores that hit in the TCC
-system.tcp_cntrl1.coalescer.gpu_st_misses            4                       # stores that miss in the GPU
-system.tcp_cntrl1.coalescer.cp_tcp_ld_hits            0                       # loads that hit in the TCP
-system.tcp_cntrl1.coalescer.cp_tcp_ld_transfers            0                       # TCP to TCP load transfers
-system.tcp_cntrl1.coalescer.cp_tcc_ld_hits            0                       # loads that hit in the TCC
-system.tcp_cntrl1.coalescer.cp_ld_misses            0                       # loads that miss in the GPU
-system.tcp_cntrl1.coalescer.cp_tcp_st_hits            0                       # stores that hit in the TCP
-system.tcp_cntrl1.coalescer.cp_tcp_st_transfers            0                       # TCP to TCP store transfers
-system.tcp_cntrl1.coalescer.cp_tcc_st_hits            0                       # stores that hit in the TCC
-system.tcp_cntrl1.coalescer.cp_st_misses            0                       # stores that miss in the GPU
-system.tcp_cntrl1.mandatoryQueue.avg_buf_msgs     0.000024                       # Average number of messages in buffer
-system.tcp_cntrl1.mandatoryQueue.avg_stall_time     0.662049                       # Average number of cycles messages are stalled in this MB
-system.tcp_cntrl1.probeToTCP.avg_buf_msgs     0.000004                       # Average number of messages in buffer
-system.tcp_cntrl1.probeToTCP.avg_stall_time   606.434608                       # Average number of cycles messages are stalled in this MB
-system.tcp_cntrl1.requestFromTCP.avg_buf_msgs     0.000430                       # Average number of messages in buffer
-system.tcp_cntrl1.requestFromTCP.avg_stall_time  4551.971675                       # Average number of cycles messages are stalled in this MB
-system.tcp_cntrl1.responseFromTCP.avg_buf_msgs     0.000360                       # Average number of messages in buffer
-system.tcp_cntrl1.responseFromTCP.avg_stall_time  4040.500048                       # Average number of cycles messages are stalled in this MB
-system.tcp_cntrl1.responseToTCP.avg_buf_msgs     0.000005                       # Average number of messages in buffer
-system.tcp_cntrl1.responseToTCP.avg_stall_time   226.696586                       # Average number of cycles messages are stalled in this MB
-system.tcp_cntrl1.sequencer.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.tcp_cntrl1.unblockFromCore.avg_buf_msgs     0.000420                       # Average number of messages in buffer
-system.tcp_cntrl1.unblockFromCore.avg_stall_time  4531.534386                       # Average number of cycles messages are stalled in this MB
-system.tcp_cntrl1.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.sqc_cntrl0.L1cache.demand_hits               0                       # Number of cache demand hits
-system.sqc_cntrl0.L1cache.demand_misses             0                       # Number of cache demand misses
-system.sqc_cntrl0.L1cache.demand_accesses            0                       # Number of cache demand accesses
-system.sqc_cntrl0.L1cache.num_data_array_reads           70                       # number of data array reads
-system.sqc_cntrl0.L1cache.num_data_array_writes            3                       # number of data array writes
-system.sqc_cntrl0.L1cache.num_tag_array_reads           70                       # number of tag array reads
-system.sqc_cntrl0.L1cache.num_tag_array_writes            3                       # number of tag array writes
-system.sqc_cntrl0.L1cache.num_data_array_stalls           28                       # number of stalls caused by data array
-system.sqc_cntrl0.mandatoryQueue.avg_buf_msgs     0.000147                       # Average number of messages in buffer
-system.sqc_cntrl0.mandatoryQueue.avg_stall_time   115.508892                       # Average number of cycles messages are stalled in this MB
-system.sqc_cntrl0.requestFromSQC.avg_buf_msgs     0.000360                       # Average number of messages in buffer
-system.sqc_cntrl0.requestFromSQC.avg_stall_time  9182.216368                       # Average number of cycles messages are stalled in this MB
-system.sqc_cntrl0.responseToSQC.avg_buf_msgs     0.000002                       # Average number of messages in buffer
-system.sqc_cntrl0.responseToSQC.avg_stall_time   228.860182                       # Average number of cycles messages are stalled in this MB
-system.sqc_cntrl0.sequencer.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.sqc_cntrl0.sequencer.load_waiting_on_load           75                       # Number of times a load aliased with a pending load
-system.sqc_cntrl0.unblockFromCore.avg_buf_msgs     0.000360                       # Average number of messages in buffer
-system.sqc_cntrl0.unblockFromCore.avg_stall_time  9144.817927                       # Average number of cycles messages are stalled in this MB
-system.sqc_cntrl0.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.tcc_cntrl0.L2cache.demand_hits               0                       # Number of cache demand hits
-system.tcc_cntrl0.L2cache.demand_misses             0                       # Number of cache demand misses
-system.tcc_cntrl0.L2cache.demand_accesses            0                       # Number of cache demand accesses
-system.tcc_cntrl0.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.tccdir_cntrl0.directory.demand_hits            0                       # Number of cache demand hits
-system.tccdir_cntrl0.directory.demand_misses            0                       # Number of cache demand misses
-system.tccdir_cntrl0.directory.demand_accesses            0                       # Number of cache demand accesses
-system.tccdir_cntrl0.directory.num_tag_array_reads         1552                       # number of tag array reads
-system.tccdir_cntrl0.directory.num_tag_array_writes           25                       # number of tag array writes
-system.tccdir_cntrl0.probeFromNB.avg_buf_msgs     0.001150                       # Average number of messages in buffer
-system.tccdir_cntrl0.probeFromNB.avg_stall_time 31997.554717                       # Average number of cycles messages are stalled in this MB
-system.tccdir_cntrl0.probeToCore.avg_buf_msgs     0.000097                       # Average number of messages in buffer
-system.tccdir_cntrl0.probeToCore.avg_stall_time   567.078591                       # Average number of cycles messages are stalled in this MB
-system.tccdir_cntrl0.requestFromTCP.avg_buf_msgs     0.001122                       # Average number of messages in buffer
-system.tccdir_cntrl0.requestFromTCP.avg_stall_time 31695.077969                       # Average number of cycles messages are stalled in this MB
-system.tccdir_cntrl0.requestToNB.avg_buf_msgs     0.002517                       # Average number of messages in buffer
-system.tccdir_cntrl0.requestToNB.avg_stall_time 13751.568729                       # Average number of cycles messages are stalled in this MB
-system.tccdir_cntrl0.responseFromNB.avg_buf_msgs     0.000010                       # Average number of messages in buffer
-system.tccdir_cntrl0.responseFromNB.avg_stall_time  3661.858802                       # Average number of cycles messages are stalled in this MB
-system.tccdir_cntrl0.responseFromTCP.avg_buf_msgs     0.000010                       # Average number of messages in buffer
-system.tccdir_cntrl0.responseFromTCP.avg_stall_time  4647.464310                       # Average number of cycles messages are stalled in this MB
-system.tccdir_cntrl0.responseToCore.avg_buf_msgs     0.000025                       # Average number of messages in buffer
-system.tccdir_cntrl0.responseToCore.avg_stall_time   114.431589                       # Average number of cycles messages are stalled in this MB
-system.tccdir_cntrl0.responseToNB.avg_buf_msgs     0.275993                       # Average number of messages in buffer
-system.tccdir_cntrl0.responseToNB.avg_stall_time 119969.254166                       # Average number of cycles messages are stalled in this MB
-system.tccdir_cntrl0.triggerQueue.avg_buf_msgs     0.000019                       # Average number of messages in buffer
-system.tccdir_cntrl0.triggerQueue.avg_stall_time   113.351290                       # Average number of cycles messages are stalled in this MB
-system.tccdir_cntrl0.unblockFromTCP.avg_buf_msgs     0.000013                       # Average number of messages in buffer
-system.tccdir_cntrl0.unblockFromTCP.avg_stall_time  4728.251535                       # Average number of cycles messages are stalled in this MB
-system.tccdir_cntrl0.unblockToNB.avg_buf_msgs     0.002517                       # Average number of messages in buffer
-system.tccdir_cntrl0.unblockToNB.avg_stall_time 13695.471067                       # Average number of cycles messages are stalled in this MB
-system.tccdir_cntrl0.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.ruby.network.int_link_buffers00.avg_buf_msgs     0.000010                       # Average number of messages in buffer
-system.ruby.network.int_link_buffers00.avg_stall_time  3550.955792                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.int_link_buffers02.avg_buf_msgs     0.001150                       # Average number of messages in buffer
-system.ruby.network.int_link_buffers02.avg_stall_time 30990.478081                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.int_link_buffers10.avg_buf_msgs     0.001150                       # Average number of messages in buffer
-system.ruby.network.int_link_buffers10.avg_stall_time 30997.677581                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.int_link_buffers12.avg_buf_msgs     0.000010                       # Average number of messages in buffer
-system.ruby.network.int_link_buffers12.avg_stall_time  3547.472163                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.int_link_buffers20.avg_buf_msgs     0.001150                       # Average number of messages in buffer
-system.ruby.network.int_link_buffers20.avg_stall_time 15999.568480                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.int_link_buffers22.avg_buf_msgs     0.000010                       # Average number of messages in buffer
-system.ruby.network.int_link_buffers22.avg_stall_time  1832.343829                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.int_link_buffers24.avg_buf_msgs     0.001150                       # Average number of messages in buffer
-system.ruby.network.int_link_buffers24.avg_stall_time 15994.677914                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.int_link_buffers30.avg_buf_msgs     0.000010                       # Average number of messages in buffer
-system.ruby.network.int_link_buffers30.avg_stall_time 13865.983836                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.int_link_buffers32.avg_buf_msgs     0.001150                       # Average number of messages in buffer
-system.ruby.network.int_link_buffers32.avg_stall_time 120968.816653                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.int_link_buffers34.avg_buf_msgs     0.000010                       # Average number of messages in buffer
-system.ruby.network.int_link_buffers34.avg_stall_time 13809.418694                       # Average number of cycles messages are stalled in this MB
-system.ruby.network.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
+system.tcp_cntrl1.L1cache.demand_hits               0                      
+system.tcp_cntrl1.L1cache.demand_misses             0                      
+system.tcp_cntrl1.L1cache.demand_accesses            0                      
+system.tcp_cntrl1.L1cache.num_data_array_reads            8                      
+system.tcp_cntrl1.L1cache.num_data_array_writes           11                      
+system.tcp_cntrl1.L1cache.num_tag_array_reads           25                      
+system.tcp_cntrl1.L1cache.num_tag_array_writes           18                      
+system.tcp_cntrl1.L1cache.num_tag_array_stalls            2                      
+system.tcp_cntrl1.L1cache.num_data_array_stalls            6                      
+system.tcp_cntrl1.coalescer.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.tcp_cntrl1.coalescer.gpu_tcp_ld_hits            3                      
+system.tcp_cntrl1.coalescer.gpu_tcp_ld_transfers            2                      
+system.tcp_cntrl1.coalescer.gpu_tcc_ld_hits            0                      
+system.tcp_cntrl1.coalescer.gpu_ld_misses            0                      
+system.tcp_cntrl1.coalescer.gpu_tcp_st_hits            4                      
+system.tcp_cntrl1.coalescer.gpu_tcp_st_transfers            1                      
+system.tcp_cntrl1.coalescer.gpu_tcc_st_hits            0                      
+system.tcp_cntrl1.coalescer.gpu_st_misses            4                      
+system.tcp_cntrl1.coalescer.cp_tcp_ld_hits            0                      
+system.tcp_cntrl1.coalescer.cp_tcp_ld_transfers            0                      
+system.tcp_cntrl1.coalescer.cp_tcc_ld_hits            0                      
+system.tcp_cntrl1.coalescer.cp_ld_misses            0                      
+system.tcp_cntrl1.coalescer.cp_tcp_st_hits            0                      
+system.tcp_cntrl1.coalescer.cp_tcp_st_transfers            0                      
+system.tcp_cntrl1.coalescer.cp_tcc_st_hits            0                      
+system.tcp_cntrl1.coalescer.cp_st_misses            0                      
+system.tcp_cntrl1.mandatoryQueue.avg_buf_msgs     0.000024                      
+system.tcp_cntrl1.mandatoryQueue.avg_stall_time     0.662049                      
+system.tcp_cntrl1.probeToTCP.avg_buf_msgs     0.000004                      
+system.tcp_cntrl1.probeToTCP.avg_stall_time   606.434608                      
+system.tcp_cntrl1.requestFromTCP.avg_buf_msgs     0.000430                      
+system.tcp_cntrl1.requestFromTCP.avg_stall_time  4551.971675                      
+system.tcp_cntrl1.responseFromTCP.avg_buf_msgs     0.000360                      
+system.tcp_cntrl1.responseFromTCP.avg_stall_time  4040.500048                      
+system.tcp_cntrl1.responseToTCP.avg_buf_msgs     0.000005                      
+system.tcp_cntrl1.responseToTCP.avg_stall_time   226.696586                      
+system.tcp_cntrl1.sequencer.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.tcp_cntrl1.unblockFromCore.avg_buf_msgs     0.000420                      
+system.tcp_cntrl1.unblockFromCore.avg_stall_time  4531.534386                      
+system.tcp_cntrl1.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.sqc_cntrl0.L1cache.demand_hits               0                      
+system.sqc_cntrl0.L1cache.demand_misses             0                      
+system.sqc_cntrl0.L1cache.demand_accesses            0                      
+system.sqc_cntrl0.L1cache.num_data_array_reads           70                      
+system.sqc_cntrl0.L1cache.num_data_array_writes            3                      
+system.sqc_cntrl0.L1cache.num_tag_array_reads           70                      
+system.sqc_cntrl0.L1cache.num_tag_array_writes            3                      
+system.sqc_cntrl0.L1cache.num_data_array_stalls           28                      
+system.sqc_cntrl0.mandatoryQueue.avg_buf_msgs     0.000147                      
+system.sqc_cntrl0.mandatoryQueue.avg_stall_time   115.508892                      
+system.sqc_cntrl0.requestFromSQC.avg_buf_msgs     0.000360                      
+system.sqc_cntrl0.requestFromSQC.avg_stall_time  9182.216368                      
+system.sqc_cntrl0.responseToSQC.avg_buf_msgs     0.000002                      
+system.sqc_cntrl0.responseToSQC.avg_stall_time   228.860182                      
+system.sqc_cntrl0.sequencer.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.sqc_cntrl0.sequencer.load_waiting_on_load           75                      
+system.sqc_cntrl0.unblockFromCore.avg_buf_msgs     0.000360                      
+system.sqc_cntrl0.unblockFromCore.avg_stall_time  9144.817927                      
+system.sqc_cntrl0.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.tcc_cntrl0.L2cache.demand_hits               0                      
+system.tcc_cntrl0.L2cache.demand_misses             0                      
+system.tcc_cntrl0.L2cache.demand_accesses            0                      
+system.tcc_cntrl0.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.tccdir_cntrl0.directory.demand_hits            0                      
+system.tccdir_cntrl0.directory.demand_misses            0                      
+system.tccdir_cntrl0.directory.demand_accesses            0                      
+system.tccdir_cntrl0.directory.num_tag_array_reads         1552                      
+system.tccdir_cntrl0.directory.num_tag_array_writes           25                      
+system.tccdir_cntrl0.probeFromNB.avg_buf_msgs     0.001150                      
+system.tccdir_cntrl0.probeFromNB.avg_stall_time 31997.554717                      
+system.tccdir_cntrl0.probeToCore.avg_buf_msgs     0.000097                      
+system.tccdir_cntrl0.probeToCore.avg_stall_time   567.078591                      
+system.tccdir_cntrl0.requestFromTCP.avg_buf_msgs     0.001122                      
+system.tccdir_cntrl0.requestFromTCP.avg_stall_time 31695.077969                      
+system.tccdir_cntrl0.requestToNB.avg_buf_msgs     0.002517                      
+system.tccdir_cntrl0.requestToNB.avg_stall_time 13751.568729                      
+system.tccdir_cntrl0.responseFromNB.avg_buf_msgs     0.000010                      
+system.tccdir_cntrl0.responseFromNB.avg_stall_time  3661.858802                      
+system.tccdir_cntrl0.responseFromTCP.avg_buf_msgs     0.000010                      
+system.tccdir_cntrl0.responseFromTCP.avg_stall_time  4647.464310                      
+system.tccdir_cntrl0.responseToCore.avg_buf_msgs     0.000025                      
+system.tccdir_cntrl0.responseToCore.avg_stall_time   114.431589                      
+system.tccdir_cntrl0.responseToNB.avg_buf_msgs     0.275993                      
+system.tccdir_cntrl0.responseToNB.avg_stall_time 119969.254166                      
+system.tccdir_cntrl0.triggerQueue.avg_buf_msgs     0.000019                      
+system.tccdir_cntrl0.triggerQueue.avg_stall_time   113.351290                      
+system.tccdir_cntrl0.unblockFromTCP.avg_buf_msgs     0.000013                      
+system.tccdir_cntrl0.unblockFromTCP.avg_stall_time  4728.251535                      
+system.tccdir_cntrl0.unblockToNB.avg_buf_msgs     0.002517                      
+system.tccdir_cntrl0.unblockToNB.avg_stall_time 13695.471067                      
+system.tccdir_cntrl0.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.ruby.network.int_link_buffers00.avg_buf_msgs     0.000010                      
+system.ruby.network.int_link_buffers00.avg_stall_time  3550.955792                      
+system.ruby.network.int_link_buffers02.avg_buf_msgs     0.001150                      
+system.ruby.network.int_link_buffers02.avg_stall_time 30990.478081                      
+system.ruby.network.int_link_buffers10.avg_buf_msgs     0.001150                      
+system.ruby.network.int_link_buffers10.avg_stall_time 30997.677581                      
+system.ruby.network.int_link_buffers12.avg_buf_msgs     0.000010                      
+system.ruby.network.int_link_buffers12.avg_stall_time  3547.472163                      
+system.ruby.network.int_link_buffers20.avg_buf_msgs     0.001150                      
+system.ruby.network.int_link_buffers20.avg_stall_time 15999.568480                      
+system.ruby.network.int_link_buffers22.avg_buf_msgs     0.000010                      
+system.ruby.network.int_link_buffers22.avg_stall_time  1832.343829                      
+system.ruby.network.int_link_buffers24.avg_buf_msgs     0.001150                      
+system.ruby.network.int_link_buffers24.avg_stall_time 15994.677914                      
+system.ruby.network.int_link_buffers30.avg_buf_msgs     0.000010                      
+system.ruby.network.int_link_buffers30.avg_stall_time 13865.983836                      
+system.ruby.network.int_link_buffers32.avg_buf_msgs     0.001150                      
+system.ruby.network.int_link_buffers32.avg_stall_time 120968.816653                      
+system.ruby.network.int_link_buffers34.avg_buf_msgs     0.000010                      
+system.ruby.network.int_link_buffers34.avg_stall_time 13809.418694                      
+system.ruby.network.pwrStateResidencyTicks::UNDEFINED    667407500                      
 system.ruby.network.msg_count.Control            3112                      
 system.ruby.network.msg_count.Request_Control         3115                      
 system.ruby.network.msg_count.Response_Data         3153                      
@@ -3013,32 +3014,32 @@ system.ruby.network.msg_byte.Request_Control        24920
 system.ruby.network.msg_byte.Response_Data       227016                      
 system.ruby.network.msg_byte.Response_Control        24592                      
 system.ruby.network.msg_byte.Unblock_Control        24920                      
-system.sqc_coalescer.clk_domain.voltage_domain.voltage            1                       # Voltage in Volts
-system.sqc_coalescer.clk_domain.clock            1000                       # Clock period in ticks
-system.sqc_coalescer.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.sqc_coalescer.uncoalesced_accesses           70                       # Number of uncoalesced TLB accesses
-system.sqc_coalescer.coalesced_accesses            50                       # Number of coalesced TLB accesses
-system.sqc_coalescer.queuing_cycles            100000                       # Number of cycles spent in queue
-system.sqc_coalescer.local_queuing_cycles       100000                       # Number of cycles spent in queue for all incoming reqs
-system.sqc_coalescer.local_latency        1428.571429                       # Avg. latency over all incoming pkts
-system.sqc_tlb.clk_domain.voltage_domain.voltage            1                       # Voltage in Volts
-system.sqc_tlb.clk_domain.clock                  1000                       # Clock period in ticks
-system.sqc_tlb.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
-system.sqc_tlb.local_TLB_accesses                  50                       # Number of TLB accesses
-system.sqc_tlb.local_TLB_hits                      49                       # Number of TLB hits
-system.sqc_tlb.local_TLB_misses                     1                       # Number of TLB misses
-system.sqc_tlb.local_TLB_miss_rate                  2                       # TLB miss rate
-system.sqc_tlb.global_TLB_accesses                 70                       # Number of TLB accesses
-system.sqc_tlb.global_TLB_hits                     62                       # Number of TLB hits
-system.sqc_tlb.global_TLB_misses                    8                       # Number of TLB misses
-system.sqc_tlb.global_TLB_miss_rate         11.428571                       # TLB miss rate
-system.sqc_tlb.access_cycles                    70008                       # Cycles spent accessing this TLB level
-system.sqc_tlb.page_table_cycles                    0                       # Cycles spent accessing the page table
-system.sqc_tlb.unique_pages                         1                       # Number of unique pages touched
-system.sqc_tlb.local_cycles                     50001                       # Number of cycles spent in queue for all incoming reqs
-system.sqc_tlb.local_latency              1000.020000                       # Avg. latency over incoming coalesced reqs
-system.sqc_tlb.avg_reuse_distance                   0                       # avg. reuse distance over all pages (in ticks)
-system.sys_port_proxy.pwrStateResidencyTicks::UNDEFINED    667407500                       # Cumulative time (in ticks) in various power states
+system.sqc_coalescer.clk_domain.voltage_domain.voltage            1                      
+system.sqc_coalescer.clk_domain.clock            1000                      
+system.sqc_coalescer.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.sqc_coalescer.uncoalesced_accesses           70                      
+system.sqc_coalescer.coalesced_accesses            50                      
+system.sqc_coalescer.queuing_cycles            100000                      
+system.sqc_coalescer.local_queuing_cycles       100000                      
+system.sqc_coalescer.local_latency        1428.571429                      
+system.sqc_tlb.clk_domain.voltage_domain.voltage            1                      
+system.sqc_tlb.clk_domain.clock                  1000                      
+system.sqc_tlb.pwrStateResidencyTicks::UNDEFINED    667407500                      
+system.sqc_tlb.local_TLB_accesses                  50                      
+system.sqc_tlb.local_TLB_hits                      49                      
+system.sqc_tlb.local_TLB_misses                     1                      
+system.sqc_tlb.local_TLB_miss_rate                  2                      
+system.sqc_tlb.global_TLB_accesses                 70                      
+system.sqc_tlb.global_TLB_hits                     62                      
+system.sqc_tlb.global_TLB_misses                    8                      
+system.sqc_tlb.global_TLB_miss_rate         11.428571                      
+system.sqc_tlb.access_cycles                    70008                      
+system.sqc_tlb.page_table_cycles                    0                      
+system.sqc_tlb.unique_pages                         1                      
+system.sqc_tlb.local_cycles                     50001                      
+system.sqc_tlb.local_latency              1000.020000                      
+system.sqc_tlb.avg_reuse_distance                   0                      
+system.sys_port_proxy.pwrStateResidencyTicks::UNDEFINED    667407500                      
 system.ruby.network.ext_links0.int_node.throttle0.link_utilization     0.005552                      
 system.ruby.network.ext_links0.int_node.throttle0.msg_count.Request_Control::0         1549                      
 system.ruby.network.ext_links0.int_node.throttle0.msg_count.Response_Data::2           12