X86: Update stats for the improved branch detection/prediction.
authorGabe Black <gblack@eecs.umich.edu>
Mon, 14 Feb 2011 01:46:04 +0000 (17:46 -0800)
committerGabe Black <gblack@eecs.umich.edu>
Mon, 14 Feb 2011 01:46:04 +0000 (17:46 -0800)
13 files changed:
tests/long/00.gzip/ref/x86/linux/o3-timing/config.ini
tests/long/00.gzip/ref/x86/linux/o3-timing/simout
tests/long/00.gzip/ref/x86/linux/o3-timing/stats.txt
tests/long/10.mcf/ref/x86/linux/o3-timing/config.ini
tests/long/10.mcf/ref/x86/linux/o3-timing/simout
tests/long/10.mcf/ref/x86/linux/o3-timing/stats.txt
tests/long/20.parser/ref/x86/linux/o3-timing/simout
tests/long/20.parser/ref/x86/linux/o3-timing/stats.txt
tests/long/70.twolf/ref/x86/linux/o3-timing/config.ini
tests/long/70.twolf/ref/x86/linux/o3-timing/simout
tests/long/70.twolf/ref/x86/linux/o3-timing/stats.txt
tests/quick/00.hello/ref/x86/linux/o3-timing/simout
tests/quick/00.hello/ref/x86/linux/o3-timing/stats.txt

index 503c61f1c7445bbb3664f2365c7539c514c90c53..9a2e60122c7d55b0cfc9d666f81a734518e6f02e 100644 (file)
@@ -488,7 +488,7 @@ type=ExeTracer
 [system.cpu.workload]
 type=LiveProcess
 cmd=gzip input.log 1
-cwd=build/X86_SE/tests/fast/long/00.gzip/x86/linux/o3-timing
+cwd=build/X86_SE/tests/opt/long/00.gzip/x86/linux/o3-timing
 egid=100
 env=
 errout=cerr
index 5ac6b64fdb82f323a6964061a4628da4e6c19b70..d3a2b5cda1c8889c61e6085cfa70533012b1de3b 100755 (executable)
@@ -5,11 +5,11 @@ The Regents of The University of Michigan
 All Rights Reserved
 
 
-M5 compiled Feb  8 2011 00:58:32
-M5 revision 705a4d351a43 7939 default qtip resforflagsstats.patch tip
-M5 started Feb  8 2011 00:58:34
+M5 compiled Feb 12 2011 02:22:23
+M5 revision 5e76f9de6972 7961 default qtip tip x86branchdetectstats.patch
+M5 started Feb 12 2011 02:22:27
 M5 executing on burrito
-command line: build/X86_SE/m5.fast -d build/X86_SE/tests/fast/long/00.gzip/x86/linux/o3-timing -re tests/run.py build/X86_SE/tests/fast/long/00.gzip/x86/linux/o3-timing
+command line: build/X86_SE/m5.opt -d build/X86_SE/tests/opt/long/00.gzip/x86/linux/o3-timing -re tests/run.py build/X86_SE/tests/opt/long/00.gzip/x86/linux/o3-timing
 Global frequency set at 1000000000000 ticks per second
 info: Entering event queue @ 0.  Starting simulation...
 spec_init
@@ -1067,4 +1067,4 @@ Uncompressing Data
 Uncompressed data 1048576 bytes in length
 Uncompressed data compared correctly
 Tested 1MB buffer: OK!
-Exiting @ tick 758990697000 because target called exit()
+Exiting @ tick 766217705000 because target called exit()
index 7fa355b9d04c8c6b59446667eea74be21e8b0274..cc548bebc81c5678391a38af4d5a71984e3ea3f8 100644 (file)
@@ -1,41 +1,41 @@
 
 ---------- Begin Simulation Statistics ----------
-host_inst_rate                                 240879                       # Simulator instruction rate (inst/s)
-host_mem_usage                                 232888                       # Number of bytes of host memory used
-host_seconds                                  6731.58                       # Real time elapsed on the host
-host_tick_rate                              112750685                       # Simulator tick rate (ticks/s)
+host_inst_rate                                 123498                       # Simulator instruction rate (inst/s)
+host_mem_usage                                 236748                       # Number of bytes of host memory used
+host_seconds                                 13129.74                       # Real time elapsed on the host
+host_tick_rate                               58357436                       # Simulator tick rate (ticks/s)
 sim_freq                                 1000000000000                       # Frequency of simulated ticks
 sim_insts                                  1621493982                       # Number of instructions simulated
-sim_seconds                                  0.758991                       # Number of seconds simulated
-sim_ticks                                758990697000                       # Number of ticks simulated
+sim_seconds                                  0.766218                       # Number of seconds simulated
+sim_ticks                                766217705000                       # Number of ticks simulated
 system.cpu.BPredUnit.BTBCorrect                     0                       # Number of correct BTB predictions (this stat may not work properly.
-system.cpu.BPredUnit.BTBHits                123829137                       # Number of BTB hits
-system.cpu.BPredUnit.BTBLookups             124444739                       # Number of BTB lookups
+system.cpu.BPredUnit.BTBHits                169776992                       # Number of BTB hits
+system.cpu.BPredUnit.BTBLookups             171183773                       # Number of BTB lookups
 system.cpu.BPredUnit.RASInCorrect                   0                       # Number of incorrect RAS predictions.
-system.cpu.BPredUnit.condIncorrect            5933451                       # Number of conditional branches incorrect
-system.cpu.BPredUnit.condPredicted          124445048                       # Number of conditional branches predicted
-system.cpu.BPredUnit.lookups                124445048                       # Number of BP lookups
+system.cpu.BPredUnit.condIncorrect            8003535                       # Number of conditional branches incorrect
+system.cpu.BPredUnit.condPredicted          180455810                       # Number of conditional branches predicted
+system.cpu.BPredUnit.lookups                180455810                       # Number of BP lookups
 system.cpu.BPredUnit.usedRAS                        0                       # Number of times the RAS was used to get a target.
 system.cpu.commit.COM:branches              107161579                       # Number of branches committed
-system.cpu.commit.COM:bw_lim_events           4428744                       # number cycles where commit BW limit reached
+system.cpu.commit.COM:bw_lim_events           7534042                       # number cycles where commit BW limit reached
 system.cpu.commit.COM:bw_limited                    0                       # number of insts not committed due to BW limits
-system.cpu.commit.COM:committed_per_cycle::samples   1488500908                       # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::mean     1.089347                       # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::stdev     1.266465                       # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::samples   1432274296                       # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::mean     1.132111                       # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::stdev     1.344268                       # Number of insts commited each cycle
 system.cpu.commit.COM:committed_per_cycle::underflows            0      0.00%      0.00% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::0    544771983     36.60%     36.60% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::1    603082048     40.52%     77.11% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::2    142955782      9.60%     86.72% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::3    121627881      8.17%     94.89% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::4     42142525      2.83%     97.72% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::5     19097450      1.28%     99.00% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::6      4632040      0.31%     99.32% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::7      5762455      0.39%     99.70% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::8      4428744      0.30%    100.00% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::0    536173455     37.44%     37.44% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::1    547306108     38.21%     75.65% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::2    130197340      9.09%     84.74% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::3    136647601      9.54%     94.28% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::4     42821104      2.99%     97.27% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::5     22915800      1.60%     98.87% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::6      3037283      0.21%     99.08% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::7      5641563      0.39%     99.47% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::8      7534042      0.53%    100.00% # Number of insts commited each cycle
 system.cpu.commit.COM:committed_per_cycle::overflows            0      0.00%    100.00% # Number of insts commited each cycle
 system.cpu.commit.COM:committed_per_cycle::min_value            0                       # Number of insts commited each cycle
 system.cpu.commit.COM:committed_per_cycle::max_value            8                       # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::total   1488500908                       # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::total   1432274296                       # Number of insts commited each cycle
 system.cpu.commit.COM:count                1621493982                       # Number of instructions committed
 system.cpu.commit.COM:fp_insts                      0                       # Number of committed floating point instructions.
 system.cpu.commit.COM:function_calls                0                       # Number of function calls committed.
@@ -44,422 +44,422 @@ system.cpu.commit.COM:loads                 419042125                       # Nu
 system.cpu.commit.COM:membars                       0                       # Number of memory barriers committed
 system.cpu.commit.COM:refs                  607228182                       # Number of memory references committed
 system.cpu.commit.COM:swp_count                     0                       # Number of s/w prefetches committed
-system.cpu.commit.branchMispredicts           5933482                       # The number of times a branch was mispredicted
+system.cpu.commit.branchMispredicts           8003567                       # The number of times a branch was mispredicted
 system.cpu.commit.commitCommittedInsts     1621493982                       # The number of committed instructions
 system.cpu.commit.commitNonSpecStalls              50                       # The number of times commit has been forced to stall to communicate backwards
-system.cpu.commit.commitSquashedInsts       174503493                       # The number of squashed insts skipped by commit
+system.cpu.commit.commitSquashedInsts       729601482                       # The number of squashed insts skipped by commit
 system.cpu.committedInsts                  1621493982                       # Number of Instructions Simulated
 system.cpu.committedInsts_total            1621493982                       # Number of Instructions Simulated
-system.cpu.cpi                               0.936162                       # CPI: Cycles Per Instruction
-system.cpu.cpi_total                         0.936162                       # CPI: Total CPI of All Threads
-system.cpu.dcache.ReadReq_accesses          328666076                       # number of ReadReq accesses(hits+misses)
-system.cpu.dcache.ReadReq_avg_miss_latency 10263.411891                       # average ReadReq miss latency
-system.cpu.dcache.ReadReq_avg_mshr_miss_latency  7269.320090                       # average ReadReq mshr miss latency
-system.cpu.dcache.ReadReq_hits              328458033                       # number of ReadReq hits
-system.cpu.dcache.ReadReq_miss_latency     2135231000                       # number of ReadReq miss cycles
-system.cpu.dcache.ReadReq_miss_rate          0.000633                       # miss rate for ReadReq accesses
-system.cpu.dcache.ReadReq_misses               208043                       # number of ReadReq misses
-system.cpu.dcache.ReadReq_mshr_hits              1354                       # number of ReadReq MSHR hits
-system.cpu.dcache.ReadReq_mshr_miss_latency   1502488500                       # number of ReadReq MSHR miss cycles
-system.cpu.dcache.ReadReq_mshr_miss_rate     0.000629                       # mshr miss rate for ReadReq accesses
-system.cpu.dcache.ReadReq_mshr_misses          206689                       # number of ReadReq MSHR misses
+system.cpu.cpi                               0.945076                       # CPI: Cycles Per Instruction
+system.cpu.cpi_total                         0.945076                       # CPI: Total CPI of All Threads
+system.cpu.dcache.ReadReq_accesses          330979138                       # number of ReadReq accesses(hits+misses)
+system.cpu.dcache.ReadReq_avg_miss_latency 10103.492713                       # average ReadReq miss latency
+system.cpu.dcache.ReadReq_avg_mshr_miss_latency  7153.561618                       # average ReadReq mshr miss latency
+system.cpu.dcache.ReadReq_hits              330761084                       # number of ReadReq hits
+system.cpu.dcache.ReadReq_miss_latency     2203107000                       # number of ReadReq miss cycles
+system.cpu.dcache.ReadReq_miss_rate          0.000659                       # miss rate for ReadReq accesses
+system.cpu.dcache.ReadReq_misses               218054                       # number of ReadReq misses
+system.cpu.dcache.ReadReq_mshr_hits              3264                       # number of ReadReq MSHR hits
+system.cpu.dcache.ReadReq_mshr_miss_latency   1536513500                       # number of ReadReq MSHR miss cycles
+system.cpu.dcache.ReadReq_mshr_miss_rate     0.000649                       # mshr miss rate for ReadReq accesses
+system.cpu.dcache.ReadReq_mshr_misses          214790                       # number of ReadReq MSHR misses
 system.cpu.dcache.WriteReq_accesses         188186057                       # number of WriteReq accesses(hits+misses)
-system.cpu.dcache.WriteReq_avg_miss_latency 19664.658707                       # average WriteReq miss latency
-system.cpu.dcache.WriteReq_avg_mshr_miss_latency  9970.057484                       # average WriteReq mshr miss latency
-system.cpu.dcache.WriteReq_hits             186942755                       # number of WriteReq hits
-system.cpu.dcache.WriteReq_miss_latency   24449109500                       # number of WriteReq miss cycles
-system.cpu.dcache.WriteReq_miss_rate         0.006607                       # miss rate for WriteReq accesses
-system.cpu.dcache.WriteReq_misses             1243302                       # number of WriteReq misses
-system.cpu.dcache.WriteReq_mshr_hits           995928                       # number of WriteReq MSHR hits
-system.cpu.dcache.WriteReq_mshr_miss_latency   2466333000                       # number of WriteReq MSHR miss cycles
-system.cpu.dcache.WriteReq_mshr_miss_rate     0.001315                       # mshr miss rate for WriteReq accesses
-system.cpu.dcache.WriteReq_mshr_misses         247374                       # number of WriteReq MSHR misses
+system.cpu.dcache.WriteReq_avg_miss_latency 19459.417847                       # average WriteReq miss latency
+system.cpu.dcache.WriteReq_avg_mshr_miss_latency 10004.386505                       # average WriteReq mshr miss latency
+system.cpu.dcache.WriteReq_hits             186948986                       # number of WriteReq hits
+system.cpu.dcache.WriteReq_miss_latency   24072681495                       # number of WriteReq miss cycles
+system.cpu.dcache.WriteReq_miss_rate         0.006574                       # miss rate for WriteReq accesses
+system.cpu.dcache.WriteReq_misses             1237071                       # number of WriteReq misses
+system.cpu.dcache.WriteReq_mshr_hits           986986                       # number of WriteReq MSHR hits
+system.cpu.dcache.WriteReq_mshr_miss_latency   2501946999                       # number of WriteReq MSHR miss cycles
+system.cpu.dcache.WriteReq_mshr_miss_rate     0.001329                       # mshr miss rate for WriteReq accesses
+system.cpu.dcache.WriteReq_mshr_misses         250085                       # number of WriteReq MSHR misses
 system.cpu.dcache.avg_blocked_cycles::no_mshrs     no_value                       # average number of cycles each access was blocked
-system.cpu.dcache.avg_blocked_cycles::no_targets 15814.402211                       # average number of cycles each access was blocked
-system.cpu.dcache.avg_refs                1135.086514                       # Average number of references to valid blocks.
+system.cpu.dcache.avg_blocked_cycles::no_targets 16007.596007                       # average number of cycles each access was blocked
+system.cpu.dcache.avg_refs                1113.654359                       # Average number of references to valid blocks.
 system.cpu.dcache.blocked::no_mshrs                 0                       # number of cycles access was blocked
-system.cpu.dcache.blocked::no_targets           29308                       # number of cycles access was blocked
+system.cpu.dcache.blocked::no_targets           29555                       # number of cycles access was blocked
 system.cpu.dcache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
-system.cpu.dcache.blocked_cycles::no_targets    463488500                       # number of cycles access was blocked
+system.cpu.dcache.blocked_cycles::no_targets    473104500                       # number of cycles access was blocked
 system.cpu.dcache.cache_copies                      0                       # number of cache copies performed
-system.cpu.dcache.demand_accesses           516852133                       # number of demand (read+write) accesses
-system.cpu.dcache.demand_avg_miss_latency 18317.037300                       # average overall miss latency
-system.cpu.dcache.demand_avg_mshr_miss_latency  8740.684663                       # average overall mshr miss latency
-system.cpu.dcache.demand_hits               515400788                       # number of demand (read+write) hits
-system.cpu.dcache.demand_miss_latency     26584340500                       # number of demand (read+write) miss cycles
-system.cpu.dcache.demand_miss_rate           0.002808                       # miss rate for demand accesses
-system.cpu.dcache.demand_misses               1451345                       # number of demand (read+write) misses
-system.cpu.dcache.demand_mshr_hits             997282                       # number of demand (read+write) MSHR hits
-system.cpu.dcache.demand_mshr_miss_latency   3968821500                       # number of demand (read+write) MSHR miss cycles
-system.cpu.dcache.demand_mshr_miss_rate      0.000879                       # mshr miss rate for demand accesses
-system.cpu.dcache.demand_mshr_misses           454063                       # number of demand (read+write) MSHR misses
+system.cpu.dcache.demand_accesses           519165195                       # number of demand (read+write) accesses
+system.cpu.dcache.demand_avg_miss_latency 18057.409841                       # average overall miss latency
+system.cpu.dcache.demand_avg_mshr_miss_latency  8687.196556                       # average overall mshr miss latency
+system.cpu.dcache.demand_hits               517710070                       # number of demand (read+write) hits
+system.cpu.dcache.demand_miss_latency     26275788495                       # number of demand (read+write) miss cycles
+system.cpu.dcache.demand_miss_rate           0.002803                       # miss rate for demand accesses
+system.cpu.dcache.demand_misses               1455125                       # number of demand (read+write) misses
+system.cpu.dcache.demand_mshr_hits             990250                       # number of demand (read+write) MSHR hits
+system.cpu.dcache.demand_mshr_miss_latency   4038460499                       # number of demand (read+write) MSHR miss cycles
+system.cpu.dcache.demand_mshr_miss_rate      0.000895                       # mshr miss rate for demand accesses
+system.cpu.dcache.demand_mshr_misses           464875                       # number of demand (read+write) MSHR misses
 system.cpu.dcache.fast_writes                       0                       # number of fast writes performed
 system.cpu.dcache.mshr_cap_events                   0                       # number of times MSHR cap was activated
 system.cpu.dcache.no_allocate_misses                0                       # Number of misses that were no-allocate
-system.cpu.dcache.occ_%::0                   0.999777                       # Average percentage of cache occupancy
-system.cpu.dcache.occ_blocks::0           4095.087002                       # Average occupied blocks per context
-system.cpu.dcache.overall_accesses          516852133                       # number of overall (read+write) accesses
-system.cpu.dcache.overall_avg_miss_latency 18317.037300                       # average overall miss latency
-system.cpu.dcache.overall_avg_mshr_miss_latency  8740.684663                       # average overall mshr miss latency
+system.cpu.dcache.occ_%::0                   0.999796                       # Average percentage of cache occupancy
+system.cpu.dcache.occ_blocks::0           4095.162912                       # Average occupied blocks per context
+system.cpu.dcache.overall_accesses          519165195                       # number of overall (read+write) accesses
+system.cpu.dcache.overall_avg_miss_latency 18057.409841                       # average overall miss latency
+system.cpu.dcache.overall_avg_mshr_miss_latency  8687.196556                       # average overall mshr miss latency
 system.cpu.dcache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
-system.cpu.dcache.overall_hits              515400788                       # number of overall hits
-system.cpu.dcache.overall_miss_latency    26584340500                       # number of overall miss cycles
-system.cpu.dcache.overall_miss_rate          0.002808                       # miss rate for overall accesses
-system.cpu.dcache.overall_misses              1451345                       # number of overall misses
-system.cpu.dcache.overall_mshr_hits            997282                       # number of overall MSHR hits
-system.cpu.dcache.overall_mshr_miss_latency   3968821500                       # number of overall MSHR miss cycles
-system.cpu.dcache.overall_mshr_miss_rate     0.000879                       # mshr miss rate for overall accesses
-system.cpu.dcache.overall_mshr_misses          454063                       # number of overall MSHR misses
+system.cpu.dcache.overall_hits              517710070                       # number of overall hits
+system.cpu.dcache.overall_miss_latency    26275788495                       # number of overall miss cycles
+system.cpu.dcache.overall_miss_rate          0.002803                       # miss rate for overall accesses
+system.cpu.dcache.overall_misses              1455125                       # number of overall misses
+system.cpu.dcache.overall_mshr_hits            990250                       # number of overall MSHR hits
+system.cpu.dcache.overall_mshr_miss_latency   4038460499                       # number of overall MSHR miss cycles
+system.cpu.dcache.overall_mshr_miss_rate     0.000895                       # mshr miss rate for overall accesses
+system.cpu.dcache.overall_mshr_misses          464875                       # number of overall MSHR misses
 system.cpu.dcache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
 system.cpu.dcache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.dcache.replacements                 449967                       # number of replacements
-system.cpu.dcache.sampled_refs                 454063                       # Sample count of references to valid blocks.
+system.cpu.dcache.replacements                 460779                       # number of replacements
+system.cpu.dcache.sampled_refs                 464875                       # Sample count of references to valid blocks.
 system.cpu.dcache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
-system.cpu.dcache.tagsinuse               4095.087002                       # Cycle average of tags in use
-system.cpu.dcache.total_refs                515400788                       # Total number of references to valid blocks.
-system.cpu.dcache.warmup_cycle              331273000                       # Cycle when the warmup percentage was hit.
-system.cpu.dcache.writebacks                   403776                       # number of writebacks
-system.cpu.decode.DECODE:BlockedCycles      134525635                       # Number of cycles decode is blocked
-system.cpu.decode.DECODE:DecodedInsts      1844468999                       # Number of instructions handled by decode
-system.cpu.decode.DECODE:IdleCycles         346793246                       # Number of cycles decode is idle
-system.cpu.decode.DECODE:RunCycles          965499551                       # Number of cycles decode is running
-system.cpu.decode.DECODE:SquashCycles        29266045                       # Number of cycles decode is squashing
-system.cpu.decode.DECODE:UnblockCycles       41682476                       # Number of cycles decode is unblocking
-system.cpu.fetch.Branches                   124445048                       # Number of branches that fetch encountered
-system.cpu.fetch.CacheLines                 129713560                       # Number of cache lines fetched
-system.cpu.fetch.Cycles                    1050276779                       # Number of cycles fetch has run and was not squashing or blocked
-system.cpu.fetch.IcacheSquashes                844154                       # Number of outstanding Icache misses that were squashed
-system.cpu.fetch.Insts                     1022007635                       # Number of instructions fetch has processed
-system.cpu.fetch.MiscStallCycles                   46                       # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs
-system.cpu.fetch.SquashCycles                12829021                       # Number of cycles fetch has spent squashing
-system.cpu.fetch.branchRate                  0.081981                       # Number of branch fetches per cycle
-system.cpu.fetch.icacheStallCycles          129713560                       # Number of cycles fetch is stalled on an Icache miss
-system.cpu.fetch.predictedBranches          123829137                       # Number of branches that fetch has predicted taken
-system.cpu.fetch.rate                        0.673268                       # Number of inst fetches per cycle
-system.cpu.fetch.rateDist::samples         1517766953                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::mean              1.229744                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::stdev             1.282154                       # Number of instructions fetched each cycle (Total)
+system.cpu.dcache.tagsinuse               4095.162912                       # Cycle average of tags in use
+system.cpu.dcache.total_refs                517710070                       # Total number of references to valid blocks.
+system.cpu.dcache.warmup_cycle              317835000                       # Cycle when the warmup percentage was hit.
+system.cpu.dcache.writebacks                   411288                       # number of writebacks
+system.cpu.decode.DECODE:BlockedCycles      610366395                       # Number of cycles decode is blocked
+system.cpu.decode.DECODE:DecodedInsts      2477699501                       # Number of instructions handled by decode
+system.cpu.decode.DECODE:IdleCycles         436378814                       # Number of cycles decode is idle
+system.cpu.decode.DECODE:RunCycles          330621598                       # Number of cycles decode is running
+system.cpu.decode.DECODE:SquashCycles        99870091                       # Number of cycles decode is squashing
+system.cpu.decode.DECODE:UnblockCycles       54907489                       # Number of cycles decode is unblocking
+system.cpu.fetch.Branches                   180455810                       # Number of branches that fetch encountered
+system.cpu.fetch.CacheLines                 168863429                       # Number of cache lines fetched
+system.cpu.fetch.Cycles                     400342229                       # Number of cycles fetch has run and was not squashing or blocked
+system.cpu.fetch.IcacheSquashes                931185                       # Number of outstanding Icache misses that were squashed
+system.cpu.fetch.Insts                     1404767222                       # Number of instructions fetch has processed
+system.cpu.fetch.MiscStallCycles                   49                       # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs
+system.cpu.fetch.SquashCycles                14936403                       # Number of cycles fetch has spent squashing
+system.cpu.fetch.branchRate                  0.117758                       # Number of branch fetches per cycle
+system.cpu.fetch.icacheStallCycles          168863429                       # Number of cycles fetch is stalled on an Icache miss
+system.cpu.fetch.predictedBranches          169776992                       # Number of branches that fetch has predicted taken
+system.cpu.fetch.rate                        0.916689                       # Number of inst fetches per cycle
+system.cpu.fetch.rateDist::samples         1532144387                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::mean              1.666939                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::stdev             3.038798                       # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::underflows               0      0.00%      0.00% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::0                499259849     32.89%     32.89% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::1                507370292     33.43%     66.32% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::2                273389808     18.01%     84.34% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::3                210662042     13.88%     98.22% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::4                  8152383      0.54%     98.75% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::5                  1243560      0.08%     98.83% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::6                      720      0.00%     98.83% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::7                     8664      0.00%     98.84% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::8                 17679635      1.16%    100.00% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::0               1134818986     74.07%     74.07% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::1                 25831687      1.69%     75.75% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::2                 14383456      0.94%     76.69% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::3                 13631087      0.89%     77.58% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::4                 30570437      2.00%     79.58% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::5                 20250642      1.32%     80.90% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::6                 34285955      2.24%     83.14% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::7                 37728615      2.46%     85.60% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::8                220643522     14.40%    100.00% # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::overflows                0      0.00%    100.00% # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::min_value                0                       # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::max_value                8                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::total           1517766953                       # Number of instructions fetched each cycle (Total)
-system.cpu.fp_regfile_reads                         2                       # number of floating regfile reads
-system.cpu.icache.ReadReq_accesses          129713560                       # number of ReadReq accesses(hits+misses)
-system.cpu.icache.ReadReq_avg_miss_latency 37165.425532                       # average ReadReq miss latency
-system.cpu.icache.ReadReq_avg_mshr_miss_latency 35455.808081                       # average ReadReq mshr miss latency
-system.cpu.icache.ReadReq_hits              129712620                       # number of ReadReq hits
-system.cpu.icache.ReadReq_miss_latency       34935500                       # number of ReadReq miss cycles
+system.cpu.fetch.rateDist::total           1532144387                       # Number of instructions fetched each cycle (Total)
+system.cpu.fp_regfile_reads                        12                       # number of floating regfile reads
+system.cpu.icache.ReadReq_accesses          168863429                       # number of ReadReq accesses(hits+misses)
+system.cpu.icache.ReadReq_avg_miss_latency 34706.050695                       # average ReadReq miss latency
+system.cpu.icache.ReadReq_avg_mshr_miss_latency 35310.841984                       # average ReadReq mshr miss latency
+system.cpu.icache.ReadReq_hits              168862206                       # number of ReadReq hits
+system.cpu.icache.ReadReq_miss_latency       42445500                       # number of ReadReq miss cycles
 system.cpu.icache.ReadReq_miss_rate          0.000007                       # miss rate for ReadReq accesses
-system.cpu.icache.ReadReq_misses                  940                       # number of ReadReq misses
-system.cpu.icache.ReadReq_mshr_hits               148                       # number of ReadReq MSHR hits
-system.cpu.icache.ReadReq_mshr_miss_latency     28081000                       # number of ReadReq MSHR miss cycles
-system.cpu.icache.ReadReq_mshr_miss_rate     0.000006                       # mshr miss rate for ReadReq accesses
-system.cpu.icache.ReadReq_mshr_misses             792                       # number of ReadReq MSHR misses
+system.cpu.icache.ReadReq_misses                 1223                       # number of ReadReq misses
+system.cpu.icache.ReadReq_mshr_hits               356                       # number of ReadReq MSHR hits
+system.cpu.icache.ReadReq_mshr_miss_latency     30614500                       # number of ReadReq MSHR miss cycles
+system.cpu.icache.ReadReq_mshr_miss_rate     0.000005                       # mshr miss rate for ReadReq accesses
+system.cpu.icache.ReadReq_mshr_misses             867                       # number of ReadReq MSHR misses
 system.cpu.icache.avg_blocked_cycles::no_mshrs     no_value                       # average number of cycles each access was blocked
 system.cpu.icache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
-system.cpu.icache.avg_refs               163778.560606                       # Average number of references to valid blocks.
+system.cpu.icache.avg_refs               194766.096886                       # Average number of references to valid blocks.
 system.cpu.icache.blocked::no_mshrs                 0                       # number of cycles access was blocked
 system.cpu.icache.blocked::no_targets               0                       # number of cycles access was blocked
 system.cpu.icache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.icache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.icache.cache_copies                      0                       # number of cache copies performed
-system.cpu.icache.demand_accesses           129713560                       # number of demand (read+write) accesses
-system.cpu.icache.demand_avg_miss_latency 37165.425532                       # average overall miss latency
-system.cpu.icache.demand_avg_mshr_miss_latency 35455.808081                       # average overall mshr miss latency
-system.cpu.icache.demand_hits               129712620                       # number of demand (read+write) hits
-system.cpu.icache.demand_miss_latency        34935500                       # number of demand (read+write) miss cycles
+system.cpu.icache.demand_accesses           168863429                       # number of demand (read+write) accesses
+system.cpu.icache.demand_avg_miss_latency 34706.050695                       # average overall miss latency
+system.cpu.icache.demand_avg_mshr_miss_latency 35310.841984                       # average overall mshr miss latency
+system.cpu.icache.demand_hits               168862206                       # number of demand (read+write) hits
+system.cpu.icache.demand_miss_latency        42445500                       # number of demand (read+write) miss cycles
 system.cpu.icache.demand_miss_rate           0.000007                       # miss rate for demand accesses
-system.cpu.icache.demand_misses                   940                       # number of demand (read+write) misses
-system.cpu.icache.demand_mshr_hits                148                       # number of demand (read+write) MSHR hits
-system.cpu.icache.demand_mshr_miss_latency     28081000                       # number of demand (read+write) MSHR miss cycles
-system.cpu.icache.demand_mshr_miss_rate      0.000006                       # mshr miss rate for demand accesses
-system.cpu.icache.demand_mshr_misses              792                       # number of demand (read+write) MSHR misses
+system.cpu.icache.demand_misses                  1223                       # number of demand (read+write) misses
+system.cpu.icache.demand_mshr_hits                356                       # number of demand (read+write) MSHR hits
+system.cpu.icache.demand_mshr_miss_latency     30614500                       # number of demand (read+write) MSHR miss cycles
+system.cpu.icache.demand_mshr_miss_rate      0.000005                       # mshr miss rate for demand accesses
+system.cpu.icache.demand_mshr_misses              867                       # number of demand (read+write) MSHR misses
 system.cpu.icache.fast_writes                       0                       # number of fast writes performed
 system.cpu.icache.mshr_cap_events                   0                       # number of times MSHR cap was activated
 system.cpu.icache.no_allocate_misses                0                       # Number of misses that were no-allocate
-system.cpu.icache.occ_%::0                   0.352940                       # Average percentage of cache occupancy
-system.cpu.icache.occ_blocks::0            722.820283                       # Average occupied blocks per context
-system.cpu.icache.overall_accesses          129713560                       # number of overall (read+write) accesses
-system.cpu.icache.overall_avg_miss_latency 37165.425532                       # average overall miss latency
-system.cpu.icache.overall_avg_mshr_miss_latency 35455.808081                       # average overall mshr miss latency
+system.cpu.icache.occ_%::0                   0.386137                       # Average percentage of cache occupancy
+system.cpu.icache.occ_blocks::0            790.808810                       # Average occupied blocks per context
+system.cpu.icache.overall_accesses          168863429                       # number of overall (read+write) accesses
+system.cpu.icache.overall_avg_miss_latency 34706.050695                       # average overall miss latency
+system.cpu.icache.overall_avg_mshr_miss_latency 35310.841984                       # average overall mshr miss latency
 system.cpu.icache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
-system.cpu.icache.overall_hits              129712620                       # number of overall hits
-system.cpu.icache.overall_miss_latency       34935500                       # number of overall miss cycles
+system.cpu.icache.overall_hits              168862206                       # number of overall hits
+system.cpu.icache.overall_miss_latency       42445500                       # number of overall miss cycles
 system.cpu.icache.overall_miss_rate          0.000007                       # miss rate for overall accesses
-system.cpu.icache.overall_misses                  940                       # number of overall misses
-system.cpu.icache.overall_mshr_hits               148                       # number of overall MSHR hits
-system.cpu.icache.overall_mshr_miss_latency     28081000                       # number of overall MSHR miss cycles
-system.cpu.icache.overall_mshr_miss_rate     0.000006                       # mshr miss rate for overall accesses
-system.cpu.icache.overall_mshr_misses             792                       # number of overall MSHR misses
+system.cpu.icache.overall_misses                 1223                       # number of overall misses
+system.cpu.icache.overall_mshr_hits               356                       # number of overall MSHR hits
+system.cpu.icache.overall_mshr_miss_latency     30614500                       # number of overall MSHR miss cycles
+system.cpu.icache.overall_mshr_miss_rate     0.000005                       # mshr miss rate for overall accesses
+system.cpu.icache.overall_mshr_misses             867                       # number of overall MSHR misses
 system.cpu.icache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
 system.cpu.icache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.icache.replacements                      4                       # number of replacements
-system.cpu.icache.sampled_refs                    792                       # Sample count of references to valid blocks.
+system.cpu.icache.replacements                     11                       # number of replacements
+system.cpu.icache.sampled_refs                    867                       # Sample count of references to valid blocks.
 system.cpu.icache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
-system.cpu.icache.tagsinuse                722.820283                       # Cycle average of tags in use
-system.cpu.icache.total_refs                129712620                       # Total number of references to valid blocks.
+system.cpu.icache.tagsinuse                790.808810                       # Cycle average of tags in use
+system.cpu.icache.total_refs                168862206                       # Total number of references to valid blocks.
 system.cpu.icache.warmup_cycle                      0                       # Cycle when the warmup percentage was hit.
 system.cpu.icache.writebacks                        0                       # number of writebacks
-system.cpu.idleCycles                          214442                       # Total number of cycles that the CPU has spent unscheduled due to idling
-system.cpu.iew.EXEC:branches                108628514                       # Number of branches executed
+system.cpu.idleCycles                          291024                       # Total number of cycles that the CPU has spent unscheduled due to idling
+system.cpu.iew.EXEC:branches                111314295                       # Number of branches executed
 system.cpu.iew.EXEC:nop                             0                       # number of nop insts executed
-system.cpu.iew.EXEC:rate                     1.113825                       # Inst execution rate
-system.cpu.iew.EXEC:refs                    627755630                       # number of memory reference insts executed
-system.cpu.iew.EXEC:stores                  190105687                       # Number of stores executed
+system.cpu.iew.EXEC:rate                     1.203312                       # Inst execution rate
+system.cpu.iew.EXEC:refs                    636104355                       # number of memory reference insts executed
+system.cpu.iew.EXEC:stores                  191312994                       # Number of stores executed
 system.cpu.iew.EXEC:swp                             0                       # number of swp insts executed
-system.cpu.iew.WB:consumers                1860684264                       # num instructions consuming a value
-system.cpu.iew.WB:count                    1687762822                       # cumulative count of insts written-back
-system.cpu.iew.WB:fanout                     0.711350                       # average fanout of values written-back
+system.cpu.iew.WB:consumers                2089450315                       # num instructions consuming a value
+system.cpu.iew.WB:count                    1839101566                       # cumulative count of insts written-back
+system.cpu.iew.WB:fanout                     0.684612                       # average fanout of values written-back
 system.cpu.iew.WB:penalized                         0                       # number of instrctions required to write to 'other' IQ
 system.cpu.iew.WB:penalized_rate                    0                       # fraction of instructions written-back that wrote to 'other' IQ
-system.cpu.iew.WB:producers                1323598001                       # num instructions producing a value
-system.cpu.iew.WB:rate                       1.111847                       # insts written-back per cycle
-system.cpu.iew.WB:sent                     1688206003                       # cumulative count of insts sent to commit
-system.cpu.iew.branchMispredicts              6113342                       # Number of branch mispredicts detected at execute
-system.cpu.iew.iewBlockCycles                 1234561                       # Number of cycles IEW is blocking
-system.cpu.iew.iewDispLoadInsts             466864036                       # Number of dispatched load instructions
-system.cpu.iew.iewDispNonSpecInsts                 67                       # Number of dispatched non-speculative instructions
-system.cpu.iew.iewDispSquashedInsts           3697894                       # Number of squashed instructions skipped by dispatch
-system.cpu.iew.iewDispStoreInsts            198431314                       # Number of dispatched store instructions
-system.cpu.iew.iewDispatchedInsts          1795988309                       # Number of instructions dispatched to IQ
-system.cpu.iew.iewExecLoadInsts             437649943                       # Number of load instructions executed
-system.cpu.iew.iewExecSquashedInsts           8316492                       # Number of squashed instructions skipped in execute
-system.cpu.iew.iewExecutedInsts            1690766136                       # Number of executed instructions
-system.cpu.iew.iewIQFullEvents                  11689                       # Number of times the IQ has become full, causing a stall
+system.cpu.iew.WB:producers                1430463261                       # num instructions producing a value
+system.cpu.iew.WB:rate                       1.200117                       # insts written-back per cycle
+system.cpu.iew.WB:sent                     1842290775                       # cumulative count of insts sent to commit
+system.cpu.iew.branchMispredicts              8145736                       # Number of branch mispredicts detected at execute
+system.cpu.iew.iewBlockCycles                 1415270                       # Number of cycles IEW is blocking
+system.cpu.iew.iewDispLoadInsts             617903270                       # Number of dispatched load instructions
+system.cpu.iew.iewDispNonSpecInsts                 78                       # Number of dispatched non-speculative instructions
+system.cpu.iew.iewDispSquashedInsts            633937                       # Number of squashed instructions skipped by dispatch
+system.cpu.iew.iewDispStoreInsts            251132554                       # Number of dispatched store instructions
+system.cpu.iew.iewDispatchedInsts          2351086206                       # Number of instructions dispatched to IQ
+system.cpu.iew.iewExecLoadInsts             444791361                       # Number of load instructions executed
+system.cpu.iew.iewExecSquashedInsts          11969895                       # Number of squashed instructions skipped in execute
+system.cpu.iew.iewExecutedInsts            1843997360                       # Number of executed instructions
+system.cpu.iew.iewIQFullEvents                  60905                       # Number of times the IQ has become full, causing a stall
 system.cpu.iew.iewIdleCycles                        0                       # Number of cycles IEW is idle
-system.cpu.iew.iewLSQFullEvents                     0                       # Number of times the LSQ has become full, causing a stall
-system.cpu.iew.iewSquashCycles               29266045                       # Number of cycles IEW is squashing
-system.cpu.iew.iewUnblockCycles                 61051                       # Number of cycles IEW is unblocking
+system.cpu.iew.iewLSQFullEvents                     2                       # Number of times the LSQ has become full, causing a stall
+system.cpu.iew.iewSquashCycles               99870091                       # Number of cycles IEW is squashing
+system.cpu.iew.iewUnblockCycles                117847                       # Number of cycles IEW is unblocking
 system.cpu.iew.lsq.thread.0.blockedLoads            0                       # Number of blocked loads due to partial load-store forwarding
-system.cpu.iew.lsq.thread.0.cacheBlocked        29308                       # Number of times an access to memory failed due to the cache being blocked
-system.cpu.iew.lsq.thread.0.forwLoads       108968785                       # Number of loads that had data forwarded from stores
-system.cpu.iew.lsq.thread.0.ignoredResponses        18692                       # Number of memory responses ignored because the instruction is squashed
+system.cpu.iew.lsq.thread.0.cacheBlocked        29753                       # Number of times an access to memory failed due to the cache being blocked
+system.cpu.iew.lsq.thread.0.forwLoads       113796852                       # Number of loads that had data forwarded from stores
+system.cpu.iew.lsq.thread.0.ignoredResponses         8470                       # Number of memory responses ignored because the instruction is squashed
 system.cpu.iew.lsq.thread.0.invAddrLoads            0                       # Number of loads ignored due to an invalid address
 system.cpu.iew.lsq.thread.0.invAddrSwpfs            0                       # Number of software prefetches ignored due to an invalid address
-system.cpu.iew.lsq.thread.0.memOrderViolation      6882405                       # Number of memory ordering violations
-system.cpu.iew.lsq.thread.0.rescheduledLoads           14                       # Number of loads that were rescheduled
-system.cpu.iew.lsq.thread.0.squashedLoads     47821911                       # Number of loads squashed
-system.cpu.iew.lsq.thread.0.squashedStores     10245257                       # Number of stores squashed
-system.cpu.iew.memOrderViolationEvents        6882405                       # Number of memory order violations
-system.cpu.iew.predictedNotTakenIncorrect         2235                       # Number of branches that were predicted not taken incorrectly
-system.cpu.iew.predictedTakenIncorrect        6111107                       # Number of branches that were predicted taken incorrectly
-system.cpu.int_regfile_reads               3195299120                       # number of integer regfile reads
-system.cpu.int_regfile_writes              1684589292                       # number of integer regfile writes
-system.cpu.ipc                               1.068191                       # IPC: Instructions Per Cycle
-system.cpu.ipc_total                         1.068191                       # IPC: Total IPC of All Threads
-system.cpu.iq.ISSUE:FU_type_0::No_OpClass     24153767      1.42%      1.42% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::IntAlu      1042557757     61.36%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::IntMult              0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::IntDiv               0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatAdd             0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatCmp             0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatCvt             0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatMult            0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatDiv             0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatSqrt            0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdAdd              0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdAddAcc            0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdAlu              0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdCmp              0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdCvt              0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdMisc             0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdMult             0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdMultAcc            0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdShift            0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdShiftAcc            0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdSqrt             0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatAdd            0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatAlu            0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatCmp            0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatCvt            0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatDiv            0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatMisc            0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatMult            0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatMultAcc            0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatSqrt            0      0.00%     62.78% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::MemRead      442155303     26.02%     88.80% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::MemWrite     190215801     11.20%    100.00% # Type of FU issued
+system.cpu.iew.lsq.thread.0.memOrderViolation      6921754                       # Number of memory ordering violations
+system.cpu.iew.lsq.thread.0.rescheduledLoads           21                       # Number of loads that were rescheduled
+system.cpu.iew.lsq.thread.0.squashedLoads    198861145                       # Number of loads squashed
+system.cpu.iew.lsq.thread.0.squashedStores     62946497                       # Number of stores squashed
+system.cpu.iew.memOrderViolationEvents        6921754                       # Number of memory order violations
+system.cpu.iew.predictedNotTakenIncorrect      3700861                       # Number of branches that were predicted not taken incorrectly
+system.cpu.iew.predictedTakenIncorrect        4444875                       # Number of branches that were predicted taken incorrectly
+system.cpu.int_regfile_reads               3233304065                       # number of integer regfile reads
+system.cpu.int_regfile_writes              1832324218                       # number of integer regfile writes
+system.cpu.ipc                               1.058116                       # IPC: Instructions Per Cycle
+system.cpu.ipc_total                         1.058116                       # IPC: Total IPC of All Threads
+system.cpu.iq.ISSUE:FU_type_0::No_OpClass     27128947      1.46%      1.46% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::IntAlu      1186880889     63.95%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::IntMult              0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::IntDiv               0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatAdd             0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatCmp             0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatCvt             0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatMult            0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatDiv             0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatSqrt            0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdAdd              0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdAddAcc            0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdAlu              0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdCmp              0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdCvt              0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdMisc             0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdMult             0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdMultAcc            0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdShift            0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdShiftAcc            0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdSqrt             0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatAdd            0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatAlu            0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatCmp            0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatCvt            0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatDiv            0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatMisc            0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatMult            0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatMultAcc            0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatSqrt            0      0.00%     65.41% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::MemRead      450365179     24.27%     89.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::MemWrite     191592240     10.32%    100.00% # Type of FU issued
 system.cpu.iq.ISSUE:FU_type_0::IprAccess            0      0.00%    100.00% # Type of FU issued
 system.cpu.iq.ISSUE:FU_type_0::InstPrefetch            0      0.00%    100.00% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::total       1699082628                       # Type of FU issued
-system.cpu.iq.ISSUE:fu_busy_cnt                898465                       # FU busy when requested
-system.cpu.iq.ISSUE:fu_busy_rate             0.000529                       # FU busy rate (busy events/executed inst)
+system.cpu.iq.ISSUE:FU_type_0::total       1855967255                       # Type of FU issued
+system.cpu.iq.ISSUE:fu_busy_cnt               4437489                       # FU busy when requested
+system.cpu.iq.ISSUE:fu_busy_rate             0.002391                       # FU busy rate (busy events/executed inst)
 system.cpu.iq.ISSUE:fu_full::No_OpClass             0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::IntAlu                 2      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::IntMult                0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::IntDiv                 0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatAdd               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatCmp               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatCvt               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatMult              0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatDiv               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatSqrt              0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdAdd                0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdAddAcc             0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdAlu                0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdCmp                0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdCvt                0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdMisc               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdMult               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdMultAcc            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdShift              0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdShiftAcc            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdSqrt               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatAdd            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatAlu            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatCmp            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatCvt            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatDiv            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatMisc            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatMult            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatMultAcc            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatSqrt            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::MemRead           782842     87.13%     87.13% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::MemWrite          115621     12.87%    100.00% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::IntAlu            118316      2.67%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::IntMult                0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::IntDiv                 0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatAdd               0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatCmp               0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatCvt               0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatMult              0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatDiv               0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatSqrt              0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdAdd                0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdAddAcc             0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdAlu                0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdCmp                0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdCvt                0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdMisc               0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdMult               0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdMultAcc            0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdShift              0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdShiftAcc            0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdSqrt               0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatAdd            0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatAlu            0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatCmp            0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatCvt            0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatDiv            0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatMisc            0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatMult            0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatMultAcc            0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatSqrt            0      0.00%      2.67% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::MemRead          3486899     78.58%     81.24% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::MemWrite          832274     18.76%    100.00% # attempts to use FU when none available
 system.cpu.iq.ISSUE:fu_full::IprAccess              0      0.00%    100.00% # attempts to use FU when none available
 system.cpu.iq.ISSUE:fu_full::InstPrefetch            0      0.00%    100.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:issued_per_cycle::samples   1517766953                       # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::mean     1.119462                       # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::stdev     0.970342                       # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::samples   1532144387                       # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::mean     1.211353                       # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::stdev     1.177271                       # Number of insts issued each cycle
 system.cpu.iq.ISSUE:issued_per_cycle::underflows            0      0.00%      0.00% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::0     418312841     27.56%     27.56% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::1     673262157     44.36%     71.92% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::2     290551111     19.14%     91.06% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::3     102329684      6.74%     97.81% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::4      29422654      1.94%     99.74% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::5       3376155      0.22%     99.97% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::6        428915      0.03%     99.99% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::7         83172      0.01%    100.00% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::8           264      0.00%    100.00% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::0     466354124     30.44%     30.44% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::1     601647548     39.27%     69.71% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::2     244545222     15.96%     85.67% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::3     139808763      9.13%     94.79% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::4      60228260      3.93%     98.72% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::5      13792665      0.90%     99.62% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::6       4627487      0.30%     99.93% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::7        960857      0.06%     99.99% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::8        179461      0.01%    100.00% # Number of insts issued each cycle
 system.cpu.iq.ISSUE:issued_per_cycle::overflows            0      0.00%    100.00% # Number of insts issued each cycle
 system.cpu.iq.ISSUE:issued_per_cycle::min_value            0                       # Number of insts issued each cycle
 system.cpu.iq.ISSUE:issued_per_cycle::max_value            8                       # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::total   1517766953                       # Number of insts issued each cycle
-system.cpu.iq.ISSUE:rate                     1.119304                       # Inst issue rate
-system.cpu.iq.fp_alu_accesses                       4                       # Number of floating point alu accesses
-system.cpu.iq.fp_inst_queue_reads                   8                       # Number of floating instruction queue reads
-system.cpu.iq.fp_inst_queue_wakeup_accesses            2                       # Number of floating instruction queue wakeup accesses
-system.cpu.iq.fp_inst_queue_writes                  8                       # Number of floating instruction queue writes
-system.cpu.iq.int_alu_accesses             1675827322                       # Number of integer alu accesses
-system.cpu.iq.int_inst_queue_reads         4916833706                       # Number of integer instruction queue reads
-system.cpu.iq.int_inst_queue_wakeup_accesses   1687762820                       # Number of integer instruction queue wakeup accesses
-system.cpu.iq.int_inst_queue_writes        1976960091                       # Number of integer instruction queue writes
-system.cpu.iq.iqInstsAdded                 1795988242                       # Number of instructions added to the IQ (excludes non-spec)
-system.cpu.iq.iqInstsIssued                1699082628                       # Number of instructions issued
-system.cpu.iq.iqNonSpecInstsAdded                  67                       # Number of non-speculative instructions added to the IQ
-system.cpu.iq.iqSquashedInstsExamined       174090375                       # Number of squashed instructions iterated over during squash; mainly for profiling
-system.cpu.iq.iqSquashedInstsIssued              3040                       # Number of squashed instructions issued
-system.cpu.iq.iqSquashedNonSpecRemoved             17                       # Number of squashed non-spec instructions that were removed
-system.cpu.iq.iqSquashedOperandsExamined    322977188                       # Number of squashed operands that are examined and possibly removed from graph
-system.cpu.l2cache.ReadExReq_accesses          247374                       # number of ReadExReq accesses(hits+misses)
-system.cpu.l2cache.ReadExReq_avg_miss_latency 34288.873379                       # average ReadExReq miss latency
-system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31083.636921                       # average ReadExReq mshr miss latency
-system.cpu.l2cache.ReadExReq_hits              188632                       # number of ReadExReq hits
-system.cpu.l2cache.ReadExReq_miss_latency   2014197000                       # number of ReadExReq miss cycles
-system.cpu.l2cache.ReadExReq_miss_rate       0.237462                       # miss rate for ReadExReq accesses
-system.cpu.l2cache.ReadExReq_misses             58742                       # number of ReadExReq misses
-system.cpu.l2cache.ReadExReq_mshr_miss_latency   1825915000                       # number of ReadExReq MSHR miss cycles
-system.cpu.l2cache.ReadExReq_mshr_miss_rate     0.237462                       # mshr miss rate for ReadExReq accesses
-system.cpu.l2cache.ReadExReq_mshr_misses        58742                       # number of ReadExReq MSHR misses
-system.cpu.l2cache.ReadReq_accesses            207481                       # number of ReadReq accesses(hits+misses)
-system.cpu.l2cache.ReadReq_avg_miss_latency 34134.816432                       # average ReadReq miss latency
-system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31005.350224                       # average ReadReq mshr miss latency
-system.cpu.l2cache.ReadReq_hits                174959                       # number of ReadReq hits
-system.cpu.l2cache.ReadReq_miss_latency    1110132500                       # number of ReadReq miss cycles
-system.cpu.l2cache.ReadReq_miss_rate         0.156747                       # miss rate for ReadReq accesses
-system.cpu.l2cache.ReadReq_misses               32522                       # number of ReadReq misses
-system.cpu.l2cache.ReadReq_mshr_miss_latency   1008356000                       # number of ReadReq MSHR miss cycles
-system.cpu.l2cache.ReadReq_mshr_miss_rate     0.156747                       # mshr miss rate for ReadReq accesses
-system.cpu.l2cache.ReadReq_mshr_misses          32522                       # number of ReadReq MSHR misses
-system.cpu.l2cache.Writeback_accesses          403776                       # number of Writeback accesses(hits+misses)
-system.cpu.l2cache.Writeback_hits              403776                       # number of Writeback hits
+system.cpu.iq.ISSUE:issued_per_cycle::total   1532144387                       # Number of insts issued each cycle
+system.cpu.iq.ISSUE:rate                     1.211123                       # Inst issue rate
+system.cpu.iq.fp_alu_accesses                      18                       # Number of floating point alu accesses
+system.cpu.iq.fp_inst_queue_reads                  33                       # Number of floating instruction queue reads
+system.cpu.iq.fp_inst_queue_wakeup_accesses           12                       # Number of floating instruction queue wakeup accesses
+system.cpu.iq.fp_inst_queue_writes                 32                       # Number of floating instruction queue writes
+system.cpu.iq.int_alu_accesses             1833275779                       # Number of integer alu accesses
+system.cpu.iq.int_inst_queue_reads         5248603279                       # Number of integer instruction queue reads
+system.cpu.iq.int_inst_queue_wakeup_accesses   1839101554                       # Number of integer instruction queue wakeup accesses
+system.cpu.iq.int_inst_queue_writes        3087460502                       # Number of integer instruction queue writes
+system.cpu.iq.iqInstsAdded                 2351086128                       # Number of instructions added to the IQ (excludes non-spec)
+system.cpu.iq.iqInstsIssued                1855967255                       # Number of instructions issued
+system.cpu.iq.iqNonSpecInstsAdded                  78                       # Number of non-speculative instructions added to the IQ
+system.cpu.iq.iqSquashedInstsExamined       729454588                       # Number of squashed instructions iterated over during squash; mainly for profiling
+system.cpu.iq.iqSquashedInstsIssued             86926                       # Number of squashed instructions issued
+system.cpu.iq.iqSquashedNonSpecRemoved             28                       # Number of squashed non-spec instructions that were removed
+system.cpu.iq.iqSquashedOperandsExamined   1543114171                       # Number of squashed operands that are examined and possibly removed from graph
+system.cpu.l2cache.ReadExReq_accesses          250094                       # number of ReadExReq accesses(hits+misses)
+system.cpu.l2cache.ReadExReq_avg_miss_latency 34363.888228                       # average ReadExReq miss latency
+system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31092.455043                       # average ReadExReq mshr miss latency
+system.cpu.l2cache.ReadExReq_hits              191260                       # number of ReadExReq hits
+system.cpu.l2cache.ReadExReq_miss_latency   2021765000                       # number of ReadExReq miss cycles
+system.cpu.l2cache.ReadExReq_miss_rate       0.235248                       # miss rate for ReadExReq accesses
+system.cpu.l2cache.ReadExReq_misses             58834                       # number of ReadExReq misses
+system.cpu.l2cache.ReadExReq_mshr_miss_latency   1829293500                       # number of ReadExReq MSHR miss cycles
+system.cpu.l2cache.ReadExReq_mshr_miss_rate     0.235248                       # mshr miss rate for ReadExReq accesses
+system.cpu.l2cache.ReadExReq_mshr_misses        58834                       # number of ReadExReq MSHR misses
+system.cpu.l2cache.ReadReq_accesses            215648                       # number of ReadReq accesses(hits+misses)
+system.cpu.l2cache.ReadReq_avg_miss_latency 34134.880348                       # average ReadReq miss latency
+system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31005.967489                       # average ReadReq mshr miss latency
+system.cpu.l2cache.ReadReq_hits                182552                       # number of ReadReq hits
+system.cpu.l2cache.ReadReq_miss_latency    1129728000                       # number of ReadReq miss cycles
+system.cpu.l2cache.ReadReq_miss_rate         0.153472                       # miss rate for ReadReq accesses
+system.cpu.l2cache.ReadReq_misses               33096                       # number of ReadReq misses
+system.cpu.l2cache.ReadReq_mshr_miss_latency   1026173500                       # number of ReadReq MSHR miss cycles
+system.cpu.l2cache.ReadReq_mshr_miss_rate     0.153472                       # mshr miss rate for ReadReq accesses
+system.cpu.l2cache.ReadReq_mshr_misses          33096                       # number of ReadReq MSHR misses
+system.cpu.l2cache.Writeback_accesses          411288                       # number of Writeback accesses(hits+misses)
+system.cpu.l2cache.Writeback_hits              411288                       # number of Writeback hits
 system.cpu.l2cache.avg_blocked_cycles::no_mshrs     no_value                       # average number of cycles each access was blocked
 system.cpu.l2cache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
-system.cpu.l2cache.avg_refs                  4.963363                       # Average number of references to valid blocks.
+system.cpu.l2cache.avg_refs                  5.099303                       # Average number of references to valid blocks.
 system.cpu.l2cache.blocked::no_mshrs                0                       # number of cycles access was blocked
 system.cpu.l2cache.blocked::no_targets              0                       # number of cycles access was blocked
 system.cpu.l2cache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.l2cache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.l2cache.cache_copies                     0                       # number of cache copies performed
-system.cpu.l2cache.demand_accesses             454855                       # number of demand (read+write) accesses
-system.cpu.l2cache.demand_avg_miss_latency 34233.975061                       # average overall miss latency
-system.cpu.l2cache.demand_avg_mshr_miss_latency 31055.739393                       # average overall mshr miss latency
-system.cpu.l2cache.demand_hits                 363591                       # number of demand (read+write) hits
-system.cpu.l2cache.demand_miss_latency     3124329500                       # number of demand (read+write) miss cycles
-system.cpu.l2cache.demand_miss_rate          0.200644                       # miss rate for demand accesses
-system.cpu.l2cache.demand_misses                91264                       # number of demand (read+write) misses
+system.cpu.l2cache.demand_accesses             465742                       # number of demand (read+write) accesses
+system.cpu.l2cache.demand_avg_miss_latency 34281.442402                       # average overall miss latency
+system.cpu.l2cache.demand_avg_mshr_miss_latency 31061.318394                       # average overall mshr miss latency
+system.cpu.l2cache.demand_hits                 373812                       # number of demand (read+write) hits
+system.cpu.l2cache.demand_miss_latency     3151493000                       # number of demand (read+write) miss cycles
+system.cpu.l2cache.demand_miss_rate          0.197384                       # miss rate for demand accesses
+system.cpu.l2cache.demand_misses                91930                       # number of demand (read+write) misses
 system.cpu.l2cache.demand_mshr_hits                 0                       # number of demand (read+write) MSHR hits
-system.cpu.l2cache.demand_mshr_miss_latency   2834271000                       # number of demand (read+write) MSHR miss cycles
-system.cpu.l2cache.demand_mshr_miss_rate     0.200644                       # mshr miss rate for demand accesses
-system.cpu.l2cache.demand_mshr_misses           91264                       # number of demand (read+write) MSHR misses
+system.cpu.l2cache.demand_mshr_miss_latency   2855467000                       # number of demand (read+write) MSHR miss cycles
+system.cpu.l2cache.demand_mshr_miss_rate     0.197384                       # mshr miss rate for demand accesses
+system.cpu.l2cache.demand_mshr_misses           91930                       # number of demand (read+write) MSHR misses
 system.cpu.l2cache.fast_writes                      0                       # number of fast writes performed
 system.cpu.l2cache.mshr_cap_events                  0                       # number of times MSHR cap was activated
 system.cpu.l2cache.no_allocate_misses               0                       # Number of misses that were no-allocate
-system.cpu.l2cache.occ_%::0                  0.058891                       # Average percentage of cache occupancy
-system.cpu.l2cache.occ_%::1                  0.491980                       # Average percentage of cache occupancy
-system.cpu.l2cache.occ_blocks::0          1929.753834                       # Average occupied blocks per context
-system.cpu.l2cache.occ_blocks::1         16121.198217                       # Average occupied blocks per context
-system.cpu.l2cache.overall_accesses            454855                       # number of overall (read+write) accesses
-system.cpu.l2cache.overall_avg_miss_latency 34233.975061                       # average overall miss latency
-system.cpu.l2cache.overall_avg_mshr_miss_latency 31055.739393                       # average overall mshr miss latency
+system.cpu.l2cache.occ_%::0                  0.059053                       # Average percentage of cache occupancy
+system.cpu.l2cache.occ_%::1                  0.491352                       # Average percentage of cache occupancy
+system.cpu.l2cache.occ_blocks::0          1935.054426                       # Average occupied blocks per context
+system.cpu.l2cache.occ_blocks::1         16100.609355                       # Average occupied blocks per context
+system.cpu.l2cache.overall_accesses            465742                       # number of overall (read+write) accesses
+system.cpu.l2cache.overall_avg_miss_latency 34281.442402                       # average overall miss latency
+system.cpu.l2cache.overall_avg_mshr_miss_latency 31061.318394                       # average overall mshr miss latency
 system.cpu.l2cache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
-system.cpu.l2cache.overall_hits                363591                       # number of overall hits
-system.cpu.l2cache.overall_miss_latency    3124329500                       # number of overall miss cycles
-system.cpu.l2cache.overall_miss_rate         0.200644                       # miss rate for overall accesses
-system.cpu.l2cache.overall_misses               91264                       # number of overall misses
+system.cpu.l2cache.overall_hits                373812                       # number of overall hits
+system.cpu.l2cache.overall_miss_latency    3151493000                       # number of overall miss cycles
+system.cpu.l2cache.overall_miss_rate         0.197384                       # miss rate for overall accesses
+system.cpu.l2cache.overall_misses               91930                       # number of overall misses
 system.cpu.l2cache.overall_mshr_hits                0                       # number of overall MSHR hits
-system.cpu.l2cache.overall_mshr_miss_latency   2834271000                       # number of overall MSHR miss cycles
-system.cpu.l2cache.overall_mshr_miss_rate     0.200644                       # mshr miss rate for overall accesses
-system.cpu.l2cache.overall_mshr_misses          91264                       # number of overall MSHR misses
+system.cpu.l2cache.overall_mshr_miss_latency   2855467000                       # number of overall MSHR miss cycles
+system.cpu.l2cache.overall_mshr_miss_rate     0.197384                       # mshr miss rate for overall accesses
+system.cpu.l2cache.overall_mshr_misses          91930                       # number of overall MSHR misses
 system.cpu.l2cache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
 system.cpu.l2cache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.l2cache.replacements                 72998                       # number of replacements
-system.cpu.l2cache.sampled_refs                 88598                       # Sample count of references to valid blocks.
+system.cpu.l2cache.replacements                 73661                       # number of replacements
+system.cpu.l2cache.sampled_refs                 89262                       # Sample count of references to valid blocks.
 system.cpu.l2cache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
-system.cpu.l2cache.tagsinuse             18050.952051                       # Cycle average of tags in use
-system.cpu.l2cache.total_refs                  439744                       # Total number of references to valid blocks.
+system.cpu.l2cache.tagsinuse             18035.663781                       # Cycle average of tags in use
+system.cpu.l2cache.total_refs                  455174                       # Total number of references to valid blocks.
 system.cpu.l2cache.warmup_cycle                     0                       # Cycle when the warmup percentage was hit.
-system.cpu.l2cache.writebacks                   58419                       # number of writebacks
-system.cpu.memDep0.conflictingLoads         312249439                       # Number of conflicting loads.
-system.cpu.memDep0.conflictingStores        119901234                       # Number of conflicting stores.
-system.cpu.memDep0.insertedLoads            466864036                       # Number of loads inserted to the mem dependence unit.
-system.cpu.memDep0.insertedStores           198431314                       # Number of stores inserted to the mem dependence unit.
-system.cpu.misc_regfile_reads               865536711                       # number of misc regfile reads
-system.cpu.numCycles                       1517981395                       # number of cpu cycles simulated
+system.cpu.l2cache.writebacks                   58542                       # number of writebacks
+system.cpu.memDep0.conflictingLoads         537232404                       # Number of conflicting loads.
+system.cpu.memDep0.conflictingStores        219207458                       # Number of conflicting stores.
+system.cpu.memDep0.insertedLoads            617903270                       # Number of loads inserted to the mem dependence unit.
+system.cpu.memDep0.insertedStores           251132554                       # Number of stores inserted to the mem dependence unit.
+system.cpu.misc_regfile_reads               931505074                       # number of misc regfile reads
+system.cpu.numCycles                       1532435411                       # number of cpu cycles simulated
 system.cpu.numWorkItemsCompleted                    0                       # number of work items this cpu completed
 system.cpu.numWorkItemsStarted                      0                       # number of work items this cpu started
-system.cpu.rename.RENAME:BlockCycles         28986025                       # Number of cycles rename is blocking
+system.cpu.rename.RENAME:BlockCycles        175534951                       # Number of cycles rename is blocking
 system.cpu.rename.RENAME:CommittedMaps     1617994650                       # Number of HB maps that are committed
-system.cpu.rename.RENAME:IQFullEvents        33672472                       # Number of times rename has blocked due to IQ full
-system.cpu.rename.RENAME:IdleCycles         389992916                       # Number of cycles rename is idle
-system.cpu.rename.RENAME:LSQFullEvents       45640252                       # Number of times rename has blocked due to LSQ full
-system.cpu.rename.RENAME:ROBFullEvents             23                       # Number of times rename has blocked due to ROB full
-system.cpu.rename.RENAME:RenameLookups     4455391031                       # Number of register rename lookups that rename has made
-system.cpu.rename.RENAME:RenamedInsts      1827559293                       # Number of instructions processed by rename
-system.cpu.rename.RENAME:RenamedOperands   1825935922                       # Number of destination operands rename has renamed
-system.cpu.rename.RENAME:RunCycles          951399892                       # Number of cycles rename is running
-system.cpu.rename.RENAME:SquashCycles        29266045                       # Number of cycles rename is squashing
-system.cpu.rename.RENAME:UnblockCycles      118119949                       # Number of cycles rename is unblocking
-system.cpu.rename.RENAME:UndoneMaps         207941272                       # Number of HB maps that are undone due to squashing
-system.cpu.rename.RENAME:fp_rename_lookups           32                       # Number of floating rename lookups
-system.cpu.rename.RENAME:int_rename_lookups   4455390999                       # Number of integer rename lookups
-system.cpu.rename.RENAME:serializeStallCycles         2126                       # count of cycles rename stalled for serializing inst
-system.cpu.rename.RENAME:serializingInsts           68                       # count of serializing insts renamed
-system.cpu.rename.RENAME:skidInsts          172417007                       # count of insts added to the skid buffer
-system.cpu.rename.RENAME:tempSerializingInsts           68                       # count of temporary serializing insts renamed
-system.cpu.rob.rob_reads                   3280069639                       # The number of ROB reads
-system.cpu.rob.rob_writes                  3621261017                       # The number of ROB writes
-system.cpu.timesIdled                           45168                       # Number of times that the entire CPU went into an idle state and unscheduled itself
+system.cpu.rename.RENAME:IQFullEvents       318243703                       # Number of times rename has blocked due to IQ full
+system.cpu.rename.RENAME:IdleCycles         499996104                       # Number of cycles rename is idle
+system.cpu.rename.RENAME:LSQFullEvents      107154792                       # Number of times rename has blocked due to LSQ full
+system.cpu.rename.RENAME:ROBFullEvents             44                       # Number of times rename has blocked due to ROB full
+system.cpu.rename.RENAME:RenameLookups     5827367622                       # Number of register rename lookups that rename has made
+system.cpu.rename.RENAME:RenamedInsts      2403532061                       # Number of instructions processed by rename
+system.cpu.rename.RENAME:RenamedOperands   2403383901                       # Number of destination operands rename has renamed
+system.cpu.rename.RENAME:RunCycles          306300874                       # Number of cycles rename is running
+system.cpu.rename.RENAME:SquashCycles        99870091                       # Number of cycles rename is squashing
+system.cpu.rename.RENAME:UnblockCycles      450439326                       # Number of cycles rename is unblocking
+system.cpu.rename.RENAME:UndoneMaps         785389251                       # Number of HB maps that are undone due to squashing
+system.cpu.rename.RENAME:fp_rename_lookups           96                       # Number of floating rename lookups
+system.cpu.rename.RENAME:int_rename_lookups   5827367526                       # Number of integer rename lookups
+system.cpu.rename.RENAME:serializeStallCycles         3041                       # count of cycles rename stalled for serializing inst
+system.cpu.rename.RENAME:serializingInsts           87                       # count of serializing insts renamed
+system.cpu.rename.RENAME:skidInsts          739921776                       # count of insts added to the skid buffer
+system.cpu.rename.RENAME:tempSerializingInsts           87                       # count of temporary serializing insts renamed
+system.cpu.rob.rob_reads                   3775835718                       # The number of ROB reads
+system.cpu.rob.rob_writes                  4802062478                       # The number of ROB writes
+system.cpu.timesIdled                           45517                       # Number of times that the entire CPU went into an idle state and unscheduled itself
 system.cpu.workload.PROG:num_syscalls              48                       # Number of system calls
 
 ---------- End Simulation Statistics   ----------
index 8e006cde52d09ac69d1e9a19c21bb408acd1bd9a..31cbafe2a18b4c55c570ff9b9d6d8776574168d5 100644 (file)
@@ -488,7 +488,7 @@ type=ExeTracer
 [system.cpu.workload]
 type=LiveProcess
 cmd=mcf mcf.in
-cwd=build/X86_SE/tests/fast/long/10.mcf/x86/linux/o3-timing
+cwd=build/X86_SE/tests/opt/long/10.mcf/x86/linux/o3-timing
 egid=100
 env=
 errout=cerr
index 5d6a523698579f7a935aac04d3258d97c69c6781..41587c0af5e5405c777ded50ea4ea8bef603ebc7 100755 (executable)
@@ -5,11 +5,11 @@ The Regents of The University of Michigan
 All Rights Reserved
 
 
-M5 compiled Feb  8 2011 00:58:32
-M5 revision 705a4d351a43 7939 default qtip resforflagsstats.patch tip
-M5 started Feb  8 2011 00:58:34
+M5 compiled Feb 12 2011 02:22:23
+M5 revision 5e76f9de6972 7961 default qtip tip x86branchdetectstats.patch
+M5 started Feb 12 2011 02:22:27
 M5 executing on burrito
-command line: build/X86_SE/m5.fast -d build/X86_SE/tests/fast/long/10.mcf/x86/linux/o3-timing -re tests/run.py build/X86_SE/tests/fast/long/10.mcf/x86/linux/o3-timing
+command line: build/X86_SE/m5.opt -d build/X86_SE/tests/opt/long/10.mcf/x86/linux/o3-timing -re tests/run.py build/X86_SE/tests/opt/long/10.mcf/x86/linux/o3-timing
 Global frequency set at 1000000000000 ticks per second
 info: Entering event queue @ 0.  Starting simulation...
 
@@ -28,4 +28,4 @@ simplex iterations         : 2663
 flow value                 : 3080014995
 checksum                   : 68389
 optimal
-Exiting @ tick 137353348000 because target called exit()
+Exiting @ tick 98622214000 because target called exit()
index e6bfb767cafecea1f46f08a129537a2f37ead50a..33b45551d50c1cfa5cca89a154fce7f581fc016d 100644 (file)
@@ -1,41 +1,41 @@
 
 ---------- Begin Simulation Statistics ----------
-host_inst_rate                                 205513                       # Simulator instruction rate (inst/s)
-host_mem_usage                                 367352                       # Number of bytes of host memory used
-host_seconds                                  1353.65                       # Real time elapsed on the host
-host_tick_rate                              101468739                       # Simulator tick rate (ticks/s)
+host_inst_rate                                 133029                       # Simulator instruction rate (inst/s)
+host_mem_usage                                 371192                       # Number of bytes of host memory used
+host_seconds                                  2091.22                       # Real time elapsed on the host
+host_tick_rate                               47160241                       # Simulator tick rate (ticks/s)
 sim_freq                                 1000000000000                       # Frequency of simulated ticks
 sim_insts                                   278192519                       # Number of instructions simulated
-sim_seconds                                  0.137353                       # Number of seconds simulated
-sim_ticks                                137353348000                       # Number of ticks simulated
+sim_seconds                                  0.098622                       # Number of seconds simulated
+sim_ticks                                 98622214000                       # Number of ticks simulated
 system.cpu.BPredUnit.BTBCorrect                     0                       # Number of correct BTB predictions (this stat may not work properly.
-system.cpu.BPredUnit.BTBHits                 43044448                       # Number of BTB hits
-system.cpu.BPredUnit.BTBLookups              43605632                       # Number of BTB lookups
+system.cpu.BPredUnit.BTBHits                 44152407                       # Number of BTB hits
+system.cpu.BPredUnit.BTBLookups              44769192                       # Number of BTB lookups
 system.cpu.BPredUnit.RASInCorrect                   0                       # Number of incorrect RAS predictions.
-system.cpu.BPredUnit.condIncorrect            4328985                       # Number of conditional branches incorrect
-system.cpu.BPredUnit.condPredicted           43605708                       # Number of conditional branches predicted
-system.cpu.BPredUnit.lookups                 43605708                       # Number of BP lookups
+system.cpu.BPredUnit.condIncorrect            3292099                       # Number of conditional branches incorrect
+system.cpu.BPredUnit.condPredicted           50608102                       # Number of conditional branches predicted
+system.cpu.BPredUnit.lookups                 50608102                       # Number of BP lookups
 system.cpu.BPredUnit.usedRAS                        0                       # Number of times the RAS was used to get a target.
 system.cpu.commit.COM:branches               29309710                       # Number of branches committed
-system.cpu.commit.COM:bw_lim_events           2295915                       # number cycles where commit BW limit reached
+system.cpu.commit.COM:bw_lim_events          11603540                       # number cycles where commit BW limit reached
 system.cpu.commit.COM:bw_limited                    0                       # number of insts not committed due to BW limits
-system.cpu.commit.COM:committed_per_cycle::samples    264042401                       # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::mean     1.053590                       # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::stdev     1.542507                       # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::samples    176948364                       # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::mean     1.572168                       # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::stdev     2.280995                       # Number of insts commited each cycle
 system.cpu.commit.COM:committed_per_cycle::underflows            0      0.00%      0.00% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::0    131063071     49.64%     49.64% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::1     68068160     25.78%     75.42% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::2     28810036     10.91%     86.33% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::3     19729094      7.47%     93.80% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::4      3997193      1.51%     95.31% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::5      3201909      1.21%     96.53% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::6      5187793      1.96%     98.49% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::7      1689230      0.64%     99.13% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::8      2295915      0.87%    100.00% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::0     83964580     47.45%     47.45% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::1     36146762     20.43%     67.88% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::2     16087394      9.09%     76.97% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::3     14069173      7.95%     84.92% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::4      7224288      4.08%     89.00% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::5      2649535      1.50%     90.50% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::6      3731341      2.11%     92.61% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::7      1471751      0.83%     93.44% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::8     11603540      6.56%    100.00% # Number of insts commited each cycle
 system.cpu.commit.COM:committed_per_cycle::overflows            0      0.00%    100.00% # Number of insts commited each cycle
 system.cpu.commit.COM:committed_per_cycle::min_value            0                       # Number of insts commited each cycle
 system.cpu.commit.COM:committed_per_cycle::max_value            8                       # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::total    264042401                       # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::total    176948364                       # Number of insts commited each cycle
 system.cpu.commit.COM:count                 278192519                       # Number of instructions committed
 system.cpu.commit.COM:fp_insts                     40                       # Number of committed floating point instructions.
 system.cpu.commit.COM:function_calls                0                       # Number of function calls committed.
@@ -44,423 +44,430 @@ system.cpu.commit.COM:loads                  90779388                       # Nu
 system.cpu.commit.COM:membars                       0                       # Number of memory barriers committed
 system.cpu.commit.COM:refs                  122219139                       # Number of memory references committed
 system.cpu.commit.COM:swp_count                     0                       # Number of s/w prefetches committed
-system.cpu.commit.branchMispredicts           4328993                       # The number of times a branch was mispredicted
+system.cpu.commit.branchMispredicts           3292117                       # The number of times a branch was mispredicted
 system.cpu.commit.commitCommittedInsts      278192519                       # The number of committed instructions
 system.cpu.commit.commitNonSpecStalls             446                       # The number of times commit has been forced to stall to communicate backwards
-system.cpu.commit.commitSquashedInsts        61447181                       # The number of squashed insts skipped by commit
+system.cpu.commit.commitSquashedInsts       130955012                       # The number of squashed insts skipped by commit
 system.cpu.committedInsts                   278192519                       # Number of Instructions Simulated
 system.cpu.committedInsts_total             278192519                       # Number of Instructions Simulated
-system.cpu.cpi                               0.987470                       # CPI: Cycles Per Instruction
-system.cpu.cpi_total                         0.987470                       # CPI: Total CPI of All Threads
-system.cpu.dcache.ReadReq_accesses           78473515                       # number of ReadReq accesses(hits+misses)
-system.cpu.dcache.ReadReq_avg_miss_latency  5892.080019                       # average ReadReq miss latency
-system.cpu.dcache.ReadReq_avg_mshr_miss_latency  2802.465298                       # average ReadReq mshr miss latency
-system.cpu.dcache.ReadReq_hits               76426591                       # number of ReadReq hits
-system.cpu.dcache.ReadReq_miss_latency    12060640000                       # number of ReadReq miss cycles
-system.cpu.dcache.ReadReq_miss_rate          0.026084                       # miss rate for ReadReq accesses
-system.cpu.dcache.ReadReq_misses              2046924                       # number of ReadReq misses
-system.cpu.dcache.ReadReq_mshr_hits             76655                       # number of ReadReq MSHR hits
-system.cpu.dcache.ReadReq_mshr_miss_latency   5521610500                       # number of ReadReq MSHR miss cycles
-system.cpu.dcache.ReadReq_mshr_miss_rate     0.025107                       # mshr miss rate for ReadReq accesses
-system.cpu.dcache.ReadReq_mshr_misses         1970269                       # number of ReadReq MSHR misses
+system.cpu.cpi                               0.709021                       # CPI: Cycles Per Instruction
+system.cpu.cpi_total                         0.709021                       # CPI: Total CPI of All Threads
+system.cpu.dcache.ReadReq_accesses           69458873                       # number of ReadReq accesses(hits+misses)
+system.cpu.dcache.ReadReq_avg_miss_latency  6142.707591                       # average ReadReq miss latency
+system.cpu.dcache.ReadReq_avg_mshr_miss_latency  3039.983703                       # average ReadReq mshr miss latency
+system.cpu.dcache.ReadReq_hits               67343989                       # number of ReadReq hits
+system.cpu.dcache.ReadReq_miss_latency    12991114000                       # number of ReadReq miss cycles
+system.cpu.dcache.ReadReq_miss_rate          0.030448                       # miss rate for ReadReq accesses
+system.cpu.dcache.ReadReq_misses              2114884                       # number of ReadReq misses
+system.cpu.dcache.ReadReq_mshr_hits            142693                       # number of ReadReq MSHR hits
+system.cpu.dcache.ReadReq_mshr_miss_latency   5995428500                       # number of ReadReq MSHR miss cycles
+system.cpu.dcache.ReadReq_mshr_miss_rate     0.028394                       # mshr miss rate for ReadReq accesses
+system.cpu.dcache.ReadReq_mshr_misses         1972191                       # number of ReadReq MSHR misses
 system.cpu.dcache.WriteReq_accesses          31439751                       # number of WriteReq accesses(hits+misses)
-system.cpu.dcache.WriteReq_avg_miss_latency 21791.452056                       # average WriteReq miss latency
-system.cpu.dcache.WriteReq_avg_mshr_miss_latency 16914.293943                       # average WriteReq mshr miss latency
-system.cpu.dcache.WriteReq_hits              31282890                       # number of WriteReq hits
-system.cpu.dcache.WriteReq_miss_latency    3418228961                       # number of WriteReq miss cycles
-system.cpu.dcache.WriteReq_miss_rate         0.004989                       # miss rate for WriteReq accesses
-system.cpu.dcache.WriteReq_misses              156861                       # number of WriteReq misses
-system.cpu.dcache.WriteReq_mshr_hits            50497                       # number of WriteReq MSHR hits
-system.cpu.dcache.WriteReq_mshr_miss_latency   1799071961                       # number of WriteReq MSHR miss cycles
-system.cpu.dcache.WriteReq_mshr_miss_rate     0.003383                       # mshr miss rate for WriteReq accesses
-system.cpu.dcache.WriteReq_mshr_misses         106364                       # number of WriteReq MSHR misses
-system.cpu.dcache.avg_blocked_cycles::no_mshrs  3035.211268                       # average number of cycles each access was blocked
+system.cpu.dcache.WriteReq_avg_miss_latency 17842.235128                       # average WriteReq miss latency
+system.cpu.dcache.WriteReq_avg_mshr_miss_latency 17696.947420                       # average WriteReq mshr miss latency
+system.cpu.dcache.WriteReq_hits              31210017                       # number of WriteReq hits
+system.cpu.dcache.WriteReq_miss_latency    4098968045                       # number of WriteReq miss cycles
+system.cpu.dcache.WriteReq_miss_rate         0.007307                       # miss rate for WriteReq accesses
+system.cpu.dcache.WriteReq_misses              229734                       # number of WriteReq misses
+system.cpu.dcache.WriteReq_mshr_hits           123609                       # number of WriteReq MSHR hits
+system.cpu.dcache.WriteReq_mshr_miss_latency   1878088545                       # number of WriteReq MSHR miss cycles
+system.cpu.dcache.WriteReq_mshr_miss_rate     0.003376                       # mshr miss rate for WriteReq accesses
+system.cpu.dcache.WriteReq_mshr_misses         106125                       # number of WriteReq MSHR misses
+system.cpu.dcache.avg_blocked_cycles::no_mshrs  3358.823529                       # average number of cycles each access was blocked
 system.cpu.dcache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
-system.cpu.dcache.avg_refs                  51.867365                       # Average number of references to valid blocks.
-system.cpu.dcache.blocked::no_mshrs                71                       # number of cycles access was blocked
+system.cpu.dcache.avg_refs                  47.420176                       # Average number of references to valid blocks.
+system.cpu.dcache.blocked::no_mshrs                85                       # number of cycles access was blocked
 system.cpu.dcache.blocked::no_targets               0                       # number of cycles access was blocked
-system.cpu.dcache.blocked_cycles::no_mshrs       215500                       # number of cycles access was blocked
+system.cpu.dcache.blocked_cycles::no_mshrs       285500                       # number of cycles access was blocked
 system.cpu.dcache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.dcache.cache_copies                      0                       # number of cache copies performed
-system.cpu.dcache.demand_accesses           109913266                       # number of demand (read+write) accesses
-system.cpu.dcache.demand_avg_miss_latency  7023.765459                       # average overall miss latency
-system.cpu.dcache.demand_avg_mshr_miss_latency  3525.265399                       # average overall mshr miss latency
-system.cpu.dcache.demand_hits               107709481                       # number of demand (read+write) hits
-system.cpu.dcache.demand_miss_latency     15478868961                       # number of demand (read+write) miss cycles
-system.cpu.dcache.demand_miss_rate           0.020050                       # miss rate for demand accesses
-system.cpu.dcache.demand_misses               2203785                       # number of demand (read+write) misses
-system.cpu.dcache.demand_mshr_hits             127152                       # number of demand (read+write) MSHR hits
-system.cpu.dcache.demand_mshr_miss_latency   7320682461                       # number of demand (read+write) MSHR miss cycles
-system.cpu.dcache.demand_mshr_miss_rate      0.018893                       # mshr miss rate for demand accesses
-system.cpu.dcache.demand_mshr_misses          2076633                       # number of demand (read+write) MSHR misses
+system.cpu.dcache.demand_accesses           100898624                       # number of demand (read+write) accesses
+system.cpu.dcache.demand_avg_miss_latency  7289.068857                       # average overall miss latency
+system.cpu.dcache.demand_avg_mshr_miss_latency  3788.411890                       # average overall mshr miss latency
+system.cpu.dcache.demand_hits                98554006                       # number of demand (read+write) hits
+system.cpu.dcache.demand_miss_latency     17090082045                       # number of demand (read+write) miss cycles
+system.cpu.dcache.demand_miss_rate           0.023237                       # miss rate for demand accesses
+system.cpu.dcache.demand_misses               2344618                       # number of demand (read+write) misses
+system.cpu.dcache.demand_mshr_hits             266302                       # number of demand (read+write) MSHR hits
+system.cpu.dcache.demand_mshr_miss_latency   7873517045                       # number of demand (read+write) MSHR miss cycles
+system.cpu.dcache.demand_mshr_miss_rate      0.020598                       # mshr miss rate for demand accesses
+system.cpu.dcache.demand_mshr_misses          2078316                       # number of demand (read+write) MSHR misses
 system.cpu.dcache.fast_writes                       0                       # number of fast writes performed
 system.cpu.dcache.mshr_cap_events                   0                       # number of times MSHR cap was activated
 system.cpu.dcache.no_allocate_misses                0                       # Number of misses that were no-allocate
-system.cpu.dcache.occ_%::0                   0.994785                       # Average percentage of cache occupancy
-system.cpu.dcache.occ_blocks::0           4074.637859                       # Average occupied blocks per context
-system.cpu.dcache.overall_accesses          109913266                       # number of overall (read+write) accesses
-system.cpu.dcache.overall_avg_miss_latency  7023.765459                       # average overall miss latency
-system.cpu.dcache.overall_avg_mshr_miss_latency  3525.265399                       # average overall mshr miss latency
+system.cpu.dcache.occ_%::0                   0.994974                       # Average percentage of cache occupancy
+system.cpu.dcache.occ_blocks::0           4075.414607                       # Average occupied blocks per context
+system.cpu.dcache.overall_accesses          100898624                       # number of overall (read+write) accesses
+system.cpu.dcache.overall_avg_miss_latency  7289.068857                       # average overall miss latency
+system.cpu.dcache.overall_avg_mshr_miss_latency  3788.411890                       # average overall mshr miss latency
 system.cpu.dcache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
-system.cpu.dcache.overall_hits              107709481                       # number of overall hits
-system.cpu.dcache.overall_miss_latency    15478868961                       # number of overall miss cycles
-system.cpu.dcache.overall_miss_rate          0.020050                       # miss rate for overall accesses
-system.cpu.dcache.overall_misses              2203785                       # number of overall misses
-system.cpu.dcache.overall_mshr_hits            127152                       # number of overall MSHR hits
-system.cpu.dcache.overall_mshr_miss_latency   7320682461                       # number of overall MSHR miss cycles
-system.cpu.dcache.overall_mshr_miss_rate     0.018893                       # mshr miss rate for overall accesses
-system.cpu.dcache.overall_mshr_misses         2076633                       # number of overall MSHR misses
+system.cpu.dcache.overall_hits               98554006                       # number of overall hits
+system.cpu.dcache.overall_miss_latency    17090082045                       # number of overall miss cycles
+system.cpu.dcache.overall_miss_rate          0.023237                       # miss rate for overall accesses
+system.cpu.dcache.overall_misses              2344618                       # number of overall misses
+system.cpu.dcache.overall_mshr_hits            266302                       # number of overall MSHR hits
+system.cpu.dcache.overall_mshr_miss_latency   7873517045                       # number of overall MSHR miss cycles
+system.cpu.dcache.overall_mshr_miss_rate     0.020598                       # mshr miss rate for overall accesses
+system.cpu.dcache.overall_mshr_misses         2078316                       # number of overall MSHR misses
 system.cpu.dcache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
 system.cpu.dcache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.dcache.replacements                2072537                       # number of replacements
-system.cpu.dcache.sampled_refs                2076633                       # Sample count of references to valid blocks.
+system.cpu.dcache.replacements                2074218                       # number of replacements
+system.cpu.dcache.sampled_refs                2078314                       # Sample count of references to valid blocks.
 system.cpu.dcache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
-system.cpu.dcache.tagsinuse               4074.637859                       # Cycle average of tags in use
-system.cpu.dcache.total_refs                107709481                       # Total number of references to valid blocks.
-system.cpu.dcache.warmup_cycle            54571641000                       # Cycle when the warmup percentage was hit.
-system.cpu.dcache.writebacks                  1440067                       # number of writebacks
-system.cpu.decode.DECODE:BlockedCycles        1078320                       # Number of cycles decode is blocked
-system.cpu.decode.DECODE:DecodedInsts       365035506                       # Number of instructions handled by decode
-system.cpu.decode.DECODE:IdleCycles          68035567                       # Number of cycles decode is idle
-system.cpu.decode.DECODE:RunCycles          194761019                       # Number of cycles decode is running
-system.cpu.decode.DECODE:SquashCycles        10324266                       # Number of cycles decode is squashing
-system.cpu.decode.DECODE:UnblockCycles         167495                       # Number of cycles decode is unblocking
-system.cpu.fetch.Branches                    43605708                       # Number of branches that fetch encountered
-system.cpu.fetch.CacheLines                  29060081                       # Number of cache lines fetched
-system.cpu.fetch.Cycles                     205057262                       # Number of cycles fetch has run and was not squashing or blocked
-system.cpu.fetch.IcacheSquashes                469074                       # Number of outstanding Icache misses that were squashed
-system.cpu.fetch.Insts                      209709437                       # Number of instructions fetch has processed
-system.cpu.fetch.MiscStallCycles                   11                       # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs
-system.cpu.fetch.SquashCycles                 4648806                       # Number of cycles fetch has spent squashing
-system.cpu.fetch.branchRate                  0.158736                       # Number of branch fetches per cycle
-system.cpu.fetch.icacheStallCycles           29060081                       # Number of cycles fetch is stalled on an Icache miss
-system.cpu.fetch.predictedBranches           43044448                       # Number of branches that fetch has predicted taken
-system.cpu.fetch.rate                        0.763394                       # Number of inst fetches per cycle
-system.cpu.fetch.rateDist::samples          274366667                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::mean              1.362439                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::stdev             1.220161                       # Number of instructions fetched each cycle (Total)
+system.cpu.dcache.tagsinuse               4075.414607                       # Cycle average of tags in use
+system.cpu.dcache.total_refs                 98554015                       # Total number of references to valid blocks.
+system.cpu.dcache.warmup_cycle            40655663000                       # Cycle when the warmup percentage was hit.
+system.cpu.dcache.writebacks                  1442059                       # number of writebacks
+system.cpu.decode.DECODE:BlockedCycles       21837286                       # Number of cycles decode is blocked
+system.cpu.decode.DECODE:DecodedInsts       443283148                       # Number of instructions handled by decode
+system.cpu.decode.DECODE:IdleCycles          77587406                       # Number of cycles decode is idle
+system.cpu.decode.DECODE:RunCycles           75762450                       # Number of cycles decode is running
+system.cpu.decode.DECODE:SquashCycles        19022168                       # Number of cycles decode is squashing
+system.cpu.decode.DECODE:UnblockCycles        1761222                       # Number of cycles decode is unblocking
+system.cpu.fetch.Branches                    50608102                       # Number of branches that fetch encountered
+system.cpu.fetch.CacheLines                  34652495                       # Number of cache lines fetched
+system.cpu.fetch.Cycles                      82344495                       # Number of cycles fetch has run and was not squashing or blocked
+system.cpu.fetch.IcacheSquashes                326035                       # Number of outstanding Icache misses that were squashed
+system.cpu.fetch.Insts                      259681215                       # Number of instructions fetch has processed
+system.cpu.fetch.MiscStallCycles                   35                       # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs
+system.cpu.fetch.SquashCycles                 3883025                       # Number of cycles fetch has spent squashing
+system.cpu.fetch.branchRate                  0.256576                       # Number of branch fetches per cycle
+system.cpu.fetch.icacheStallCycles           34652495                       # Number of cycles fetch is stalled on an Icache miss
+system.cpu.fetch.predictedBranches           44152407                       # Number of branches that fetch has predicted taken
+system.cpu.fetch.rate                        1.316545                       # Number of inst fetches per cycle
+system.cpu.fetch.rateDist::samples          195970532                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::mean              2.323843                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::stdev             3.188074                       # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::underflows               0      0.00%      0.00% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::0                 75544313     27.53%     27.53% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::1                 99907030     36.41%     63.95% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::2                 38310109     13.96%     77.91% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::3                 50324165     18.34%     96.25% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::4                  5339949      1.95%     98.20% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::5                  4719664      1.72%     99.92% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::6                   210294      0.08%    100.00% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::7                      928      0.00%    100.00% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::8                    10215      0.00%    100.00% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::0                116145210     59.27%     59.27% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::1                  6750085      3.44%     62.71% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::2                  3016102      1.54%     64.25% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::3                  8362073      4.27%     68.52% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::4                  7646936      3.90%     72.42% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::5                  6348764      3.24%     75.66% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::6                  9080088      4.63%     80.29% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::7                  8246058      4.21%     84.50% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::8                 30375216     15.50%    100.00% # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::overflows                0      0.00%    100.00% # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::min_value                0                       # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::max_value                8                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::total            274366667                       # Number of instructions fetched each cycle (Total)
-system.cpu.fp_regfile_reads                        46                       # number of floating regfile reads
-system.cpu.fp_regfile_writes                       32                       # number of floating regfile writes
-system.cpu.icache.ReadReq_accesses           29060081                       # number of ReadReq accesses(hits+misses)
-system.cpu.icache.ReadReq_avg_miss_latency 37083.333333                       # average ReadReq miss latency
-system.cpu.icache.ReadReq_avg_mshr_miss_latency 35353.296703                       # average ReadReq mshr miss latency
-system.cpu.icache.ReadReq_hits               29059007                       # number of ReadReq hits
-system.cpu.icache.ReadReq_miss_latency       39827500                       # number of ReadReq miss cycles
-system.cpu.icache.ReadReq_miss_rate          0.000037                       # miss rate for ReadReq accesses
-system.cpu.icache.ReadReq_misses                 1074                       # number of ReadReq misses
-system.cpu.icache.ReadReq_mshr_hits               164                       # number of ReadReq MSHR hits
-system.cpu.icache.ReadReq_mshr_miss_latency     32171500                       # number of ReadReq MSHR miss cycles
-system.cpu.icache.ReadReq_mshr_miss_rate     0.000031                       # mshr miss rate for ReadReq accesses
-system.cpu.icache.ReadReq_mshr_misses             910                       # number of ReadReq MSHR misses
+system.cpu.fetch.rateDist::total            195970532                       # Number of instructions fetched each cycle (Total)
+system.cpu.fp_regfile_reads                        75                       # number of floating regfile reads
+system.cpu.fp_regfile_writes                       41                       # number of floating regfile writes
+system.cpu.icache.ReadReq_accesses           34652495                       # number of ReadReq accesses(hits+misses)
+system.cpu.icache.ReadReq_avg_miss_latency 35675.242356                       # average ReadReq miss latency
+system.cpu.icache.ReadReq_avg_mshr_miss_latency 35201.684836                       # average ReadReq mshr miss latency
+system.cpu.icache.ReadReq_hits               34651154                       # number of ReadReq hits
+system.cpu.icache.ReadReq_miss_latency       47840500                       # number of ReadReq miss cycles
+system.cpu.icache.ReadReq_miss_rate          0.000039                       # miss rate for ReadReq accesses
+system.cpu.icache.ReadReq_misses                 1341                       # number of ReadReq misses
+system.cpu.icache.ReadReq_mshr_hits               332                       # number of ReadReq MSHR hits
+system.cpu.icache.ReadReq_mshr_miss_latency     35518500                       # number of ReadReq MSHR miss cycles
+system.cpu.icache.ReadReq_mshr_miss_rate     0.000029                       # mshr miss rate for ReadReq accesses
+system.cpu.icache.ReadReq_mshr_misses            1009                       # number of ReadReq MSHR misses
 system.cpu.icache.avg_blocked_cycles::no_mshrs     no_value                       # average number of cycles each access was blocked
 system.cpu.icache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
-system.cpu.icache.avg_refs               31932.974725                       # Average number of references to valid blocks.
+system.cpu.icache.avg_refs               34376.144841                       # Average number of references to valid blocks.
 system.cpu.icache.blocked::no_mshrs                 0                       # number of cycles access was blocked
 system.cpu.icache.blocked::no_targets               0                       # number of cycles access was blocked
 system.cpu.icache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.icache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.icache.cache_copies                      0                       # number of cache copies performed
-system.cpu.icache.demand_accesses            29060081                       # number of demand (read+write) accesses
-system.cpu.icache.demand_avg_miss_latency 37083.333333                       # average overall miss latency
-system.cpu.icache.demand_avg_mshr_miss_latency 35353.296703                       # average overall mshr miss latency
-system.cpu.icache.demand_hits                29059007                       # number of demand (read+write) hits
-system.cpu.icache.demand_miss_latency        39827500                       # number of demand (read+write) miss cycles
-system.cpu.icache.demand_miss_rate           0.000037                       # miss rate for demand accesses
-system.cpu.icache.demand_misses                  1074                       # number of demand (read+write) misses
-system.cpu.icache.demand_mshr_hits                164                       # number of demand (read+write) MSHR hits
-system.cpu.icache.demand_mshr_miss_latency     32171500                       # number of demand (read+write) MSHR miss cycles
-system.cpu.icache.demand_mshr_miss_rate      0.000031                       # mshr miss rate for demand accesses
-system.cpu.icache.demand_mshr_misses              910                       # number of demand (read+write) MSHR misses
+system.cpu.icache.demand_accesses            34652495                       # number of demand (read+write) accesses
+system.cpu.icache.demand_avg_miss_latency 35675.242356                       # average overall miss latency
+system.cpu.icache.demand_avg_mshr_miss_latency 35201.684836                       # average overall mshr miss latency
+system.cpu.icache.demand_hits                34651154                       # number of demand (read+write) hits
+system.cpu.icache.demand_miss_latency        47840500                       # number of demand (read+write) miss cycles
+system.cpu.icache.demand_miss_rate           0.000039                       # miss rate for demand accesses
+system.cpu.icache.demand_misses                  1341                       # number of demand (read+write) misses
+system.cpu.icache.demand_mshr_hits                332                       # number of demand (read+write) MSHR hits
+system.cpu.icache.demand_mshr_miss_latency     35518500                       # number of demand (read+write) MSHR miss cycles
+system.cpu.icache.demand_mshr_miss_rate      0.000029                       # mshr miss rate for demand accesses
+system.cpu.icache.demand_mshr_misses             1009                       # number of demand (read+write) MSHR misses
 system.cpu.icache.fast_writes                       0                       # number of fast writes performed
 system.cpu.icache.mshr_cap_events                   0                       # number of times MSHR cap was activated
 system.cpu.icache.no_allocate_misses                0                       # Number of misses that were no-allocate
-system.cpu.icache.occ_%::0                   0.357987                       # Average percentage of cache occupancy
-system.cpu.icache.occ_blocks::0            733.158070                       # Average occupied blocks per context
-system.cpu.icache.overall_accesses           29060081                       # number of overall (read+write) accesses
-system.cpu.icache.overall_avg_miss_latency 37083.333333                       # average overall miss latency
-system.cpu.icache.overall_avg_mshr_miss_latency 35353.296703                       # average overall mshr miss latency
+system.cpu.icache.occ_%::0                   0.392466                       # Average percentage of cache occupancy
+system.cpu.icache.occ_blocks::0            803.770978                       # Average occupied blocks per context
+system.cpu.icache.overall_accesses           34652495                       # number of overall (read+write) accesses
+system.cpu.icache.overall_avg_miss_latency 35675.242356                       # average overall miss latency
+system.cpu.icache.overall_avg_mshr_miss_latency 35201.684836                       # average overall mshr miss latency
 system.cpu.icache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
-system.cpu.icache.overall_hits               29059007                       # number of overall hits
-system.cpu.icache.overall_miss_latency       39827500                       # number of overall miss cycles
-system.cpu.icache.overall_miss_rate          0.000037                       # miss rate for overall accesses
-system.cpu.icache.overall_misses                 1074                       # number of overall misses
-system.cpu.icache.overall_mshr_hits               164                       # number of overall MSHR hits
-system.cpu.icache.overall_mshr_miss_latency     32171500                       # number of overall MSHR miss cycles
-system.cpu.icache.overall_mshr_miss_rate     0.000031                       # mshr miss rate for overall accesses
-system.cpu.icache.overall_mshr_misses             910                       # number of overall MSHR misses
+system.cpu.icache.overall_hits               34651154                       # number of overall hits
+system.cpu.icache.overall_miss_latency       47840500                       # number of overall miss cycles
+system.cpu.icache.overall_miss_rate          0.000039                       # miss rate for overall accesses
+system.cpu.icache.overall_misses                 1341                       # number of overall misses
+system.cpu.icache.overall_mshr_hits               332                       # number of overall MSHR hits
+system.cpu.icache.overall_mshr_miss_latency     35518500                       # number of overall MSHR miss cycles
+system.cpu.icache.overall_mshr_miss_rate     0.000029                       # mshr miss rate for overall accesses
+system.cpu.icache.overall_mshr_misses            1009                       # number of overall MSHR misses
 system.cpu.icache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
 system.cpu.icache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.icache.replacements                     37                       # number of replacements
-system.cpu.icache.sampled_refs                    910                       # Sample count of references to valid blocks.
+system.cpu.icache.replacements                     60                       # number of replacements
+system.cpu.icache.sampled_refs                   1008                       # Sample count of references to valid blocks.
 system.cpu.icache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
-system.cpu.icache.tagsinuse                733.158070                       # Cycle average of tags in use
-system.cpu.icache.total_refs                 29059007                       # Total number of references to valid blocks.
+system.cpu.icache.tagsinuse                803.770978                       # Cycle average of tags in use
+system.cpu.icache.total_refs                 34651154                       # Total number of references to valid blocks.
 system.cpu.icache.warmup_cycle                      0                       # Cycle when the warmup percentage was hit.
 system.cpu.icache.writebacks                        0                       # number of writebacks
-system.cpu.idleCycles                          340030                       # Total number of cycles that the CPU has spent unscheduled due to idling
-system.cpu.iew.EXEC:branches                 31975279                       # Number of branches executed
+system.cpu.idleCycles                         1273897                       # Total number of cycles that the CPU has spent unscheduled due to idling
+system.cpu.iew.EXEC:branches                 33755681                       # Number of branches executed
 system.cpu.iew.EXEC:nop                             0                       # number of nop insts executed
-system.cpu.iew.EXEC:rate                     1.141834                       # Inst execution rate
-system.cpu.iew.EXEC:refs                    137788104                       # number of memory reference insts executed
-system.cpu.iew.EXEC:stores                   32893684                       # Number of stores executed
+system.cpu.iew.EXEC:rate                     1.719732                       # Inst execution rate
+system.cpu.iew.EXEC:refs                    143271490                       # number of memory reference insts executed
+system.cpu.iew.EXEC:stores                   33964004                       # Number of stores executed
 system.cpu.iew.EXEC:swp                             0                       # number of swp insts executed
-system.cpu.iew.WB:consumers                 268477654                       # num instructions consuming a value
-system.cpu.iew.WB:count                     310858537                       # cumulative count of insts written-back
-system.cpu.iew.WB:fanout                     0.831176                       # average fanout of values written-back
+system.cpu.iew.WB:consumers                 356152066                       # num instructions consuming a value
+system.cpu.iew.WB:count                     334303723                       # cumulative count of insts written-back
+system.cpu.iew.WB:fanout                     0.713943                       # average fanout of values written-back
 system.cpu.iew.WB:penalized                         0                       # number of instrctions required to write to 'other' IQ
 system.cpu.iew.WB:penalized_rate                    0                       # fraction of instructions written-back that wrote to 'other' IQ
-system.cpu.iew.WB:producers                 223152216                       # num instructions producing a value
-system.cpu.iew.WB:rate                       1.131602                       # insts written-back per cycle
-system.cpu.iew.WB:sent                      311298125                       # cumulative count of insts sent to commit
-system.cpu.iew.branchMispredicts              5432801                       # Number of branch mispredicts detected at execute
-system.cpu.iew.iewBlockCycles                  434257                       # Number of cycles IEW is blocking
-system.cpu.iew.iewDispLoadInsts             113153901                       # Number of dispatched load instructions
-system.cpu.iew.iewDispNonSpecInsts                453                       # Number of dispatched non-speculative instructions
-system.cpu.iew.iewDispSquashedInsts           3329994                       # Number of squashed instructions skipped by dispatch
-system.cpu.iew.iewDispStoreInsts             36225707                       # Number of dispatched store instructions
-system.cpu.iew.iewDispatchedInsts           339638144                       # Number of instructions dispatched to IQ
-system.cpu.iew.iewExecLoadInsts             104894420                       # Number of load instructions executed
-system.cpu.iew.iewExecSquashedInsts           7540683                       # Number of squashed instructions skipped in execute
-system.cpu.iew.iewExecutedInsts             313669330                       # Number of executed instructions
-system.cpu.iew.iewIQFullEvents                   1132                       # Number of times the IQ has become full, causing a stall
+system.cpu.iew.WB:producers                 254272214                       # num instructions producing a value
+system.cpu.iew.WB:rate                       1.694870                       # insts written-back per cycle
+system.cpu.iew.WB:sent                      336664522                       # cumulative count of insts sent to commit
+system.cpu.iew.branchMispredicts              3987132                       # Number of branch mispredicts detected at execute
+system.cpu.iew.iewBlockCycles                  754395                       # Number of cycles IEW is blocking
+system.cpu.iew.iewDispLoadInsts             138835558                       # Number of dispatched load instructions
+system.cpu.iew.iewDispNonSpecInsts                465                       # Number of dispatched non-speculative instructions
+system.cpu.iew.iewDispSquashedInsts            663120                       # Number of squashed instructions skipped by dispatch
+system.cpu.iew.iewDispStoreInsts             42750154                       # Number of dispatched store instructions
+system.cpu.iew.iewDispatchedInsts           409142439                       # Number of instructions dispatched to IQ
+system.cpu.iew.iewExecLoadInsts             109307486                       # Number of load instructions executed
+system.cpu.iew.iewExecSquashedInsts           6572046                       # Number of squashed instructions skipped in execute
+system.cpu.iew.iewExecutedInsts             339207523                       # Number of executed instructions
+system.cpu.iew.iewIQFullEvents                   2275                       # Number of times the IQ has become full, causing a stall
 system.cpu.iew.iewIdleCycles                        0                       # Number of cycles IEW is idle
-system.cpu.iew.iewLSQFullEvents                 39972                       # Number of times the LSQ has become full, causing a stall
-system.cpu.iew.iewSquashCycles               10324266                       # Number of cycles IEW is squashing
-system.cpu.iew.iewUnblockCycles                 75875                       # Number of cycles IEW is unblocking
+system.cpu.iew.iewLSQFullEvents                 78833                       # Number of times the LSQ has become full, causing a stall
+system.cpu.iew.iewSquashCycles               19022168                       # Number of cycles IEW is squashing
+system.cpu.iew.iewUnblockCycles                104797                       # Number of cycles IEW is unblocking
 system.cpu.iew.lsq.thread.0.blockedLoads            0                       # Number of blocked loads due to partial load-store forwarding
-system.cpu.iew.lsq.thread.0.cacheBlocked         6157                       # Number of times an access to memory failed due to the cache being blocked
-system.cpu.iew.lsq.thread.0.forwLoads        26233968                       # Number of loads that had data forwarded from stores
-system.cpu.iew.lsq.thread.0.ignoredResponses        75546                       # Number of memory responses ignored because the instruction is squashed
+system.cpu.iew.lsq.thread.0.cacheBlocked        14565                       # Number of times an access to memory failed due to the cache being blocked
+system.cpu.iew.lsq.thread.0.forwLoads        39666706                       # Number of loads that had data forwarded from stores
+system.cpu.iew.lsq.thread.0.ignoredResponses        30063                       # Number of memory responses ignored because the instruction is squashed
 system.cpu.iew.lsq.thread.0.invAddrLoads            0                       # Number of loads ignored due to an invalid address
 system.cpu.iew.lsq.thread.0.invAddrSwpfs            0                       # Number of software prefetches ignored due to an invalid address
-system.cpu.iew.lsq.thread.0.memOrderViolation       373621                       # Number of memory ordering violations
-system.cpu.iew.lsq.thread.0.rescheduledLoads         2668                       # Number of loads that were rescheduled
-system.cpu.iew.lsq.thread.0.squashedLoads     22374513                       # Number of loads squashed
-system.cpu.iew.lsq.thread.0.squashedStores      4785956                       # Number of stores squashed
-system.cpu.iew.memOrderViolationEvents         373621                       # Number of memory order violations
-system.cpu.iew.predictedNotTakenIncorrect         7861                       # Number of branches that were predicted not taken incorrectly
-system.cpu.iew.predictedTakenIncorrect        5424940                       # Number of branches that were predicted taken incorrectly
-system.cpu.int_regfile_reads                553724199                       # number of integer regfile reads
-system.cpu.int_regfile_writes               279097661                       # number of integer regfile writes
-system.cpu.ipc                               1.012689                       # IPC: Instructions Per Cycle
-system.cpu.ipc_total                         1.012689                       # IPC: Total IPC of All Threads
-system.cpu.iq.ISSUE:FU_type_0::No_OpClass        16700      0.01%      0.01% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::IntAlu       181103840     56.38%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::IntMult              0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::IntDiv               0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatAdd            15      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatCmp             0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatCvt             0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatMult            0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatDiv             0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatSqrt            0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdAdd              0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdAddAcc            0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdAlu              0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdCmp              0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdCvt              0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdMisc             0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdMult             0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdMultAcc            0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdShift            0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdShiftAcc            0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdSqrt             0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatAdd            0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatAlu            0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatCmp            0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatCvt            0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatDiv            0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatMisc            0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatMult            0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatMultAcc            0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatSqrt            0      0.00%     56.39% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::MemRead      106927667     33.29%     89.68% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::MemWrite      33161791     10.32%    100.00% # Type of FU issued
+system.cpu.iew.lsq.thread.0.memOrderViolation      1469253                       # Number of memory ordering violations
+system.cpu.iew.lsq.thread.0.rescheduledLoads         2742                       # Number of loads that were rescheduled
+system.cpu.iew.lsq.thread.0.squashedLoads     48056170                       # Number of loads squashed
+system.cpu.iew.lsq.thread.0.squashedStores     11310403                       # Number of stores squashed
+system.cpu.iew.memOrderViolationEvents        1469253                       # Number of memory order violations
+system.cpu.iew.predictedNotTakenIncorrect       865481                       # Number of branches that were predicted not taken incorrectly
+system.cpu.iew.predictedTakenIncorrect        3121651                       # Number of branches that were predicted taken incorrectly
+system.cpu.int_regfile_reads                577634708                       # number of integer regfile reads
+system.cpu.int_regfile_writes               302216415                       # number of integer regfile writes
+system.cpu.ipc                               1.410395                       # IPC: Instructions Per Cycle
+system.cpu.ipc_total                         1.410395                       # IPC: Total IPC of All Threads
+system.cpu.iq.ISSUE:FU_type_0::No_OpClass        16702      0.00%      0.00% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::IntAlu       200471700     57.98%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::IntMult              0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::IntDiv               0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatAdd            15      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatCmp             0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatCvt             0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatMult            0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatDiv             0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatSqrt            0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdAdd              0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdAddAcc            0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdAlu              0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdCmp              0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdCvt              0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdMisc             0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdMult             0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdMultAcc            0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdShift            0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdShiftAcc            0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdSqrt             0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatAdd            0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatAlu            0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatCmp            0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatCvt            0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatDiv            0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatMisc            0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatMult            0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatMultAcc            0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatSqrt            0      0.00%     57.98% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::MemRead      110857049     32.06%     90.04% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::MemWrite      34434103      9.96%    100.00% # Type of FU issued
 system.cpu.iq.ISSUE:FU_type_0::IprAccess            0      0.00%    100.00% # Type of FU issued
 system.cpu.iq.ISSUE:FU_type_0::InstPrefetch            0      0.00%    100.00% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::total        321210013                       # Type of FU issued
-system.cpu.iq.ISSUE:fu_busy_cnt               1288241                       # FU busy when requested
-system.cpu.iq.ISSUE:fu_busy_rate             0.004011                       # FU busy rate (busy events/executed inst)
+system.cpu.iq.ISSUE:FU_type_0::total        345779569                       # Type of FU issued
+system.cpu.iq.ISSUE:fu_busy_cnt               4109732                       # FU busy when requested
+system.cpu.iq.ISSUE:fu_busy_rate             0.011885                       # FU busy rate (busy events/executed inst)
 system.cpu.iq.ISSUE:fu_full::No_OpClass             0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::IntAlu                 1      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::IntMult                0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::IntDiv                 0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatAdd               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatCmp               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatCvt               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatMult              0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatDiv               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatSqrt              0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdAdd                0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdAddAcc             0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdAlu                0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdCmp                0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdCvt                0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdMisc               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdMult               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdMultAcc            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdShift              0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdShiftAcc            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdSqrt               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatAdd            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatAlu            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatCmp            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatCvt            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatDiv            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatMisc            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatMult            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatMultAcc            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatSqrt            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::MemRead          1088765     84.52%     84.52% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::MemWrite          199475     15.48%    100.00% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::IntAlu             26819      0.65%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::IntMult                0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::IntDiv                 0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatAdd               0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatCmp               0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatCvt               0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatMult              0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatDiv               0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatSqrt              0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdAdd                0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdAddAcc             0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdAlu                0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdCmp                0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdCvt                0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdMisc               0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdMult               0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdMultAcc            0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdShift              0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdShiftAcc            0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdSqrt               0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatAdd            0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatAlu            0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatCmp            0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatCvt            0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatDiv            0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatMisc            0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatMult            0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatMultAcc            0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatSqrt            0      0.00%      0.65% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::MemRead          3817756     92.90%     93.55% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::MemWrite          265157      6.45%    100.00% # attempts to use FU when none available
 system.cpu.iq.ISSUE:fu_full::IprAccess              0      0.00%    100.00% # attempts to use FU when none available
 system.cpu.iq.ISSUE:fu_full::InstPrefetch            0      0.00%    100.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:issued_per_cycle::samples    274366667                       # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::mean     1.170733                       # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::stdev     1.057250                       # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::samples    195970532                       # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::mean     1.764447                       # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::stdev     1.745109                       # Number of insts issued each cycle
 system.cpu.iq.ISSUE:issued_per_cycle::underflows            0      0.00%      0.00% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::0      85009751     30.98%     30.98% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::1      94999011     34.62%     65.61% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::2      64668868     23.57%     89.18% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::3      24623631      8.97%     98.15% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::4       3181639      1.16%     99.31% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::5       1035626      0.38%     99.69% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::6        839375      0.31%    100.00% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::7          8691      0.00%    100.00% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::8            75      0.00%    100.00% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::0      63955785     32.64%     32.64% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::1      38956843     19.88%     52.51% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::2      30997952     15.82%     68.33% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::3      27554899     14.06%     82.39% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::4      19728653     10.07%     92.46% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::5       8783605      4.48%     96.94% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::6       3191043      1.63%     98.57% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::7       2230786      1.14%     99.71% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::8        570966      0.29%    100.00% # Number of insts issued each cycle
 system.cpu.iq.ISSUE:issued_per_cycle::overflows            0      0.00%    100.00% # Number of insts issued each cycle
 system.cpu.iq.ISSUE:issued_per_cycle::min_value            0                       # Number of insts issued each cycle
 system.cpu.iq.ISSUE:issued_per_cycle::max_value            8                       # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::total    274366667                       # Number of insts issued each cycle
-system.cpu.iq.ISSUE:rate                     1.169284                       # Inst issue rate
-system.cpu.iq.fp_alu_accesses                      58                       # Number of floating point alu accesses
-system.cpu.iq.fp_inst_queue_reads                 116                       # Number of floating instruction queue reads
-system.cpu.iq.fp_inst_queue_wakeup_accesses           52                       # Number of floating instruction queue wakeup accesses
-system.cpu.iq.fp_inst_queue_writes                102                       # Number of floating instruction queue writes
-system.cpu.iq.int_alu_accesses              322481496                       # Number of integer alu accesses
-system.cpu.iq.int_inst_queue_reads          918075310                       # Number of integer instruction queue reads
-system.cpu.iq.int_inst_queue_wakeup_accesses    310858485                       # Number of integer instruction queue wakeup accesses
-system.cpu.iq.int_inst_queue_writes         400954774                       # Number of integer instruction queue writes
-system.cpu.iq.iqInstsAdded                  339637691                       # Number of instructions added to the IQ (excludes non-spec)
-system.cpu.iq.iqInstsIssued                 321210013                       # Number of instructions issued
-system.cpu.iq.iqNonSpecInstsAdded                 453                       # Number of non-speculative instructions added to the IQ
-system.cpu.iq.iqSquashedInstsExamined        61001038                       # Number of squashed instructions iterated over during squash; mainly for profiling
-system.cpu.iq.iqSquashedInstsIssued               492                       # Number of squashed instructions issued
-system.cpu.iq.iqSquashedNonSpecRemoved              7                       # Number of squashed non-spec instructions that were removed
-system.cpu.iq.iqSquashedOperandsExamined     74571352                       # Number of squashed operands that are examined and possibly removed from graph
-system.cpu.l2cache.ReadExReq_accesses          106364                       # number of ReadExReq accesses(hits+misses)
-system.cpu.l2cache.ReadExReq_avg_miss_latency 34222.852226                       # average ReadExReq miss latency
-system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31038.534987                       # average ReadExReq mshr miss latency
-system.cpu.l2cache.ReadExReq_hits               63948                       # number of ReadExReq hits
-system.cpu.l2cache.ReadExReq_miss_latency   1451596500                       # number of ReadExReq miss cycles
-system.cpu.l2cache.ReadExReq_miss_rate       0.398782                       # miss rate for ReadExReq accesses
-system.cpu.l2cache.ReadExReq_misses             42416                       # number of ReadExReq misses
-system.cpu.l2cache.ReadExReq_mshr_miss_latency   1316530500                       # number of ReadExReq MSHR miss cycles
-system.cpu.l2cache.ReadExReq_mshr_miss_rate     0.398782                       # mshr miss rate for ReadExReq accesses
-system.cpu.l2cache.ReadExReq_mshr_misses        42416                       # number of ReadExReq MSHR misses
-system.cpu.l2cache.ReadReq_accesses           1971179                       # number of ReadReq accesses(hits+misses)
-system.cpu.l2cache.ReadReq_avg_miss_latency 34221.265286                       # average ReadReq miss latency
-system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31012.315915                       # average ReadReq mshr miss latency
-system.cpu.l2cache.ReadReq_hits               1936752                       # number of ReadReq hits
-system.cpu.l2cache.ReadReq_miss_latency    1178135500                       # number of ReadReq miss cycles
-system.cpu.l2cache.ReadReq_miss_rate         0.017465                       # miss rate for ReadReq accesses
-system.cpu.l2cache.ReadReq_misses               34427                       # number of ReadReq misses
-system.cpu.l2cache.ReadReq_mshr_miss_latency   1067661000                       # number of ReadReq MSHR miss cycles
-system.cpu.l2cache.ReadReq_mshr_miss_rate     0.017465                       # mshr miss rate for ReadReq accesses
-system.cpu.l2cache.ReadReq_mshr_misses          34427                       # number of ReadReq MSHR misses
-system.cpu.l2cache.Writeback_accesses         1440067                       # number of Writeback accesses(hits+misses)
-system.cpu.l2cache.Writeback_hits             1440067                       # number of Writeback hits
-system.cpu.l2cache.avg_blocked_cycles::no_mshrs  1272.727273                       # average number of cycles each access was blocked
+system.cpu.iq.ISSUE:issued_per_cycle::total    195970532                       # Number of insts issued each cycle
+system.cpu.iq.ISSUE:rate                     1.753051                       # Inst issue rate
+system.cpu.iq.fp_alu_accesses                     110                       # Number of floating point alu accesses
+system.cpu.iq.fp_inst_queue_reads                 224                       # Number of floating instruction queue reads
+system.cpu.iq.fp_inst_queue_wakeup_accesses           83                       # Number of floating instruction queue wakeup accesses
+system.cpu.iq.fp_inst_queue_writes                263                       # Number of floating instruction queue writes
+system.cpu.iq.int_alu_accesses              349872489                       # Number of integer alu accesses
+system.cpu.iq.int_inst_queue_reads          891669703                       # Number of integer instruction queue reads
+system.cpu.iq.int_inst_queue_wakeup_accesses    334303640                       # Number of integer instruction queue wakeup accesses
+system.cpu.iq.int_inst_queue_writes         540919004                       # Number of integer instruction queue writes
+system.cpu.iq.iqInstsAdded                  409141974                       # Number of instructions added to the IQ (excludes non-spec)
+system.cpu.iq.iqInstsIssued                 345779569                       # Number of instructions issued
+system.cpu.iq.iqNonSpecInstsAdded                 465                       # Number of non-speculative instructions added to the IQ
+system.cpu.iq.iqSquashedInstsExamined       130872312                       # Number of squashed instructions iterated over during squash; mainly for profiling
+system.cpu.iq.iqSquashedInstsIssued             30525                       # Number of squashed instructions issued
+system.cpu.iq.iqSquashedNonSpecRemoved             19                       # Number of squashed non-spec instructions that were removed
+system.cpu.iq.iqSquashedOperandsExamined    221868127                       # Number of squashed operands that are examined and possibly removed from graph
+system.cpu.l2cache.ReadExReq_accesses          106126                       # number of ReadExReq accesses(hits+misses)
+system.cpu.l2cache.ReadExReq_avg_miss_latency 34139.167845                       # average ReadExReq miss latency
+system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31050.412541                       # average ReadExReq mshr miss latency
+system.cpu.l2cache.ReadExReq_hits               63706                       # number of ReadExReq hits
+system.cpu.l2cache.ReadExReq_miss_latency   1448183500                       # number of ReadExReq miss cycles
+system.cpu.l2cache.ReadExReq_miss_rate       0.399714                       # miss rate for ReadExReq accesses
+system.cpu.l2cache.ReadExReq_misses             42420                       # number of ReadExReq misses
+system.cpu.l2cache.ReadExReq_mshr_miss_latency   1317158500                       # number of ReadExReq MSHR miss cycles
+system.cpu.l2cache.ReadExReq_mshr_miss_rate     0.399714                       # mshr miss rate for ReadExReq accesses
+system.cpu.l2cache.ReadExReq_mshr_misses        42420                       # number of ReadExReq MSHR misses
+system.cpu.l2cache.ReadReq_accesses           1973197                       # number of ReadReq accesses(hits+misses)
+system.cpu.l2cache.ReadReq_avg_miss_latency 34279.521718                       # average ReadReq miss latency
+system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31013.978995                       # average ReadReq mshr miss latency
+system.cpu.l2cache.ReadReq_hits               1938824                       # number of ReadReq hits
+system.cpu.l2cache.ReadReq_miss_latency    1178290000                       # number of ReadReq miss cycles
+system.cpu.l2cache.ReadReq_miss_rate         0.017420                       # miss rate for ReadReq accesses
+system.cpu.l2cache.ReadReq_misses               34373                       # number of ReadReq misses
+system.cpu.l2cache.ReadReq_mshr_miss_latency   1066043500                       # number of ReadReq MSHR miss cycles
+system.cpu.l2cache.ReadReq_mshr_miss_rate     0.017420                       # mshr miss rate for ReadReq accesses
+system.cpu.l2cache.ReadReq_mshr_misses          34373                       # number of ReadReq MSHR misses
+system.cpu.l2cache.UpgradeReq_accesses              1                       # number of UpgradeReq accesses(hits+misses)
+system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency        31000                       # average UpgradeReq mshr miss latency
+system.cpu.l2cache.UpgradeReq_miss_rate             1                       # miss rate for UpgradeReq accesses
+system.cpu.l2cache.UpgradeReq_misses                1                       # number of UpgradeReq misses
+system.cpu.l2cache.UpgradeReq_mshr_miss_latency        31000                       # number of UpgradeReq MSHR miss cycles
+system.cpu.l2cache.UpgradeReq_mshr_miss_rate            1                       # mshr miss rate for UpgradeReq accesses
+system.cpu.l2cache.UpgradeReq_mshr_misses            1                       # number of UpgradeReq MSHR misses
+system.cpu.l2cache.Writeback_accesses         1442058                       # number of Writeback accesses(hits+misses)
+system.cpu.l2cache.Writeback_hits             1442058                       # number of Writeback hits
+system.cpu.l2cache.avg_blocked_cycles::no_mshrs  2176.470588                       # average number of cycles each access was blocked
 system.cpu.l2cache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
-system.cpu.l2cache.avg_refs                 42.754105                       # Average number of references to valid blocks.
-system.cpu.l2cache.blocked::no_mshrs               11                       # number of cycles access was blocked
+system.cpu.l2cache.avg_refs                 42.835533                       # Average number of references to valid blocks.
+system.cpu.l2cache.blocked::no_mshrs               17                       # number of cycles access was blocked
 system.cpu.l2cache.blocked::no_targets              0                       # number of cycles access was blocked
-system.cpu.l2cache.blocked_cycles::no_mshrs        14000                       # number of cycles access was blocked
+system.cpu.l2cache.blocked_cycles::no_mshrs        37000                       # number of cycles access was blocked
 system.cpu.l2cache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.l2cache.cache_copies                     0                       # number of cache copies performed
-system.cpu.l2cache.demand_accesses            2077543                       # number of demand (read+write) accesses
-system.cpu.l2cache.demand_avg_miss_latency 34222.141249                       # average overall miss latency
-system.cpu.l2cache.demand_avg_mshr_miss_latency 31026.788387                       # average overall mshr miss latency
-system.cpu.l2cache.demand_hits                2000700                       # number of demand (read+write) hits
-system.cpu.l2cache.demand_miss_latency     2629732000                       # number of demand (read+write) miss cycles
-system.cpu.l2cache.demand_miss_rate          0.036987                       # miss rate for demand accesses
-system.cpu.l2cache.demand_misses                76843                       # number of demand (read+write) misses
+system.cpu.l2cache.demand_accesses            2079323                       # number of demand (read+write) accesses
+system.cpu.l2cache.demand_avg_miss_latency 34201.991067                       # average overall miss latency
+system.cpu.l2cache.demand_avg_mshr_miss_latency 31034.104671                       # average overall mshr miss latency
+system.cpu.l2cache.demand_hits                2002530                       # number of demand (read+write) hits
+system.cpu.l2cache.demand_miss_latency     2626473500                       # number of demand (read+write) miss cycles
+system.cpu.l2cache.demand_miss_rate          0.036932                       # miss rate for demand accesses
+system.cpu.l2cache.demand_misses                76793                       # number of demand (read+write) misses
 system.cpu.l2cache.demand_mshr_hits                 0                       # number of demand (read+write) MSHR hits
-system.cpu.l2cache.demand_mshr_miss_latency   2384191500                       # number of demand (read+write) MSHR miss cycles
-system.cpu.l2cache.demand_mshr_miss_rate     0.036987                       # mshr miss rate for demand accesses
-system.cpu.l2cache.demand_mshr_misses           76843                       # number of demand (read+write) MSHR misses
+system.cpu.l2cache.demand_mshr_miss_latency   2383202000                       # number of demand (read+write) MSHR miss cycles
+system.cpu.l2cache.demand_mshr_miss_rate     0.036932                       # mshr miss rate for demand accesses
+system.cpu.l2cache.demand_mshr_misses           76793                       # number of demand (read+write) MSHR misses
 system.cpu.l2cache.fast_writes                      0                       # number of fast writes performed
 system.cpu.l2cache.mshr_cap_events                  0                       # number of times MSHR cap was activated
 system.cpu.l2cache.no_allocate_misses               0                       # Number of misses that were no-allocate
-system.cpu.l2cache.occ_%::0                  0.188685                       # Average percentage of cache occupancy
-system.cpu.l2cache.occ_%::1                  0.343727                       # Average percentage of cache occupancy
-system.cpu.l2cache.occ_blocks::0          6182.815069                       # Average occupied blocks per context
-system.cpu.l2cache.occ_blocks::1         11263.234870                       # Average occupied blocks per context
-system.cpu.l2cache.overall_accesses           2077543                       # number of overall (read+write) accesses
-system.cpu.l2cache.overall_avg_miss_latency 34222.141249                       # average overall miss latency
-system.cpu.l2cache.overall_avg_mshr_miss_latency 31026.788387                       # average overall mshr miss latency
+system.cpu.l2cache.occ_%::0                  0.185144                       # Average percentage of cache occupancy
+system.cpu.l2cache.occ_%::1                  0.337522                       # Average percentage of cache occupancy
+system.cpu.l2cache.occ_blocks::0          6066.784489                       # Average occupied blocks per context
+system.cpu.l2cache.occ_blocks::1         11059.931141                       # Average occupied blocks per context
+system.cpu.l2cache.overall_accesses           2079323                       # number of overall (read+write) accesses
+system.cpu.l2cache.overall_avg_miss_latency 34201.991067                       # average overall miss latency
+system.cpu.l2cache.overall_avg_mshr_miss_latency 31034.104671                       # average overall mshr miss latency
 system.cpu.l2cache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
-system.cpu.l2cache.overall_hits               2000700                       # number of overall hits
-system.cpu.l2cache.overall_miss_latency    2629732000                       # number of overall miss cycles
-system.cpu.l2cache.overall_miss_rate         0.036987                       # miss rate for overall accesses
-system.cpu.l2cache.overall_misses               76843                       # number of overall misses
+system.cpu.l2cache.overall_hits               2002530                       # number of overall hits
+system.cpu.l2cache.overall_miss_latency    2626473500                       # number of overall miss cycles
+system.cpu.l2cache.overall_miss_rate         0.036932                       # miss rate for overall accesses
+system.cpu.l2cache.overall_misses               76793                       # number of overall misses
 system.cpu.l2cache.overall_mshr_hits                0                       # number of overall MSHR hits
-system.cpu.l2cache.overall_mshr_miss_latency   2384191500                       # number of overall MSHR miss cycles
-system.cpu.l2cache.overall_mshr_miss_rate     0.036987                       # mshr miss rate for overall accesses
-system.cpu.l2cache.overall_mshr_misses          76843                       # number of overall MSHR misses
+system.cpu.l2cache.overall_mshr_miss_latency   2383202000                       # number of overall MSHR miss cycles
+system.cpu.l2cache.overall_mshr_miss_rate     0.036932                       # mshr miss rate for overall accesses
+system.cpu.l2cache.overall_mshr_misses          76793                       # number of overall MSHR misses
 system.cpu.l2cache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
 system.cpu.l2cache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.l2cache.replacements                 49399                       # number of replacements
-system.cpu.l2cache.sampled_refs                 77399                       # Sample count of references to valid blocks.
+system.cpu.l2cache.replacements                 49342                       # number of replacements
+system.cpu.l2cache.sampled_refs                 77347                       # Sample count of references to valid blocks.
 system.cpu.l2cache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
-system.cpu.l2cache.tagsinuse             17446.049939                       # Cycle average of tags in use
-system.cpu.l2cache.total_refs                 3309125                       # Total number of references to valid blocks.
+system.cpu.l2cache.tagsinuse             17126.715630                       # Cycle average of tags in use
+system.cpu.l2cache.total_refs                 3313200                       # Total number of references to valid blocks.
 system.cpu.l2cache.warmup_cycle                     0                       # Cycle when the warmup percentage was hit.
-system.cpu.l2cache.writebacks                   29483                       # number of writebacks
-system.cpu.memDep0.conflictingLoads          30510087                       # Number of conflicting loads.
-system.cpu.memDep0.conflictingStores          6437799                       # Number of conflicting stores.
-system.cpu.memDep0.insertedLoads            113153901                       # Number of loads inserted to the mem dependence unit.
-system.cpu.memDep0.insertedStores            36225707                       # Number of stores inserted to the mem dependence unit.
-system.cpu.misc_regfile_reads               204124363                       # number of misc regfile reads
-system.cpu.numCycles                        274706697                       # number of cpu cycles simulated
+system.cpu.l2cache.writebacks                   29450                       # number of writebacks
+system.cpu.memDep0.conflictingLoads          87882428                       # Number of conflicting loads.
+system.cpu.memDep0.conflictingStores         16100005                       # Number of conflicting stores.
+system.cpu.memDep0.insertedLoads            138835558                       # Number of loads inserted to the mem dependence unit.
+system.cpu.memDep0.insertedStores            42750154                       # Number of stores inserted to the mem dependence unit.
+system.cpu.misc_regfile_reads               218323859                       # number of misc regfile reads
+system.cpu.numCycles                        197244429                       # number of cpu cycles simulated
 system.cpu.numWorkItemsCompleted                    0                       # number of work items this cpu completed
 system.cpu.numWorkItemsStarted                      0                       # number of work items this cpu started
-system.cpu.rename.RENAME:BlockCycles           682912                       # Number of cycles rename is blocking
+system.cpu.rename.RENAME:BlockCycles          6557218                       # Number of cycles rename is blocking
 system.cpu.rename.RENAME:CommittedMaps      248344192                       # Number of HB maps that are committed
-system.cpu.rename.RENAME:IQFullEvents           11638                       # Number of times rename has blocked due to IQ full
-system.cpu.rename.RENAME:IdleCycles          72242818                       # Number of cycles rename is idle
-system.cpu.rename.RENAME:LSQFullEvents         253088                       # Number of times rename has blocked due to LSQ full
-system.cpu.rename.RENAME:ROBFullEvents              2                       # Number of times rename has blocked due to ROB full
-system.cpu.rename.RENAME:RenameLookups      867316457                       # Number of register rename lookups that rename has made
-system.cpu.rename.RENAME:RenamedInsts       357042681                       # Number of instructions processed by rename
-system.cpu.rename.RENAME:RenamedOperands    317208618                       # Number of destination operands rename has renamed
-system.cpu.rename.RENAME:RunCycles          190696526                       # Number of cycles rename is running
-system.cpu.rename.RENAME:SquashCycles        10324266                       # Number of cycles rename is squashing
-system.cpu.rename.RENAME:UnblockCycles         414923                       # Number of cycles rename is unblocking
-system.cpu.rename.RENAME:UndoneMaps          68864426                       # Number of HB maps that are undone due to squashing
-system.cpu.rename.RENAME:fp_rename_lookups          276                       # Number of floating rename lookups
-system.cpu.rename.RENAME:int_rename_lookups    867316181                       # Number of integer rename lookups
-system.cpu.rename.RENAME:serializeStallCycles         5222                       # count of cycles rename stalled for serializing inst
-system.cpu.rename.RENAME:serializingInsts          452                       # count of serializing insts renamed
-system.cpu.rename.RENAME:skidInsts             585103                       # count of insts added to the skid buffer
-system.cpu.rename.RENAME:tempSerializingInsts          450                       # count of temporary serializing insts renamed
-system.cpu.rob.rob_reads                    601386186                       # The number of ROB reads
-system.cpu.rob.rob_writes                   689603687                       # The number of ROB writes
-system.cpu.timesIdled                           20021                       # Number of times that the entire CPU went into an idle state and unscheduled itself
+system.cpu.rename.RENAME:IQFullEvents          228138                       # Number of times rename has blocked due to IQ full
+system.cpu.rename.RENAME:IdleCycles          83203716                       # Number of cycles rename is idle
+system.cpu.rename.RENAME:LSQFullEvents       14824029                       # Number of times rename has blocked due to LSQ full
+system.cpu.rename.RENAME:ROBFullEvents             13                       # Number of times rename has blocked due to ROB full
+system.cpu.rename.RENAME:RenameLookups     1059543178                       # Number of register rename lookups that rename has made
+system.cpu.rename.RENAME:RenamedInsts       431467970                       # Number of instructions processed by rename
+system.cpu.rename.RENAME:RenamedOperands    388798641                       # Number of destination operands rename has renamed
+system.cpu.rename.RENAME:RunCycles           71280917                       # Number of cycles rename is running
+system.cpu.rename.RENAME:SquashCycles        19022168                       # Number of cycles rename is squashing
+system.cpu.rename.RENAME:UnblockCycles       15900092                       # Number of cycles rename is unblocking
+system.cpu.rename.RENAME:UndoneMaps         140454449                       # Number of HB maps that are undone due to squashing
+system.cpu.rename.RENAME:fp_rename_lookups          574                       # Number of floating rename lookups
+system.cpu.rename.RENAME:int_rename_lookups   1059542604                       # Number of integer rename lookups
+system.cpu.rename.RENAME:serializeStallCycles         6421                       # count of cycles rename stalled for serializing inst
+system.cpu.rename.RENAME:serializingInsts          469                       # count of serializing insts renamed
+system.cpu.rename.RENAME:skidInsts           38067869                       # count of insts added to the skid buffer
+system.cpu.rename.RENAME:tempSerializingInsts          463                       # count of temporary serializing insts renamed
+system.cpu.rob.rob_reads                    574492355                       # The number of ROB reads
+system.cpu.rob.rob_writes                   837321831                       # The number of ROB writes
+system.cpu.timesIdled                           40675                       # Number of times that the entire CPU went into an idle state and unscheduled itself
 system.cpu.workload.PROG:num_syscalls             444                       # Number of system calls
 
 ---------- End Simulation Statistics   ----------
index 3dfc0b5fadc35f26465b93cb2ef3d1aa2610b6ff..696087afcd5ad1c8eeefe249b1aac2b9c3c75069 100755 (executable)
@@ -5,16 +5,16 @@ The Regents of The University of Michigan
 All Rights Reserved
 
 
-M5 compiled Feb 10 2011 23:58:37
-M5 revision a36c6a370231 7943 default qtip resforflagsstats.patch tip
-M5 started Feb 10 2011 23:58:40
+M5 compiled Feb 12 2011 02:22:23
+M5 revision 5e76f9de6972 7961 default qtip tip x86branchdetectstats.patch
+M5 started Feb 12 2011 02:22:27
 M5 executing on burrito
 command line: build/X86_SE/m5.opt -d build/X86_SE/tests/opt/long/20.parser/x86/linux/o3-timing -re tests/run.py build/X86_SE/tests/opt/long/20.parser/x86/linux/o3-timing
 Global frequency set at 1000000000000 ticks per second
 info: Entering event queue @ 0.  Starting simulation...
 
- Reading the dictionary files: *****************************info: Increasing stack size by one page.
-********************
+ Reading the dictionary files: ***********************info: Increasing stack size by one page.
+**************************
  58924 words stored in 3784810 bytes
 
 
@@ -26,10 +26,10 @@ Processing sentences in batch mode
 
 Echoing of input sentence turned on.
 * as had expected the party to be a success , it was a success 
-info: Increasing stack size by one page.
 * do you know where John 's 
 * he said that , finding that it was impossible to get work as a waiter , he would work as a janitor 
 info: Increasing stack size by one page.
+info: Increasing stack size by one page.
 * how fast the program is it 
 * I am wondering whether to invite to the party 
 * I gave him for his birthday it 
@@ -74,4 +74,4 @@ info: Increasing stack size by one page.
   about 2 million people attended 
   the five best costumes got prizes 
 No errors!
-Exiting @ tick 698491025500 because target called exit()
+Exiting @ tick 610952992000 because target called exit()
index c379599e3f75879c4a9bc02867c9567eb0caf49d..070979214ccd842ca1501b64cef99c64a01c9f6f 100644 (file)
 
 ---------- Begin Simulation Statistics ----------
-host_inst_rate                                 139548                       # Simulator instruction rate (inst/s)
-host_mem_usage                                 244652                       # Number of bytes of host memory used
-host_seconds                                 10956.69                       # Real time elapsed on the host
-host_tick_rate                               63750196                       # Simulator tick rate (ticks/s)
+host_inst_rate                                 130186                       # Simulator instruction rate (inst/s)
+host_mem_usage                                 285488                       # Number of bytes of host memory used
+host_seconds                                 11733.03                       # Real time elapsed on the host
+host_tick_rate                               52071207                       # Simulator tick rate (ticks/s)
 sim_freq                                 1000000000000                       # Frequency of simulated ticks
-sim_insts                                  1528988756                       # Number of instructions simulated
-sim_seconds                                  0.698491                       # Number of seconds simulated
-sim_ticks                                698491025500                       # Number of ticks simulated
+sim_insts                                  1527476062                       # Number of instructions simulated
+sim_seconds                                  0.610953                       # Number of seconds simulated
+sim_ticks                                610952992000                       # Number of ticks simulated
 system.cpu.BPredUnit.BTBCorrect                     0                       # Number of correct BTB predictions (this stat may not work properly.
-system.cpu.BPredUnit.BTBHits                172887264                       # Number of BTB hits
-system.cpu.BPredUnit.BTBLookups             187312240                       # Number of BTB lookups
+system.cpu.BPredUnit.BTBHits                220273443                       # Number of BTB hits
+system.cpu.BPredUnit.BTBLookups             239822696                       # Number of BTB lookups
 system.cpu.BPredUnit.RASInCorrect                   0                       # Number of incorrect RAS predictions.
-system.cpu.BPredUnit.condIncorrect           17887438                       # Number of conditional branches incorrect
-system.cpu.BPredUnit.condPredicted          187888188                       # Number of conditional branches predicted
-system.cpu.BPredUnit.lookups                187888188                       # Number of BP lookups
+system.cpu.BPredUnit.condIncorrect           16691862                       # Number of conditional branches incorrect
+system.cpu.BPredUnit.condPredicted          254901320                       # Number of conditional branches predicted
+system.cpu.BPredUnit.lookups                254901320                       # Number of BP lookups
 system.cpu.BPredUnit.usedRAS                        0                       # Number of times the RAS was used to get a target.
-system.cpu.commit.COM:branches              149758588                       # Number of branches committed
-system.cpu.commit.COM:bw_lim_events          10029766                       # number cycles where commit BW limit reached
+system.cpu.commit.COM:branches              149616585                       # Number of branches committed
+system.cpu.commit.COM:bw_lim_events          33918821                       # number cycles where commit BW limit reached
 system.cpu.commit.COM:bw_limited                    0                       # number of insts not committed due to BW limits
-system.cpu.commit.COM:committed_per_cycle::samples   1350871673                       # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::mean     1.131853                       # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::stdev     1.433209                       # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::samples   1083369873                       # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::mean     1.409930                       # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::stdev     1.877801                       # Number of insts commited each cycle
 system.cpu.commit.COM:committed_per_cycle::underflows            0      0.00%      0.00% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::0    568349245     42.07%     42.07% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::1    413717350     30.63%     72.70% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::2    172321570     12.76%     85.46% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::3    110104358      8.15%     93.61% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::4     43035291      3.19%     96.79% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::5     18507275      1.37%     98.16% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::6      8248201      0.61%     98.77% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::7      6558617      0.49%     99.26% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::8     10029766      0.74%    100.00% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::0    454928288     41.99%     41.99% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::1    282557908     26.08%     68.07% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::2    120287774     11.10%     79.18% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::3    105365409      9.73%     88.90% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::4     40172301      3.71%     92.61% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::5     27676804      2.55%     95.16% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::6     11415389      1.05%     96.22% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::7      7047179      0.65%     96.87% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::8     33918821      3.13%    100.00% # Number of insts commited each cycle
 system.cpu.commit.COM:committed_per_cycle::overflows            0      0.00%    100.00% # Number of insts commited each cycle
 system.cpu.commit.COM:committed_per_cycle::min_value            0                       # Number of insts commited each cycle
 system.cpu.commit.COM:committed_per_cycle::max_value            8                       # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::total   1350871673                       # Number of insts commited each cycle
-system.cpu.commit.COM:count                1528988756                       # Number of instructions committed
+system.cpu.commit.COM:committed_per_cycle::total   1083369873                       # Number of insts commited each cycle
+system.cpu.commit.COM:count                1527476062                       # Number of instructions committed
 system.cpu.commit.COM:fp_insts                      0                       # Number of committed floating point instructions.
 system.cpu.commit.COM:function_calls                0                       # Number of function calls committed.
-system.cpu.commit.COM:int_insts            1528317614                       # Number of committed integer instructions.
-system.cpu.commit.COM:loads                 384102160                       # Number of loads committed
+system.cpu.commit.COM:int_insts            1526804920                       # Number of committed integer instructions.
+system.cpu.commit.COM:loads                 383724495                       # Number of loads committed
 system.cpu.commit.COM:membars                       0                       # Number of memory barriers committed
-system.cpu.commit.COM:refs                  533262345                       # Number of memory references committed
+system.cpu.commit.COM:refs                  532790180                       # Number of memory references committed
 system.cpu.commit.COM:swp_count                     0                       # Number of s/w prefetches committed
-system.cpu.commit.branchMispredicts          17888761                       # The number of times a branch was mispredicted
-system.cpu.commit.commitCommittedInsts     1528988756                       # The number of committed instructions
+system.cpu.commit.branchMispredicts          16726957                       # The number of times a branch was mispredicted
+system.cpu.commit.commitCommittedInsts     1527476062                       # The number of committed instructions
 system.cpu.commit.commitNonSpecStalls             553                       # The number of times commit has been forced to stall to communicate backwards
-system.cpu.commit.commitSquashedInsts       257046446                       # The number of squashed insts skipped by commit
-system.cpu.committedInsts                  1528988756                       # Number of Instructions Simulated
-system.cpu.committedInsts_total            1528988756                       # Number of Instructions Simulated
-system.cpu.cpi                               0.913664                       # CPI: Cycles Per Instruction
-system.cpu.cpi_total                         0.913664                       # CPI: Total CPI of All Threads
-system.cpu.dcache.ReadReq_accesses          334229227                       # number of ReadReq accesses(hits+misses)
-system.cpu.dcache.ReadReq_avg_miss_latency 14263.584813                       # average ReadReq miss latency
-system.cpu.dcache.ReadReq_avg_mshr_miss_latency  8537.168964                       # average ReadReq mshr miss latency
-system.cpu.dcache.ReadReq_hits              332171764                       # number of ReadReq hits
-system.cpu.dcache.ReadReq_miss_latency    29346798000                       # number of ReadReq miss cycles
-system.cpu.dcache.ReadReq_miss_rate          0.006156                       # miss rate for ReadReq accesses
-system.cpu.dcache.ReadReq_misses              2057463                       # number of ReadReq misses
-system.cpu.dcache.ReadReq_mshr_hits            319131                       # number of ReadReq MSHR hits
-system.cpu.dcache.ReadReq_mshr_miss_latency  14840434000                       # number of ReadReq MSHR miss cycles
-system.cpu.dcache.ReadReq_mshr_miss_rate     0.005201                       # mshr miss rate for ReadReq accesses
-system.cpu.dcache.ReadReq_mshr_misses         1738332                       # number of ReadReq MSHR misses
-system.cpu.dcache.WriteReq_accesses         149160201                       # number of WriteReq accesses(hits+misses)
-system.cpu.dcache.WriteReq_avg_miss_latency 16290.992476                       # average WriteReq miss latency
-system.cpu.dcache.WriteReq_avg_mshr_miss_latency 12654.921756                       # average WriteReq mshr miss latency
-system.cpu.dcache.WriteReq_hits             148197195                       # number of WriteReq hits
-system.cpu.dcache.WriteReq_miss_latency   15688323500                       # number of WriteReq miss cycles
-system.cpu.dcache.WriteReq_miss_rate         0.006456                       # miss rate for WriteReq accesses
-system.cpu.dcache.WriteReq_misses              963006                       # number of WriteReq misses
-system.cpu.dcache.WriteReq_mshr_hits           176041                       # number of WriteReq MSHR hits
-system.cpu.dcache.WriteReq_mshr_miss_latency   9958980500                       # number of WriteReq MSHR miss cycles
-system.cpu.dcache.WriteReq_mshr_miss_rate     0.005276                       # mshr miss rate for WriteReq accesses
-system.cpu.dcache.WriteReq_mshr_misses         786965                       # number of WriteReq MSHR misses
+system.cpu.commit.commitSquashedInsts       841443918                       # The number of squashed insts skipped by commit
+system.cpu.committedInsts                  1527476062                       # Number of Instructions Simulated
+system.cpu.committedInsts_total            1527476062                       # Number of Instructions Simulated
+system.cpu.cpi                               0.799951                       # CPI: Cycles Per Instruction
+system.cpu.cpi_total                         0.799951                       # CPI: Total CPI of All Threads
+system.cpu.dcache.ReadReq_accesses          320046346                       # number of ReadReq accesses(hits+misses)
+system.cpu.dcache.ReadReq_avg_miss_latency 15794.070061                       # average ReadReq miss latency
+system.cpu.dcache.ReadReq_avg_mshr_miss_latency  8150.695480                       # average ReadReq mshr miss latency
+system.cpu.dcache.ReadReq_hits              317137092                       # number of ReadReq hits
+system.cpu.dcache.ReadReq_miss_latency    45948961500                       # number of ReadReq miss cycles
+system.cpu.dcache.ReadReq_miss_rate          0.009090                       # miss rate for ReadReq accesses
+system.cpu.dcache.ReadReq_misses              2909254                       # number of ReadReq misses
+system.cpu.dcache.ReadReq_mshr_hits           1183970                       # number of ReadReq MSHR hits
+system.cpu.dcache.ReadReq_mshr_miss_latency  14062264500                       # number of ReadReq MSHR miss cycles
+system.cpu.dcache.ReadReq_mshr_miss_rate     0.005391                       # mshr miss rate for ReadReq accesses
+system.cpu.dcache.ReadReq_mshr_misses         1725284                       # number of ReadReq MSHR misses
+system.cpu.dcache.WriteReq_accesses         149065701                       # number of WriteReq accesses(hits+misses)
+system.cpu.dcache.WriteReq_avg_miss_latency 23554.108597                       # average WriteReq miss latency
+system.cpu.dcache.WriteReq_avg_mshr_miss_latency 18051.470496                       # average WriteReq mshr miss latency
+system.cpu.dcache.WriteReq_hits             147419835                       # number of WriteReq hits
+system.cpu.dcache.WriteReq_miss_latency   38766906500                       # number of WriteReq miss cycles
+system.cpu.dcache.WriteReq_miss_rate         0.011041                       # miss rate for WriteReq accesses
+system.cpu.dcache.WriteReq_misses             1645866                       # number of WriteReq misses
+system.cpu.dcache.WriteReq_mshr_hits           608291                       # number of WriteReq MSHR hits
+system.cpu.dcache.WriteReq_mshr_miss_latency  18729754500                       # number of WriteReq MSHR miss cycles
+system.cpu.dcache.WriteReq_mshr_miss_rate     0.006961                       # mshr miss rate for WriteReq accesses
+system.cpu.dcache.WriteReq_mshr_misses        1037575                       # number of WriteReq MSHR misses
 system.cpu.dcache.avg_blocked_cycles::no_mshrs     no_value                       # average number of cycles each access was blocked
 system.cpu.dcache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
-system.cpu.dcache.avg_refs                 190.400689                       # Average number of references to valid blocks.
+system.cpu.dcache.avg_refs                 185.704246                       # Average number of references to valid blocks.
 system.cpu.dcache.blocked::no_mshrs                 0                       # number of cycles access was blocked
 system.cpu.dcache.blocked::no_targets               0                       # number of cycles access was blocked
 system.cpu.dcache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.dcache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.dcache.cache_copies                      0                       # number of cache copies performed
-system.cpu.dcache.demand_accesses           483389428                       # number of demand (read+write) accesses
-system.cpu.dcache.demand_avg_miss_latency 14909.976398                       # average overall miss latency
-system.cpu.dcache.demand_avg_mshr_miss_latency  9820.395185                       # average overall mshr miss latency
-system.cpu.dcache.demand_hits               480368959                       # number of demand (read+write) hits
-system.cpu.dcache.demand_miss_latency     45035121500                       # number of demand (read+write) miss cycles
-system.cpu.dcache.demand_miss_rate           0.006249                       # miss rate for demand accesses
-system.cpu.dcache.demand_misses               3020469                       # number of demand (read+write) misses
-system.cpu.dcache.demand_mshr_hits             495172                       # number of demand (read+write) MSHR hits
-system.cpu.dcache.demand_mshr_miss_latency  24799414500                       # number of demand (read+write) MSHR miss cycles
-system.cpu.dcache.demand_mshr_miss_rate      0.005224                       # mshr miss rate for demand accesses
-system.cpu.dcache.demand_mshr_misses          2525297                       # number of demand (read+write) MSHR misses
+system.cpu.dcache.demand_accesses           469112047                       # number of demand (read+write) accesses
+system.cpu.dcache.demand_avg_miss_latency 18597.944291                       # average overall miss latency
+system.cpu.dcache.demand_avg_mshr_miss_latency 11868.871701                       # average overall mshr miss latency
+system.cpu.dcache.demand_hits               464556927                       # number of demand (read+write) hits
+system.cpu.dcache.demand_miss_latency     84715868000                       # number of demand (read+write) miss cycles
+system.cpu.dcache.demand_miss_rate           0.009710                       # miss rate for demand accesses
+system.cpu.dcache.demand_misses               4555120                       # number of demand (read+write) misses
+system.cpu.dcache.demand_mshr_hits            1792261                       # number of demand (read+write) MSHR hits
+system.cpu.dcache.demand_mshr_miss_latency  32792019000                       # number of demand (read+write) MSHR miss cycles
+system.cpu.dcache.demand_mshr_miss_rate      0.005890                       # mshr miss rate for demand accesses
+system.cpu.dcache.demand_mshr_misses          2762859                       # number of demand (read+write) MSHR misses
 system.cpu.dcache.fast_writes                       0                       # number of fast writes performed
 system.cpu.dcache.mshr_cap_events                   0                       # number of times MSHR cap was activated
 system.cpu.dcache.no_allocate_misses                0                       # Number of misses that were no-allocate
-system.cpu.dcache.occ_%::0                   0.997741                       # Average percentage of cache occupancy
-system.cpu.dcache.occ_blocks::0           4086.747665                       # Average occupied blocks per context
-system.cpu.dcache.overall_accesses          483389428                       # number of overall (read+write) accesses
-system.cpu.dcache.overall_avg_miss_latency 14909.976398                       # average overall miss latency
-system.cpu.dcache.overall_avg_mshr_miss_latency  9820.395185                       # average overall mshr miss latency
+system.cpu.dcache.occ_%::0                   0.998028                       # Average percentage of cache occupancy
+system.cpu.dcache.occ_blocks::0           4087.922333                       # Average occupied blocks per context
+system.cpu.dcache.overall_accesses          469112047                       # number of overall (read+write) accesses
+system.cpu.dcache.overall_avg_miss_latency 18597.944291                       # average overall miss latency
+system.cpu.dcache.overall_avg_mshr_miss_latency 11868.871701                       # average overall mshr miss latency
 system.cpu.dcache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
-system.cpu.dcache.overall_hits              480368959                       # number of overall hits
-system.cpu.dcache.overall_miss_latency    45035121500                       # number of overall miss cycles
-system.cpu.dcache.overall_miss_rate          0.006249                       # miss rate for overall accesses
-system.cpu.dcache.overall_misses              3020469                       # number of overall misses
-system.cpu.dcache.overall_mshr_hits            495172                       # number of overall MSHR hits
-system.cpu.dcache.overall_mshr_miss_latency  24799414500                       # number of overall MSHR miss cycles
-system.cpu.dcache.overall_mshr_miss_rate     0.005224                       # mshr miss rate for overall accesses
-system.cpu.dcache.overall_mshr_misses         2525297                       # number of overall MSHR misses
+system.cpu.dcache.overall_hits              464556927                       # number of overall hits
+system.cpu.dcache.overall_miss_latency    84715868000                       # number of overall miss cycles
+system.cpu.dcache.overall_miss_rate          0.009710                       # miss rate for overall accesses
+system.cpu.dcache.overall_misses              4555120                       # number of overall misses
+system.cpu.dcache.overall_mshr_hits           1792261                       # number of overall MSHR hits
+system.cpu.dcache.overall_mshr_miss_latency  32792019000                       # number of overall MSHR miss cycles
+system.cpu.dcache.overall_mshr_miss_rate     0.005890                       # mshr miss rate for overall accesses
+system.cpu.dcache.overall_mshr_misses         2762859                       # number of overall MSHR misses
 system.cpu.dcache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
 system.cpu.dcache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.dcache.replacements                2518885                       # number of replacements
-system.cpu.dcache.sampled_refs                2522981                       # Sample count of references to valid blocks.
+system.cpu.dcache.replacements                2504740                       # number of replacements
+system.cpu.dcache.sampled_refs                2508836                       # Sample count of references to valid blocks.
 system.cpu.dcache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
-system.cpu.dcache.tagsinuse               4086.747665                       # Cycle average of tags in use
-system.cpu.dcache.total_refs                480377321                       # Total number of references to valid blocks.
-system.cpu.dcache.warmup_cycle             3312879000                       # Cycle when the warmup percentage was hit.
-system.cpu.dcache.writebacks                  2225275                       # number of writebacks
-system.cpu.decode.DECODE:BlockedCycles       18280435                       # Number of cycles decode is blocked
-system.cpu.decode.DECODE:DecodedInsts      1869219380                       # Number of instructions handled by decode
-system.cpu.decode.DECODE:IdleCycles         343093281                       # Number of cycles decode is idle
-system.cpu.decode.DECODE:RunCycles          984893533                       # Number of cycles decode is running
-system.cpu.decode.DECODE:SquashCycles        39316255                       # Number of cycles decode is squashing
-system.cpu.decode.DECODE:UnblockCycles        4604424                       # Number of cycles decode is unblocking
-system.cpu.fetch.Branches                   187888188                       # Number of branches that fetch encountered
-system.cpu.fetch.CacheLines                 144979108                       # Number of cache lines fetched
-system.cpu.fetch.Cycles                    1039380252                       # Number of cycles fetch has run and was not squashing or blocked
-system.cpu.fetch.IcacheSquashes               2070461                       # Number of outstanding Icache misses that were squashed
-system.cpu.fetch.Insts                      999560833                       # Number of instructions fetch has processed
-system.cpu.fetch.MiscStallCycles                 1828                       # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs
-system.cpu.fetch.SquashCycles                17988626                       # Number of cycles fetch has spent squashing
-system.cpu.fetch.branchRate                  0.134496                       # Number of branch fetches per cycle
-system.cpu.fetch.icacheStallCycles          144979108                       # Number of cycles fetch is stalled on an Icache miss
-system.cpu.fetch.predictedBranches          172887264                       # Number of branches that fetch has predicted taken
-system.cpu.fetch.rate                        0.715514                       # Number of inst fetches per cycle
-system.cpu.fetch.rateDist::samples         1390187928                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::mean              1.363495                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::stdev             1.275570                       # Number of instructions fetched each cycle (Total)
+system.cpu.dcache.tagsinuse               4087.922333                       # Cycle average of tags in use
+system.cpu.dcache.total_refs                465901497                       # Total number of references to valid blocks.
+system.cpu.dcache.warmup_cycle             2529382000                       # Cycle when the warmup percentage was hit.
+system.cpu.dcache.writebacks                  2229751                       # number of writebacks
+system.cpu.decode.DECODE:BlockedCycles      215366555                       # Number of cycles decode is blocked
+system.cpu.decode.DECODE:DecodedInsts      2516935544                       # Number of instructions handled by decode
+system.cpu.decode.DECODE:IdleCycles         437043857                       # Number of cycles decode is idle
+system.cpu.decode.DECODE:RunCycles          404205746                       # Number of cycles decode is running
+system.cpu.decode.DECODE:SquashCycles       113949773                       # Number of cycles decode is squashing
+system.cpu.decode.DECODE:UnblockCycles       26753715                       # Number of cycles decode is unblocking
+system.cpu.fetch.Branches                   254901320                       # Number of branches that fetch encountered
+system.cpu.fetch.CacheLines                 190461812                       # Number of cache lines fetched
+system.cpu.fetch.Cycles                     445534669                       # Number of cycles fetch has run and was not squashing or blocked
+system.cpu.fetch.IcacheSquashes               3068431                       # Number of outstanding Icache misses that were squashed
+system.cpu.fetch.Insts                     1374706338                       # Number of instructions fetch has processed
+system.cpu.fetch.MiscStallCycles                85274                       # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs
+system.cpu.fetch.SquashCycles                18549281                       # Number of cycles fetch has spent squashing
+system.cpu.fetch.branchRate                  0.208610                       # Number of branch fetches per cycle
+system.cpu.fetch.icacheStallCycles          190461812                       # Number of cycles fetch is stalled on an Icache miss
+system.cpu.fetch.predictedBranches          220273443                       # Number of branches that fetch has predicted taken
+system.cpu.fetch.rate                        1.125051                       # Number of inst fetches per cycle
+system.cpu.fetch.rateDist::samples         1197319646                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::mean              2.144693                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::stdev             3.178811                       # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::underflows               0      0.00%      0.00% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::0                388271402     27.93%     27.93% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::1                493387093     35.49%     63.42% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::2                229970387     16.54%     79.96% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::3                224046516     16.12%     96.08% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::4                 21915192      1.58%     97.66% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::5                 25802023      1.86%     99.51% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::6                   493192      0.04%     99.55% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::7                       12      0.00%     99.55% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::8                  6302111      0.45%    100.00% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::0                756027205     63.14%     63.14% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::1                 34054494      2.84%     65.99% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::2                 36745231      3.07%     69.06% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::3                 33767076      2.82%     71.88% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::4                 21459245      1.79%     73.67% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::5                 40493114      3.38%     77.05% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::6                 45860411      3.83%     80.88% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::7                 35731624      2.98%     83.87% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::8                193181246     16.13%    100.00% # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::overflows                0      0.00%    100.00% # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::min_value                0                       # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::max_value                8                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::total           1390187928                       # Number of instructions fetched each cycle (Total)
-system.cpu.fp_regfile_reads                         9                       # number of floating regfile reads
-system.cpu.icache.ReadReq_accesses          144979108                       # number of ReadReq accesses(hits+misses)
-system.cpu.icache.ReadReq_avg_miss_latency 22807.726664                       # average ReadReq miss latency
-system.cpu.icache.ReadReq_avg_mshr_miss_latency 19441.756997                       # average ReadReq mshr miss latency
-system.cpu.icache.ReadReq_hits              144972391                       # number of ReadReq hits
-system.cpu.icache.ReadReq_miss_latency      153199500                       # number of ReadReq miss cycles
-system.cpu.icache.ReadReq_miss_rate          0.000046                       # miss rate for ReadReq accesses
-system.cpu.icache.ReadReq_misses                 6717                       # number of ReadReq misses
-system.cpu.icache.ReadReq_mshr_hits               536                       # number of ReadReq MSHR hits
-system.cpu.icache.ReadReq_mshr_miss_latency    120169500                       # number of ReadReq MSHR miss cycles
-system.cpu.icache.ReadReq_mshr_miss_rate     0.000043                       # mshr miss rate for ReadReq accesses
-system.cpu.icache.ReadReq_mshr_misses            6181                       # number of ReadReq MSHR misses
+system.cpu.fetch.rateDist::total           1197319646                       # Number of instructions fetched each cycle (Total)
+system.cpu.fp_regfile_reads                        31                       # number of floating regfile reads
+system.cpu.icache.ReadReq_accesses          190461812                       # number of ReadReq accesses(hits+misses)
+system.cpu.icache.ReadReq_avg_miss_latency  6527.954910                       # average ReadReq miss latency
+system.cpu.icache.ReadReq_avg_mshr_miss_latency  3419.281975                       # average ReadReq mshr miss latency
+system.cpu.icache.ReadReq_hits              190192396                       # number of ReadReq hits
+system.cpu.icache.ReadReq_miss_latency     1758735500                       # number of ReadReq miss cycles
+system.cpu.icache.ReadReq_miss_rate          0.001415                       # miss rate for ReadReq accesses
+system.cpu.icache.ReadReq_misses               269416                       # number of ReadReq misses
+system.cpu.icache.ReadReq_mshr_hits              1570                       # number of ReadReq MSHR hits
+system.cpu.icache.ReadReq_mshr_miss_latency    915841000                       # number of ReadReq MSHR miss cycles
+system.cpu.icache.ReadReq_mshr_miss_rate     0.001406                       # mshr miss rate for ReadReq accesses
+system.cpu.icache.ReadReq_mshr_misses          267846                       # number of ReadReq MSHR misses
 system.cpu.icache.avg_blocked_cycles::no_mshrs     no_value                       # average number of cycles each access was blocked
 system.cpu.icache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
-system.cpu.icache.avg_refs               43679.520036                       # Average number of references to valid blocks.
+system.cpu.icache.avg_refs               17699.832480                       # Average number of references to valid blocks.
 system.cpu.icache.blocked::no_mshrs                 0                       # number of cycles access was blocked
 system.cpu.icache.blocked::no_targets               0                       # number of cycles access was blocked
 system.cpu.icache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.icache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.icache.cache_copies                      0                       # number of cache copies performed
-system.cpu.icache.demand_accesses           144979108                       # number of demand (read+write) accesses
-system.cpu.icache.demand_avg_miss_latency 22807.726664                       # average overall miss latency
-system.cpu.icache.demand_avg_mshr_miss_latency 19441.756997                       # average overall mshr miss latency
-system.cpu.icache.demand_hits               144972391                       # number of demand (read+write) hits
-system.cpu.icache.demand_miss_latency       153199500                       # number of demand (read+write) miss cycles
-system.cpu.icache.demand_miss_rate           0.000046                       # miss rate for demand accesses
-system.cpu.icache.demand_misses                  6717                       # number of demand (read+write) misses
-system.cpu.icache.demand_mshr_hits                536                       # number of demand (read+write) MSHR hits
-system.cpu.icache.demand_mshr_miss_latency    120169500                       # number of demand (read+write) MSHR miss cycles
-system.cpu.icache.demand_mshr_miss_rate      0.000043                       # mshr miss rate for demand accesses
-system.cpu.icache.demand_mshr_misses             6181                       # number of demand (read+write) MSHR misses
+system.cpu.icache.demand_accesses           190461812                       # number of demand (read+write) accesses
+system.cpu.icache.demand_avg_miss_latency  6527.954910                       # average overall miss latency
+system.cpu.icache.demand_avg_mshr_miss_latency  3419.281975                       # average overall mshr miss latency
+system.cpu.icache.demand_hits               190192396                       # number of demand (read+write) hits
+system.cpu.icache.demand_miss_latency      1758735500                       # number of demand (read+write) miss cycles
+system.cpu.icache.demand_miss_rate           0.001415                       # miss rate for demand accesses
+system.cpu.icache.demand_misses                269416                       # number of demand (read+write) misses
+system.cpu.icache.demand_mshr_hits               1570                       # number of demand (read+write) MSHR hits
+system.cpu.icache.demand_mshr_miss_latency    915841000                       # number of demand (read+write) MSHR miss cycles
+system.cpu.icache.demand_mshr_miss_rate      0.001406                       # mshr miss rate for demand accesses
+system.cpu.icache.demand_mshr_misses           267846                       # number of demand (read+write) MSHR misses
 system.cpu.icache.fast_writes                       0                       # number of fast writes performed
 system.cpu.icache.mshr_cap_events                   0                       # number of times MSHR cap was activated
 system.cpu.icache.no_allocate_misses                0                       # Number of misses that were no-allocate
-system.cpu.icache.occ_%::0                   0.450710                       # Average percentage of cache occupancy
-system.cpu.icache.occ_blocks::0            923.054085                       # Average occupied blocks per context
-system.cpu.icache.overall_accesses          144979108                       # number of overall (read+write) accesses
-system.cpu.icache.overall_avg_miss_latency 22807.726664                       # average overall miss latency
-system.cpu.icache.overall_avg_mshr_miss_latency 19441.756997                       # average overall mshr miss latency
+system.cpu.icache.occ_%::0                   0.466021                       # Average percentage of cache occupancy
+system.cpu.icache.occ_blocks::0            954.411836                       # Average occupied blocks per context
+system.cpu.icache.overall_accesses          190461812                       # number of overall (read+write) accesses
+system.cpu.icache.overall_avg_miss_latency  6527.954910                       # average overall miss latency
+system.cpu.icache.overall_avg_mshr_miss_latency  3419.281975                       # average overall mshr miss latency
 system.cpu.icache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
-system.cpu.icache.overall_hits              144972391                       # number of overall hits
-system.cpu.icache.overall_miss_latency      153199500                       # number of overall miss cycles
-system.cpu.icache.overall_miss_rate          0.000046                       # miss rate for overall accesses
-system.cpu.icache.overall_misses                 6717                       # number of overall misses
-system.cpu.icache.overall_mshr_hits               536                       # number of overall MSHR hits
-system.cpu.icache.overall_mshr_miss_latency    120169500                       # number of overall MSHR miss cycles
-system.cpu.icache.overall_mshr_miss_rate     0.000043                       # mshr miss rate for overall accesses
-system.cpu.icache.overall_mshr_misses            6181                       # number of overall MSHR misses
+system.cpu.icache.overall_hits              190192396                       # number of overall hits
+system.cpu.icache.overall_miss_latency     1758735500                       # number of overall miss cycles
+system.cpu.icache.overall_miss_rate          0.001415                       # miss rate for overall accesses
+system.cpu.icache.overall_misses               269416                       # number of overall misses
+system.cpu.icache.overall_mshr_hits              1570                       # number of overall MSHR hits
+system.cpu.icache.overall_mshr_miss_latency    915841000                       # number of overall MSHR miss cycles
+system.cpu.icache.overall_mshr_miss_rate     0.001406                       # mshr miss rate for overall accesses
+system.cpu.icache.overall_mshr_misses          267846                       # number of overall MSHR misses
 system.cpu.icache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
 system.cpu.icache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.icache.replacements                   1737                       # number of replacements
-system.cpu.icache.sampled_refs                   3319                       # Sample count of references to valid blocks.
+system.cpu.icache.replacements                   9298                       # number of replacements
+system.cpu.icache.sampled_refs                  10745                       # Sample count of references to valid blocks.
 system.cpu.icache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
-system.cpu.icache.tagsinuse                923.054085                       # Cycle average of tags in use
-system.cpu.icache.total_refs                144972327                       # Total number of references to valid blocks.
+system.cpu.icache.tagsinuse                954.411836                       # Cycle average of tags in use
+system.cpu.icache.total_refs                190184700                       # Total number of references to valid blocks.
 system.cpu.icache.warmup_cycle                      0                       # Cycle when the warmup percentage was hit.
-system.cpu.icache.writebacks                        0                       # number of writebacks
-system.cpu.idleCycles                         6794124                       # Total number of cycles that the CPU has spent unscheduled due to idling
-system.cpu.iew.EXEC:branches                154306305                       # Number of branches executed
+system.cpu.icache.writebacks                        3                       # number of writebacks
+system.cpu.idleCycles                        24586339                       # Total number of cycles that the CPU has spent unscheduled due to idling
+system.cpu.iew.EXEC:branches                175611349                       # Number of branches executed
 system.cpu.iew.EXEC:nop                             0                       # number of nop insts executed
-system.cpu.iew.EXEC:rate                     1.173655                       # Inst execution rate
-system.cpu.iew.EXEC:refs                    571924541                       # number of memory reference insts executed
-system.cpu.iew.EXEC:stores                  156120222                       # Number of stores executed
+system.cpu.iew.EXEC:rate                     1.537639                       # Inst execution rate
+system.cpu.iew.EXEC:refs                    604612823                       # number of memory reference insts executed
+system.cpu.iew.EXEC:stores                  164362000                       # Number of stores executed
 system.cpu.iew.EXEC:swp                             0                       # number of swp insts executed
-system.cpu.iew.WB:consumers                1557537154                       # num instructions consuming a value
-system.cpu.iew.WB:count                    1628444279                       # cumulative count of insts written-back
-system.cpu.iew.WB:fanout                     0.759406                       # average fanout of values written-back
+system.cpu.iew.WB:consumers                2150205320                       # num instructions consuming a value
+system.cpu.iew.WB:count                    1865910107                       # cumulative count of insts written-back
+system.cpu.iew.WB:fanout                     0.666196                       # average fanout of values written-back
 system.cpu.iew.WB:penalized                         0                       # number of instrctions required to write to 'other' IQ
 system.cpu.iew.WB:penalized_rate                    0                       # fraction of instructions written-back that wrote to 'other' IQ
-system.cpu.iew.WB:producers                1182802327                       # num instructions producing a value
-system.cpu.iew.WB:rate                       1.165687                       # insts written-back per cycle
-system.cpu.iew.WB:sent                     1630313962                       # cumulative count of insts sent to commit
-system.cpu.iew.branchMispredicts             18753816                       # Number of branch mispredicts detected at execute
-system.cpu.iew.iewBlockCycles                 4588629                       # Number of cycles IEW is blocking
-system.cpu.iew.iewDispLoadInsts             454402470                       # Number of dispatched load instructions
-system.cpu.iew.iewDispNonSpecInsts                570                       # Number of dispatched non-speculative instructions
-system.cpu.iew.iewDispSquashedInsts          11948307                       # Number of squashed instructions skipped by dispatch
-system.cpu.iew.iewDispStoreInsts            170547501                       # Number of dispatched store instructions
-system.cpu.iew.iewDispatchedInsts          1786034876                       # Number of instructions dispatched to IQ
-system.cpu.iew.iewExecLoadInsts             415804319                       # Number of load instructions executed
-system.cpu.iew.iewExecSquashedInsts          21119599                       # Number of squashed instructions skipped in execute
-system.cpu.iew.iewExecutedInsts            1639574511                       # Number of executed instructions
-system.cpu.iew.iewIQFullEvents                 357621                       # Number of times the IQ has become full, causing a stall
+system.cpu.iew.WB:producers                1432458045                       # num instructions producing a value
+system.cpu.iew.WB:rate                       1.527049                       # insts written-back per cycle
+system.cpu.iew.WB:sent                     1872952311                       # cumulative count of insts sent to commit
+system.cpu.iew.branchMispredicts             18187438                       # Number of branch mispredicts detected at execute
+system.cpu.iew.iewBlockCycles                 9702727                       # Number of cycles IEW is blocking
+system.cpu.iew.iewDispLoadInsts             598780500                       # Number of dispatched load instructions
+system.cpu.iew.iewDispNonSpecInsts               6555                       # Number of dispatched non-speculative instructions
+system.cpu.iew.iewDispSquashedInsts           2427132                       # Number of squashed instructions skipped by dispatch
+system.cpu.iew.iewDispStoreInsts            227725972                       # Number of dispatched store instructions
+system.cpu.iew.iewDispatchedInsts          2368916953                       # Number of instructions dispatched to IQ
+system.cpu.iew.iewExecLoadInsts             440250823                       # Number of load instructions executed
+system.cpu.iew.iewExecSquashedInsts          24902522                       # Number of squashed instructions skipped in execute
+system.cpu.iew.iewExecutedInsts            1878850199                       # Number of executed instructions
+system.cpu.iew.iewIQFullEvents                 999062                       # Number of times the IQ has become full, causing a stall
 system.cpu.iew.iewIdleCycles                        0                       # Number of cycles IEW is idle
-system.cpu.iew.iewLSQFullEvents                  9695                       # Number of times the LSQ has become full, causing a stall
-system.cpu.iew.iewSquashCycles               39316255                       # Number of cycles IEW is squashing
-system.cpu.iew.iewUnblockCycles                668139                       # Number of cycles IEW is unblocking
+system.cpu.iew.iewLSQFullEvents                 48995                       # Number of times the LSQ has become full, causing a stall
+system.cpu.iew.iewSquashCycles              113949773                       # Number of cycles IEW is squashing
+system.cpu.iew.iewUnblockCycles               1501929                       # Number of cycles IEW is unblocking
 system.cpu.iew.lsq.thread.0.blockedLoads            0                       # Number of blocked loads due to partial load-store forwarding
 system.cpu.iew.lsq.thread.0.cacheBlocked            0                       # Number of times an access to memory failed due to the cache being blocked
-system.cpu.iew.lsq.thread.0.forwLoads        80610216                       # Number of loads that had data forwarded from stores
-system.cpu.iew.lsq.thread.0.ignoredResponses       294173                       # Number of memory responses ignored because the instruction is squashed
+system.cpu.iew.lsq.thread.0.forwLoads       119150872                       # Number of loads that had data forwarded from stores
+system.cpu.iew.lsq.thread.0.ignoredResponses       153037                       # Number of memory responses ignored because the instruction is squashed
 system.cpu.iew.lsq.thread.0.invAddrLoads            0                       # Number of loads ignored due to an invalid address
 system.cpu.iew.lsq.thread.0.invAddrSwpfs            0                       # Number of software prefetches ignored due to an invalid address
-system.cpu.iew.lsq.thread.0.memOrderViolation       154646                       # Number of memory ordering violations
-system.cpu.iew.lsq.thread.0.rescheduledLoads          837                       # Number of loads that were rescheduled
-system.cpu.iew.lsq.thread.0.squashedLoads     70300310                       # Number of loads squashed
-system.cpu.iew.lsq.thread.0.squashedStores     21387316                       # Number of stores squashed
-system.cpu.iew.memOrderViolationEvents         154646                       # Number of memory order violations
-system.cpu.iew.predictedNotTakenIncorrect       515713                       # Number of branches that were predicted not taken incorrectly
-system.cpu.iew.predictedTakenIncorrect       18238103                       # Number of branches that were predicted taken incorrectly
-system.cpu.int_regfile_reads               2891828761                       # number of integer regfile reads
-system.cpu.int_regfile_writes              1524435086                       # number of integer regfile writes
-system.cpu.ipc                               1.094494                       # IPC: Instructions Per Cycle
-system.cpu.ipc_total                         1.094494                       # IPC: Total IPC of All Threads
-system.cpu.iq.ISSUE:FU_type_0::No_OpClass      1929805      0.12%      0.12% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::IntAlu      1078730229     64.96%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::IntMult              0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::IntDiv               0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatAdd             0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatCmp             0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatCvt             0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatMult            0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatDiv             0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatSqrt            0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdAdd              0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdAddAcc            0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdAlu              0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdCmp              0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdCvt              0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdMisc             0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdMult             0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdMultAcc            0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdShift            0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdShiftAcc            0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdSqrt             0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatAdd            0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatAlu            0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatCmp            0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatCvt            0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatDiv            0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatMisc            0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatMult            0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatMultAcc            0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatSqrt            0      0.00%     65.07% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::MemRead      421270517     25.37%     90.44% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::MemWrite     158763559      9.56%    100.00% # Type of FU issued
+system.cpu.iew.lsq.thread.0.memOrderViolation      1905759                       # Number of memory ordering violations
+system.cpu.iew.lsq.thread.0.rescheduledLoads         1230                       # Number of loads that were rescheduled
+system.cpu.iew.lsq.thread.0.squashedLoads    215056005                       # Number of loads squashed
+system.cpu.iew.lsq.thread.0.squashedStores     78660287                       # Number of stores squashed
+system.cpu.iew.memOrderViolationEvents        1905759                       # Number of memory order violations
+system.cpu.iew.predictedNotTakenIncorrect      2718790                       # Number of branches that were predicted not taken incorrectly
+system.cpu.iew.predictedTakenIncorrect       15468648                       # Number of branches that were predicted taken incorrectly
+system.cpu.int_regfile_reads               3097184079                       # number of integer regfile reads
+system.cpu.int_regfile_writes              1741804464                       # number of integer regfile writes
+system.cpu.ipc                               1.250077                       # IPC: Instructions Per Cycle
+system.cpu.ipc_total                         1.250077                       # IPC: Total IPC of All Threads
+system.cpu.iq.ISSUE:FU_type_0::No_OpClass      2283854      0.12%      0.12% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::IntAlu      1286143659     67.56%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::IntMult              0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::IntDiv               0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatAdd             0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatCmp             0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatCvt             0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatMult            0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatDiv             0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatSqrt            0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdAdd              0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdAddAcc            0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdAlu              0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdCmp              0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdCvt              0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdMisc             0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdMult             0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdMultAcc            0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdShift            0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdShiftAcc            0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdSqrt             0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatAdd            0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatAlu            0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatCmp            0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatCvt            0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatDiv            0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatMisc            0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatMult            0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatMultAcc            0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatSqrt            0      0.00%     67.68% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::MemRead      446588315     23.46%     91.14% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::MemWrite     168736893      8.86%    100.00% # Type of FU issued
 system.cpu.iq.ISSUE:FU_type_0::IprAccess            0      0.00%    100.00% # Type of FU issued
 system.cpu.iq.ISSUE:FU_type_0::InstPrefetch            0      0.00%    100.00% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::total       1660694110                       # Type of FU issued
-system.cpu.iq.ISSUE:fu_busy_cnt                783660                       # FU busy when requested
-system.cpu.iq.ISSUE:fu_busy_rate             0.000472                       # FU busy rate (busy events/executed inst)
+system.cpu.iq.ISSUE:FU_type_0::total       1903752721                       # Type of FU issued
+system.cpu.iq.ISSUE:fu_busy_cnt              12019370                       # FU busy when requested
+system.cpu.iq.ISSUE:fu_busy_rate             0.006314                       # FU busy rate (busy events/executed inst)
 system.cpu.iq.ISSUE:fu_full::No_OpClass             0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::IntAlu             37602      4.80%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::IntMult                0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::IntDiv                 0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatAdd               0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatCmp               0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatCvt               0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatMult              0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatDiv               0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatSqrt              0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdAdd                0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdAddAcc             0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdAlu                0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdCmp                0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdCvt                0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdMisc               0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdMult               0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdMultAcc            0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdShift              0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdShiftAcc            0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdSqrt               0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatAdd            0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatAlu            0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatCmp            0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatCvt            0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatDiv            0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatMisc            0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatMult            0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatMultAcc            0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatSqrt            0      0.00%      4.80% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::MemRead           575954     73.50%     78.29% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::MemWrite          170104     21.71%    100.00% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::IntAlu           1063366      8.85%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::IntMult                0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::IntDiv                 0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatAdd               0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatCmp               0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatCvt               0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatMult              0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatDiv               0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatSqrt              0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdAdd                0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdAddAcc             0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdAlu                0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdCmp                0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdCvt                0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdMisc               0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdMult               0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdMultAcc            0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdShift              0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdShiftAcc            0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdSqrt               0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatAdd            0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatAlu            0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatCmp            0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatCvt            0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatDiv            0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatMisc            0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatMult            0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatMultAcc            0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatSqrt            0      0.00%      8.85% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::MemRead          7508013     62.47%     71.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::MemWrite         3447991     28.69%    100.00% # attempts to use FU when none available
 system.cpu.iq.ISSUE:fu_full::IprAccess              0      0.00%    100.00% # attempts to use FU when none available
 system.cpu.iq.ISSUE:fu_full::InstPrefetch            0      0.00%    100.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:issued_per_cycle::samples   1390187928                       # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::mean     1.194582                       # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::stdev     1.080366                       # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::samples   1197319646                       # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::mean     1.590012                       # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::stdev     1.576110                       # Number of insts issued each cycle
 system.cpu.iq.ISSUE:issued_per_cycle::underflows            0      0.00%      0.00% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::0     424313305     30.52%     30.52% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::1     484307598     34.84%     65.36% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::2     321495427     23.13%     88.49% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::3     117467117      8.45%     96.94% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::4      33024815      2.38%     99.31% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::5       8635258      0.62%     99.93% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::6        892156      0.06%    100.00% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::7         52195      0.00%    100.00% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::8            57      0.00%    100.00% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::0     380569061     31.79%     31.79% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::1     297509781     24.85%     56.63% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::2     210374930     17.57%     74.20% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::3     147240855     12.30%     86.50% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::4      95168176      7.95%     94.45% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::5      42314918      3.53%     97.98% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::6      17818883      1.49%     99.47% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::7       5974413      0.50%     99.97% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::8        348629      0.03%    100.00% # Number of insts issued each cycle
 system.cpu.iq.ISSUE:issued_per_cycle::overflows            0      0.00%    100.00% # Number of insts issued each cycle
 system.cpu.iq.ISSUE:issued_per_cycle::min_value            0                       # Number of insts issued each cycle
 system.cpu.iq.ISSUE:issued_per_cycle::max_value            8                       # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::total   1390187928                       # Number of insts issued each cycle
-system.cpu.iq.ISSUE:rate                     1.188773                       # Inst issue rate
-system.cpu.iq.fp_alu_accesses                      22                       # Number of floating point alu accesses
-system.cpu.iq.fp_inst_queue_reads                  44                       # Number of floating instruction queue reads
-system.cpu.iq.fp_inst_queue_wakeup_accesses            9                       # Number of floating instruction queue wakeup accesses
-system.cpu.iq.fp_inst_queue_writes                 68                       # Number of floating instruction queue writes
-system.cpu.iq.int_alu_accesses             1659547943                       # Number of integer alu accesses
-system.cpu.iq.int_inst_queue_reads         4712390399                       # Number of integer instruction queue reads
-system.cpu.iq.int_inst_queue_wakeup_accesses   1628444270                       # Number of integer instruction queue wakeup accesses
-system.cpu.iq.int_inst_queue_writes        2036676469                       # Number of integer instruction queue writes
-system.cpu.iq.iqInstsAdded                 1786034306                       # Number of instructions added to the IQ (excludes non-spec)
-system.cpu.iq.iqInstsIssued                1660694110                       # Number of instructions issued
-system.cpu.iq.iqNonSpecInstsAdded                 570                       # Number of non-speculative instructions added to the IQ
-system.cpu.iq.iqSquashedInstsExamined       250539717                       # Number of squashed instructions iterated over during squash; mainly for profiling
-system.cpu.iq.iqSquashedInstsIssued             30635                       # Number of squashed instructions issued
-system.cpu.iq.iqSquashedNonSpecRemoved             17                       # Number of squashed non-spec instructions that were removed
-system.cpu.iq.iqSquashedOperandsExamined    443519402                       # Number of squashed operands that are examined and possibly removed from graph
-system.cpu.l2cache.ReadExReq_accesses          789066                       # number of ReadExReq accesses(hits+misses)
-system.cpu.l2cache.ReadExReq_avg_miss_latency 34257.778038                       # average ReadExReq miss latency
-system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31001.587520                       # average ReadExReq mshr miss latency
-system.cpu.l2cache.ReadExReq_hits              541510                       # number of ReadExReq hits
-system.cpu.l2cache.ReadExReq_miss_latency   8480718500                       # number of ReadExReq miss cycles
-system.cpu.l2cache.ReadExReq_miss_rate       0.313733                       # miss rate for ReadExReq accesses
-system.cpu.l2cache.ReadExReq_misses            247556                       # number of ReadExReq misses
-system.cpu.l2cache.ReadExReq_mshr_miss_latency   7674629000                       # number of ReadExReq MSHR miss cycles
-system.cpu.l2cache.ReadExReq_mshr_miss_rate     0.313733                       # mshr miss rate for ReadExReq accesses
-system.cpu.l2cache.ReadExReq_mshr_misses       247556                       # number of ReadExReq MSHR misses
-system.cpu.l2cache.ReadReq_accesses           1737232                       # number of ReadReq accesses(hits+misses)
-system.cpu.l2cache.ReadReq_avg_miss_latency 34158.153227                       # average ReadReq miss latency
-system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31002.616867                       # average ReadReq mshr miss latency
-system.cpu.l2cache.ReadReq_hits               1403818                       # number of ReadReq hits
-system.cpu.l2cache.ReadReq_miss_latency   11388806500                       # number of ReadReq miss cycles
-system.cpu.l2cache.ReadReq_miss_rate         0.191923                       # miss rate for ReadReq accesses
-system.cpu.l2cache.ReadReq_misses              333414                       # number of ReadReq misses
-system.cpu.l2cache.ReadReq_mshr_miss_latency  10336706500                       # number of ReadReq MSHR miss cycles
-system.cpu.l2cache.ReadReq_mshr_miss_rate     0.191923                       # mshr miss rate for ReadReq accesses
-system.cpu.l2cache.ReadReq_mshr_misses         333414                       # number of ReadReq MSHR misses
-system.cpu.l2cache.UpgradeReq_accesses           2858                       # number of UpgradeReq accesses(hits+misses)
-system.cpu.l2cache.UpgradeReq_avg_miss_latency    24.740050                       # average UpgradeReq miss latency
-system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 31000.358551                       # average UpgradeReq mshr miss latency
-system.cpu.l2cache.UpgradeReq_hits                 69                       # number of UpgradeReq hits
-system.cpu.l2cache.UpgradeReq_miss_latency        69000                       # number of UpgradeReq miss cycles
-system.cpu.l2cache.UpgradeReq_miss_rate      0.975857                       # miss rate for UpgradeReq accesses
-system.cpu.l2cache.UpgradeReq_misses             2789                       # number of UpgradeReq misses
-system.cpu.l2cache.UpgradeReq_mshr_miss_latency     86460000                       # number of UpgradeReq MSHR miss cycles
-system.cpu.l2cache.UpgradeReq_mshr_miss_rate     0.975857                       # mshr miss rate for UpgradeReq accesses
-system.cpu.l2cache.UpgradeReq_mshr_misses         2789                       # number of UpgradeReq MSHR misses
-system.cpu.l2cache.Writeback_accesses         2225275                       # number of Writeback accesses(hits+misses)
-system.cpu.l2cache.Writeback_hits             2225275                       # number of Writeback hits
+system.cpu.iq.ISSUE:issued_per_cycle::total   1197319646                       # Number of insts issued each cycle
+system.cpu.iq.ISSUE:rate                     1.558019                       # Inst issue rate
+system.cpu.iq.fp_alu_accesses                      59                       # Number of floating point alu accesses
+system.cpu.iq.fp_inst_queue_reads                 119                       # Number of floating instruction queue reads
+system.cpu.iq.fp_inst_queue_wakeup_accesses           31                       # Number of floating instruction queue wakeup accesses
+system.cpu.iq.fp_inst_queue_writes               7970                       # Number of floating instruction queue writes
+system.cpu.iq.int_alu_accesses             1913488178                       # Number of integer alu accesses
+system.cpu.iq.int_inst_queue_reads         5017400189                       # Number of integer instruction queue reads
+system.cpu.iq.int_inst_queue_wakeup_accesses   1865910076                       # Number of integer instruction queue wakeup accesses
+system.cpu.iq.int_inst_queue_writes        3209512631                       # Number of integer instruction queue writes
+system.cpu.iq.iqInstsAdded                 2368910398                       # Number of instructions added to the IQ (excludes non-spec)
+system.cpu.iq.iqInstsIssued                1903752721                       # Number of instructions issued
+system.cpu.iq.iqNonSpecInstsAdded                6555                       # Number of non-speculative instructions added to the IQ
+system.cpu.iq.iqSquashedInstsExamined       838752495                       # Number of squashed instructions iterated over during squash; mainly for profiling
+system.cpu.iq.iqSquashedInstsIssued            555850                       # Number of squashed instructions issued
+system.cpu.iq.iqSquashedNonSpecRemoved           6002                       # Number of squashed non-spec instructions that were removed
+system.cpu.iq.iqSquashedOperandsExamined   1472792375                       # Number of squashed operands that are examined and possibly removed from graph
+system.cpu.l2cache.ReadExReq_accesses          786848                       # number of ReadExReq accesses(hits+misses)
+system.cpu.l2cache.ReadExReq_avg_miss_latency 34255.494728                       # average ReadExReq miss latency
+system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31001.453653                       # average ReadExReq mshr miss latency
+system.cpu.l2cache.ReadExReq_hits              539884                       # number of ReadExReq hits
+system.cpu.l2cache.ReadExReq_miss_latency   8459874000                       # number of ReadExReq miss cycles
+system.cpu.l2cache.ReadExReq_miss_rate       0.313865                       # miss rate for ReadExReq accesses
+system.cpu.l2cache.ReadExReq_misses            246964                       # number of ReadExReq misses
+system.cpu.l2cache.ReadExReq_mshr_miss_latency   7656243000                       # number of ReadExReq MSHR miss cycles
+system.cpu.l2cache.ReadExReq_mshr_miss_rate     0.313865                       # mshr miss rate for ReadExReq accesses
+system.cpu.l2cache.ReadExReq_mshr_misses       246964                       # number of ReadExReq MSHR misses
+system.cpu.l2cache.ReadReq_accesses           1732679                       # number of ReadReq accesses(hits+misses)
+system.cpu.l2cache.ReadReq_avg_miss_latency 34171.480760                       # average ReadReq miss latency
+system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31002.917505                       # average ReadReq mshr miss latency
+system.cpu.l2cache.ReadReq_hits               1415970                       # number of ReadReq hits
+system.cpu.l2cache.ReadReq_miss_latency   10822415500                       # number of ReadReq miss cycles
+system.cpu.l2cache.ReadReq_miss_rate         0.182786                       # miss rate for ReadReq accesses
+system.cpu.l2cache.ReadReq_misses              316709                       # number of ReadReq misses
+system.cpu.l2cache.ReadReq_mshr_miss_latency   9818903000                       # number of ReadReq MSHR miss cycles
+system.cpu.l2cache.ReadReq_mshr_miss_rate     0.182786                       # mshr miss rate for ReadReq accesses
+system.cpu.l2cache.ReadReq_mshr_misses         316709                       # number of ReadReq MSHR misses
+system.cpu.l2cache.UpgradeReq_accesses         256943                       # number of UpgradeReq accesses(hits+misses)
+system.cpu.l2cache.UpgradeReq_avg_miss_latency    40.077896                       # average UpgradeReq miss latency
+system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 31003.030576                       # average UpgradeReq mshr miss latency
+system.cpu.l2cache.UpgradeReq_hits               1216                       # number of UpgradeReq hits
+system.cpu.l2cache.UpgradeReq_miss_latency     10249000                       # number of UpgradeReq miss cycles
+system.cpu.l2cache.UpgradeReq_miss_rate      0.995267                       # miss rate for UpgradeReq accesses
+system.cpu.l2cache.UpgradeReq_misses           255727                       # number of UpgradeReq misses
+system.cpu.l2cache.UpgradeReq_mshr_miss_latency   7928312000                       # number of UpgradeReq MSHR miss cycles
+system.cpu.l2cache.UpgradeReq_mshr_miss_rate     0.995267                       # mshr miss rate for UpgradeReq accesses
+system.cpu.l2cache.UpgradeReq_mshr_misses       255727                       # number of UpgradeReq MSHR misses
+system.cpu.l2cache.Writeback_accesses         2229754                       # number of Writeback accesses(hits+misses)
+system.cpu.l2cache.Writeback_hits             2229754                       # number of Writeback hits
 system.cpu.l2cache.avg_blocked_cycles::no_mshrs     no_value                       # average number of cycles each access was blocked
 system.cpu.l2cache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
-system.cpu.l2cache.avg_refs                  5.353417                       # Average number of references to valid blocks.
+system.cpu.l2cache.avg_refs                  5.404070                       # Average number of references to valid blocks.
 system.cpu.l2cache.blocked::no_mshrs                0                       # number of cycles access was blocked
 system.cpu.l2cache.blocked::no_targets              0                       # number of cycles access was blocked
 system.cpu.l2cache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.l2cache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.l2cache.cache_copies                     0                       # number of cache copies performed
-system.cpu.l2cache.demand_accesses            2526298                       # number of demand (read+write) accesses
-system.cpu.l2cache.demand_avg_miss_latency 34200.604162                       # average overall miss latency
-system.cpu.l2cache.demand_avg_mshr_miss_latency 31002.178254                       # average overall mshr miss latency
-system.cpu.l2cache.demand_hits                1945328                       # number of demand (read+write) hits
-system.cpu.l2cache.demand_miss_latency    19869525000                       # number of demand (read+write) miss cycles
-system.cpu.l2cache.demand_miss_rate          0.229969                       # miss rate for demand accesses
-system.cpu.l2cache.demand_misses               580970                       # number of demand (read+write) misses
+system.cpu.l2cache.demand_accesses            2519527                       # number of demand (read+write) accesses
+system.cpu.l2cache.demand_avg_miss_latency 34208.290090                       # average overall miss latency
+system.cpu.l2cache.demand_avg_mshr_miss_latency 31002.276142                       # average overall mshr miss latency
+system.cpu.l2cache.demand_hits                1955854                       # number of demand (read+write) hits
+system.cpu.l2cache.demand_miss_latency    19282289500                       # number of demand (read+write) miss cycles
+system.cpu.l2cache.demand_miss_rate          0.223722                       # miss rate for demand accesses
+system.cpu.l2cache.demand_misses               563673                       # number of demand (read+write) misses
 system.cpu.l2cache.demand_mshr_hits                 0                       # number of demand (read+write) MSHR hits
-system.cpu.l2cache.demand_mshr_miss_latency  18011335500                       # number of demand (read+write) MSHR miss cycles
-system.cpu.l2cache.demand_mshr_miss_rate     0.229969                       # mshr miss rate for demand accesses
-system.cpu.l2cache.demand_mshr_misses          580970                       # number of demand (read+write) MSHR misses
+system.cpu.l2cache.demand_mshr_miss_latency  17475146000                       # number of demand (read+write) MSHR miss cycles
+system.cpu.l2cache.demand_mshr_miss_rate     0.223722                       # mshr miss rate for demand accesses
+system.cpu.l2cache.demand_mshr_misses          563673                       # number of demand (read+write) MSHR misses
 system.cpu.l2cache.fast_writes                      0                       # number of fast writes performed
 system.cpu.l2cache.mshr_cap_events                  0                       # number of times MSHR cap was activated
 system.cpu.l2cache.no_allocate_misses               0                       # Number of misses that were no-allocate
-system.cpu.l2cache.occ_%::0                  0.234251                       # Average percentage of cache occupancy
-system.cpu.l2cache.occ_%::1                  0.418210                       # Average percentage of cache occupancy
-system.cpu.l2cache.occ_blocks::0          7675.941579                       # Average occupied blocks per context
-system.cpu.l2cache.occ_blocks::1         13703.908999                       # Average occupied blocks per context
-system.cpu.l2cache.overall_accesses           2526298                       # number of overall (read+write) accesses
-system.cpu.l2cache.overall_avg_miss_latency 34200.604162                       # average overall miss latency
-system.cpu.l2cache.overall_avg_mshr_miss_latency 31002.178254                       # average overall mshr miss latency
+system.cpu.l2cache.occ_%::0                  0.213694                       # Average percentage of cache occupancy
+system.cpu.l2cache.occ_%::1                  0.433705                       # Average percentage of cache occupancy
+system.cpu.l2cache.occ_blocks::0          7002.339473                       # Average occupied blocks per context
+system.cpu.l2cache.occ_blocks::1         14211.631717                       # Average occupied blocks per context
+system.cpu.l2cache.overall_accesses           2519527                       # number of overall (read+write) accesses
+system.cpu.l2cache.overall_avg_miss_latency 34208.290090                       # average overall miss latency
+system.cpu.l2cache.overall_avg_mshr_miss_latency 31002.276142                       # average overall mshr miss latency
 system.cpu.l2cache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
-system.cpu.l2cache.overall_hits               1945328                       # number of overall hits
-system.cpu.l2cache.overall_miss_latency   19869525000                       # number of overall miss cycles
-system.cpu.l2cache.overall_miss_rate         0.229969                       # miss rate for overall accesses
-system.cpu.l2cache.overall_misses              580970                       # number of overall misses
+system.cpu.l2cache.overall_hits               1955854                       # number of overall hits
+system.cpu.l2cache.overall_miss_latency   19282289500                       # number of overall miss cycles
+system.cpu.l2cache.overall_miss_rate         0.223722                       # miss rate for overall accesses
+system.cpu.l2cache.overall_misses              563673                       # number of overall misses
 system.cpu.l2cache.overall_mshr_hits                0                       # number of overall MSHR hits
-system.cpu.l2cache.overall_mshr_miss_latency  18011335500                       # number of overall MSHR miss cycles
-system.cpu.l2cache.overall_mshr_miss_rate     0.229969                       # mshr miss rate for overall accesses
-system.cpu.l2cache.overall_mshr_misses         580970                       # number of overall MSHR misses
+system.cpu.l2cache.overall_mshr_miss_latency  17475146000                       # number of overall MSHR miss cycles
+system.cpu.l2cache.overall_mshr_miss_rate     0.223722                       # mshr miss rate for overall accesses
+system.cpu.l2cache.overall_mshr_misses         563673                       # number of overall MSHR misses
 system.cpu.l2cache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
 system.cpu.l2cache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.l2cache.replacements                570217                       # number of replacements
-system.cpu.l2cache.sampled_refs                589293                       # Sample count of references to valid blocks.
+system.cpu.l2cache.replacements                553099                       # number of replacements
+system.cpu.l2cache.sampled_refs                571950                       # Sample count of references to valid blocks.
 system.cpu.l2cache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
-system.cpu.l2cache.tagsinuse             21379.850577                       # Cycle average of tags in use
-system.cpu.l2cache.total_refs                 3154731                       # Total number of references to valid blocks.
-system.cpu.l2cache.warmup_cycle          377230361000                       # Cycle when the warmup percentage was hit.
-system.cpu.l2cache.writebacks                  411577                       # number of writebacks
-system.cpu.memDep0.conflictingLoads         169465698                       # Number of conflicting loads.
-system.cpu.memDep0.conflictingStores         40622935                       # Number of conflicting stores.
-system.cpu.memDep0.insertedLoads            454402470                       # Number of loads inserted to the mem dependence unit.
-system.cpu.memDep0.insertedStores           170547499                       # Number of stores inserted to the mem dependence unit.
-system.cpu.misc_regfile_reads               909615360                       # number of misc regfile reads
-system.cpu.numCycles                       1396982052                       # number of cpu cycles simulated
+system.cpu.l2cache.tagsinuse             21213.971190                       # Cycle average of tags in use
+system.cpu.l2cache.total_refs                 3090858                       # Total number of references to valid blocks.
+system.cpu.l2cache.warmup_cycle          329890014000                       # Cycle when the warmup percentage was hit.
+system.cpu.l2cache.writebacks                  404346                       # number of writebacks
+system.cpu.memDep0.conflictingLoads         432040536                       # Number of conflicting loads.
+system.cpu.memDep0.conflictingStores        167867809                       # Number of conflicting stores.
+system.cpu.memDep0.insertedLoads            598780500                       # Number of loads inserted to the mem dependence unit.
+system.cpu.memDep0.insertedStores           227724252                       # Number of stores inserted to the mem dependence unit.
+system.cpu.misc_regfile_reads              1024928879                       # number of misc regfile reads
+system.cpu.numCycles                       1221905985                       # number of cpu cycles simulated
 system.cpu.numWorkItemsCompleted                    0                       # number of work items this cpu completed
 system.cpu.numWorkItemsStarted                      0                       # number of work items this cpu started
-system.cpu.rename.RENAME:BlockCycles          7556367                       # Number of cycles rename is blocking
-system.cpu.rename.RENAME:CommittedMaps     1427299027                       # Number of HB maps that are committed
-system.cpu.rename.RENAME:IQFullEvents         5884693                       # Number of times rename has blocked due to IQ full
-system.cpu.rename.RENAME:IdleCycles         361176398                       # Number of cycles rename is idle
-system.cpu.rename.RENAME:LSQFullEvents        2156935                       # Number of times rename has blocked due to LSQ full
-system.cpu.rename.RENAME:ROBFullEvents             61                       # Number of times rename has blocked due to ROB full
-system.cpu.rename.RENAME:RenameLookups     4360508954                       # Number of register rename lookups that rename has made
-system.cpu.rename.RENAME:RenamedInsts      1840516856                       # Number of instructions processed by rename
-system.cpu.rename.RENAME:RenamedOperands   1743217369                       # Number of destination operands rename has renamed
-system.cpu.rename.RENAME:RunCycles          971079353                       # Number of cycles rename is running
-system.cpu.rename.RENAME:SquashCycles        39316255                       # Number of cycles rename is squashing
-system.cpu.rename.RENAME:UnblockCycles       11053475                       # Number of cycles rename is unblocking
-system.cpu.rename.RENAME:UndoneMaps         315918342                       # Number of HB maps that are undone due to squashing
-system.cpu.rename.RENAME:fp_rename_lookups          168                       # Number of floating rename lookups
-system.cpu.rename.RENAME:int_rename_lookups   4360508786                       # Number of integer rename lookups
-system.cpu.rename.RENAME:serializeStallCycles         6080                       # count of cycles rename stalled for serializing inst
-system.cpu.rename.RENAME:serializingInsts          557                       # count of serializing insts renamed
-system.cpu.rename.RENAME:skidInsts           18505861                       # count of insts added to the skid buffer
-system.cpu.rename.RENAME:tempSerializingInsts          554                       # count of temporary serializing insts renamed
-system.cpu.rob.rob_reads                   3126877109                       # The number of ROB reads
-system.cpu.rob.rob_writes                  3611419620                       # The number of ROB writes
-system.cpu.timesIdled                          237370                       # Number of times that the entire CPU went into an idle state and unscheduled itself
+system.cpu.rename.RENAME:BlockCycles         64472267                       # Number of cycles rename is blocking
+system.cpu.rename.RENAME:CommittedMaps     1425688721                       # Number of HB maps that are committed
+system.cpu.rename.RENAME:IQFullEvents        52544368                       # Number of times rename has blocked due to IQ full
+system.cpu.rename.RENAME:IdleCycles         479786184                       # Number of cycles rename is idle
+system.cpu.rename.RENAME:LSQFullEvents       82632603                       # Number of times rename has blocked due to LSQ full
+system.cpu.rename.RENAME:ROBFullEvents           8428                       # Number of times rename has blocked due to ROB full
+system.cpu.rename.RENAME:RenameLookups     5772028874                       # Number of register rename lookups that rename has made
+system.cpu.rename.RENAME:RenamedInsts      2456264739                       # Number of instructions processed by rename
+system.cpu.rename.RENAME:RenamedOperands   2290118455                       # Number of destination operands rename has renamed
+system.cpu.rename.RENAME:RunCycles          385614091                       # Number of cycles rename is running
+system.cpu.rename.RENAME:SquashCycles       113949773                       # Number of cycles rename is squashing
+system.cpu.rename.RENAME:UnblockCycles      153477395                       # Number of cycles rename is unblocking
+system.cpu.rename.RENAME:UndoneMaps         864429734                       # Number of HB maps that are undone due to squashing
+system.cpu.rename.RENAME:fp_rename_lookups        19762                       # Number of floating rename lookups
+system.cpu.rename.RENAME:int_rename_lookups   5772009112                       # Number of integer rename lookups
+system.cpu.rename.RENAME:serializeStallCycles        19936                       # count of cycles rename stalled for serializing inst
+system.cpu.rename.RENAME:serializingInsts         2550                       # count of serializing insts renamed
+system.cpu.rename.RENAME:skidInsts          360051799                       # count of insts added to the skid buffer
+system.cpu.rename.RENAME:tempSerializingInsts         2561                       # count of temporary serializing insts renamed
+system.cpu.rob.rob_reads                   3418371032                       # The number of ROB reads
+system.cpu.rob.rob_writes                  4851844016                       # The number of ROB writes
+system.cpu.timesIdled                          625791                       # Number of times that the entire CPU went into an idle state and unscheduled itself
 system.cpu.workload.PROG:num_syscalls             551                       # Number of system calls
 
 ---------- End Simulation Statistics   ----------
index 78a8cbd6c3219bff4035340e5f114e6f7a83e373..f69fd4da6a466683191ebb80dc6f938d5b0c1c0c 100644 (file)
@@ -488,7 +488,7 @@ type=ExeTracer
 [system.cpu.workload]
 type=LiveProcess
 cmd=twolf smred
-cwd=build/X86_SE/tests/fast/long/70.twolf/x86/linux/o3-timing
+cwd=build/X86_SE/tests/opt/long/70.twolf/x86/linux/o3-timing
 egid=100
 env=
 errout=cerr
index 1d17ec2f7e1641ea4c14912b1b22db8fcf939da3..2ac976df68ea4cf3ad241c8193e19bb6b902b18f 100755 (executable)
@@ -5,11 +5,11 @@ The Regents of The University of Michigan
 All Rights Reserved
 
 
-M5 compiled Feb  8 2011 00:58:32
-M5 revision 705a4d351a43 7939 default qtip resforflagsstats.patch tip
-M5 started Feb  8 2011 00:58:34
+M5 compiled Feb 12 2011 02:22:23
+M5 revision 5e76f9de6972 7961 default qtip tip x86branchdetectstats.patch
+M5 started Feb 12 2011 02:22:27
 M5 executing on burrito
-command line: build/X86_SE/m5.fast -d build/X86_SE/tests/fast/long/70.twolf/x86/linux/o3-timing -re tests/run.py build/X86_SE/tests/fast/long/70.twolf/x86/linux/o3-timing
+command line: build/X86_SE/m5.opt -d build/X86_SE/tests/opt/long/70.twolf/x86/linux/o3-timing -re tests/run.py build/X86_SE/tests/opt/long/70.twolf/x86/linux/o3-timing
 Global frequency set at 1000000000000 ticks per second
 info: Entering event queue @ 0.  Starting simulation...
 
@@ -27,4 +27,4 @@ info: Increasing stack size by one page.
  76  77  78  79  80  81  82  83  84  85  86  87  88  89  90 
  91  92  93  94  95  96  97  98  99 100 101 102 103 104 105 
 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 
-122 123 124 Exiting @ tick 114045138500 because target called exit()
+122 123 124 Exiting @ tick 108875474000 because target called exit()
index 6577540a080b765e90e5a7aa6d252d75b188d07d..a77afc84962b1e7913b7de6644c6fd03707fda61 100644 (file)
@@ -1,41 +1,41 @@
 
 ---------- Begin Simulation Statistics ----------
-host_inst_rate                                 187440                       # Simulator instruction rate (inst/s)
-host_mem_usage                                 240848                       # Number of bytes of host memory used
-host_seconds                                  1180.98                       # Real time elapsed on the host
-host_tick_rate                               96568147                       # Simulator tick rate (ticks/s)
+host_inst_rate                                  92938                       # Simulator instruction rate (inst/s)
+host_mem_usage                                 245208                       # Number of bytes of host memory used
+host_seconds                                  2381.84                       # Real time elapsed on the host
+host_tick_rate                               45710653                       # Simulator tick rate (ticks/s)
 sim_freq                                 1000000000000                       # Frequency of simulated ticks
 sim_insts                                   221363017                       # Number of instructions simulated
-sim_seconds                                  0.114045                       # Number of seconds simulated
-sim_ticks                                114045138500                       # Number of ticks simulated
+sim_seconds                                  0.108875                       # Number of seconds simulated
+sim_ticks                                108875474000                       # Number of ticks simulated
 system.cpu.BPredUnit.BTBCorrect                     0                       # Number of correct BTB predictions (this stat may not work properly.
-system.cpu.BPredUnit.BTBHits                 15975516                       # Number of BTB hits
-system.cpu.BPredUnit.BTBLookups              17934192                       # Number of BTB lookups
+system.cpu.BPredUnit.BTBHits                 19725800                       # Number of BTB hits
+system.cpu.BPredUnit.BTBLookups              22620341                       # Number of BTB lookups
 system.cpu.BPredUnit.RASInCorrect                   0                       # Number of incorrect RAS predictions.
-system.cpu.BPredUnit.condIncorrect            3581786                       # Number of conditional branches incorrect
-system.cpu.BPredUnit.condPredicted           18022710                       # Number of conditional branches predicted
-system.cpu.BPredUnit.lookups                 18022710                       # Number of BP lookups
+system.cpu.BPredUnit.condIncorrect            3050205                       # Number of conditional branches incorrect
+system.cpu.BPredUnit.condPredicted           25317132                       # Number of conditional branches predicted
+system.cpu.BPredUnit.lookups                 25317132                       # Number of BP lookups
 system.cpu.BPredUnit.usedRAS                        0                       # Number of times the RAS was used to get a target.
 system.cpu.commit.COM:branches               12326943                       # Number of branches committed
-system.cpu.commit.COM:bw_lim_events            723634                       # number cycles where commit BW limit reached
+system.cpu.commit.COM:bw_lim_events           2257656                       # number cycles where commit BW limit reached
 system.cpu.commit.COM:bw_limited                    0                       # number of insts not committed due to BW limits
-system.cpu.commit.COM:committed_per_cycle::samples    220177428                       # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::mean     1.005385                       # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::stdev     1.254706                       # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::samples    193712128                       # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::mean     1.142742                       # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::stdev     1.492040                       # Number of insts commited each cycle
 system.cpu.commit.COM:committed_per_cycle::underflows            0      0.00%      0.00% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::0     88641889     40.26%     40.26% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::1     86561337     39.31%     79.57% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::2     21386723      9.71%     89.29% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::3     12188145      5.54%     94.82% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::4      6588488      2.99%     97.82% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::5      2070275      0.94%     98.76% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::6      1149159      0.52%     99.28% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::7       867778      0.39%     99.67% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::8       723634      0.33%    100.00% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::0     76077426     39.27%     39.27% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::1     72463860     37.41%     76.68% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::2     18818378      9.71%     86.40% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::3     12600057      6.50%     92.90% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::4      5960288      3.08%     95.98% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::5      2688234      1.39%     97.37% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::6      1804943      0.93%     98.30% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::7      1041286      0.54%     98.83% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::8      2257656      1.17%    100.00% # Number of insts commited each cycle
 system.cpu.commit.COM:committed_per_cycle::overflows            0      0.00%    100.00% # Number of insts commited each cycle
 system.cpu.commit.COM:committed_per_cycle::min_value            0                       # Number of insts commited each cycle
 system.cpu.commit.COM:committed_per_cycle::max_value            8                       # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::total    220177428                       # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::total    193712128                       # Number of insts commited each cycle
 system.cpu.commit.COM:count                 221363017                       # Number of instructions committed
 system.cpu.commit.COM:fp_insts                2162459                       # Number of committed floating point instructions.
 system.cpu.commit.COM:function_calls                0                       # Number of function calls committed.
@@ -44,423 +44,424 @@ system.cpu.commit.COM:loads                  56649590                       # Nu
 system.cpu.commit.COM:membars                       0                       # Number of memory barriers committed
 system.cpu.commit.COM:refs                   77165306                       # Number of memory references committed
 system.cpu.commit.COM:swp_count                     0                       # Number of s/w prefetches committed
-system.cpu.commit.branchMispredicts           3581794                       # The number of times a branch was mispredicted
+system.cpu.commit.branchMispredicts           3050238                       # The number of times a branch was mispredicted
 system.cpu.commit.commitCommittedInsts      221363017                       # The number of committed instructions
 system.cpu.commit.commitNonSpecStalls            1246                       # The number of times commit has been forced to stall to communicate backwards
-system.cpu.commit.commitSquashedInsts        48027716                       # The number of squashed insts skipped by commit
+system.cpu.commit.commitSquashedInsts       180173936                       # The number of squashed insts skipped by commit
 system.cpu.committedInsts                   221363017                       # Number of Instructions Simulated
 system.cpu.committedInsts_total             221363017                       # Number of Instructions Simulated
-system.cpu.cpi                               1.030390                       # CPI: Cycles Per Instruction
-system.cpu.cpi_total                         1.030390                       # CPI: Total CPI of All Threads
-system.cpu.dcache.ReadReq_accesses           50422643                       # number of ReadReq accesses(hits+misses)
-system.cpu.dcache.ReadReq_avg_miss_latency 32842.809365                       # average ReadReq miss latency
-system.cpu.dcache.ReadReq_avg_mshr_miss_latency 34433.615819                       # average ReadReq mshr miss latency
-system.cpu.dcache.ReadReq_hits               50422045                       # number of ReadReq hits
-system.cpu.dcache.ReadReq_miss_latency       19640000                       # number of ReadReq miss cycles
-system.cpu.dcache.ReadReq_miss_rate          0.000012                       # miss rate for ReadReq accesses
-system.cpu.dcache.ReadReq_misses                  598                       # number of ReadReq misses
-system.cpu.dcache.ReadReq_mshr_hits               244                       # number of ReadReq MSHR hits
-system.cpu.dcache.ReadReq_mshr_miss_latency     12189500                       # number of ReadReq MSHR miss cycles
-system.cpu.dcache.ReadReq_mshr_miss_rate     0.000007                       # mshr miss rate for ReadReq accesses
-system.cpu.dcache.ReadReq_mshr_misses             354                       # number of ReadReq MSHR misses
+system.cpu.cpi                               0.983683                       # CPI: Cycles Per Instruction
+system.cpu.cpi_total                         0.983683                       # CPI: Total CPI of All Threads
+system.cpu.dcache.ReadReq_accesses           50495037                       # number of ReadReq accesses(hits+misses)
+system.cpu.dcache.ReadReq_avg_miss_latency 33300.295858                       # average ReadReq miss latency
+system.cpu.dcache.ReadReq_avg_mshr_miss_latency 34031.250000                       # average ReadReq mshr miss latency
+system.cpu.dcache.ReadReq_hits               50494361                       # number of ReadReq hits
+system.cpu.dcache.ReadReq_miss_latency       22511000                       # number of ReadReq miss cycles
+system.cpu.dcache.ReadReq_miss_rate          0.000013                       # miss rate for ReadReq accesses
+system.cpu.dcache.ReadReq_misses                  676                       # number of ReadReq misses
+system.cpu.dcache.ReadReq_mshr_hits               292                       # number of ReadReq MSHR hits
+system.cpu.dcache.ReadReq_mshr_miss_latency     13068000                       # number of ReadReq MSHR miss cycles
+system.cpu.dcache.ReadReq_mshr_miss_rate     0.000008                       # mshr miss rate for ReadReq accesses
+system.cpu.dcache.ReadReq_mshr_misses             384                       # number of ReadReq MSHR misses
 system.cpu.dcache.WriteReq_accesses          20515730                       # number of WriteReq accesses(hits+misses)
-system.cpu.dcache.WriteReq_avg_miss_latency 26406.061747                       # average WriteReq miss latency
-system.cpu.dcache.WriteReq_avg_mshr_miss_latency 35285.532995                       # average WriteReq mshr miss latency
-system.cpu.dcache.WriteReq_hits              20510418                       # number of WriteReq hits
-system.cpu.dcache.WriteReq_miss_latency     140269000                       # number of WriteReq miss cycles
-system.cpu.dcache.WriteReq_miss_rate         0.000259                       # miss rate for WriteReq accesses
-system.cpu.dcache.WriteReq_misses                5312                       # number of WriteReq misses
-system.cpu.dcache.WriteReq_mshr_hits             3736                       # number of WriteReq MSHR hits
-system.cpu.dcache.WriteReq_mshr_miss_latency     55610000                       # number of WriteReq MSHR miss cycles
-system.cpu.dcache.WriteReq_mshr_miss_rate     0.000077                       # mshr miss rate for WriteReq accesses
-system.cpu.dcache.WriteReq_mshr_misses           1576                       # number of WriteReq MSHR misses
+system.cpu.dcache.WriteReq_avg_miss_latency 26250.708416                       # average WriteReq miss latency
+system.cpu.dcache.WriteReq_avg_mshr_miss_latency 35437.100894                       # average WriteReq mshr miss latency
+system.cpu.dcache.WriteReq_hits              20508672                       # number of WriteReq hits
+system.cpu.dcache.WriteReq_miss_latency     185277500                       # number of WriteReq miss cycles
+system.cpu.dcache.WriteReq_miss_rate         0.000344                       # miss rate for WriteReq accesses
+system.cpu.dcache.WriteReq_misses                7058                       # number of WriteReq misses
+system.cpu.dcache.WriteReq_mshr_hits             5492                       # number of WriteReq MSHR hits
+system.cpu.dcache.WriteReq_mshr_miss_latency     55494500                       # number of WriteReq MSHR miss cycles
+system.cpu.dcache.WriteReq_mshr_miss_rate     0.000076                       # mshr miss rate for WriteReq accesses
+system.cpu.dcache.WriteReq_mshr_misses           1566                       # number of WriteReq MSHR misses
 system.cpu.dcache.avg_blocked_cycles::no_mshrs     no_value                       # average number of cycles each access was blocked
 system.cpu.dcache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
-system.cpu.dcache.avg_refs               36752.571503                       # Average number of references to valid blocks.
+system.cpu.dcache.avg_refs               36411.811795                       # Average number of references to valid blocks.
 system.cpu.dcache.blocked::no_mshrs                 0                       # number of cycles access was blocked
 system.cpu.dcache.blocked::no_targets               0                       # number of cycles access was blocked
 system.cpu.dcache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.dcache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.dcache.cache_copies                      0                       # number of cache copies performed
-system.cpu.dcache.demand_accesses            70938373                       # number of demand (read+write) accesses
-system.cpu.dcache.demand_avg_miss_latency 27057.360406                       # average overall miss latency
-system.cpu.dcache.demand_avg_mshr_miss_latency 35129.274611                       # average overall mshr miss latency
-system.cpu.dcache.demand_hits                70932463                       # number of demand (read+write) hits
-system.cpu.dcache.demand_miss_latency       159909000                       # number of demand (read+write) miss cycles
-system.cpu.dcache.demand_miss_rate           0.000083                       # miss rate for demand accesses
-system.cpu.dcache.demand_misses                  5910                       # number of demand (read+write) misses
-system.cpu.dcache.demand_mshr_hits               3980                       # number of demand (read+write) MSHR hits
-system.cpu.dcache.demand_mshr_miss_latency     67799500                       # number of demand (read+write) MSHR miss cycles
+system.cpu.dcache.demand_accesses            71010767                       # number of demand (read+write) accesses
+system.cpu.dcache.demand_avg_miss_latency 26866.886475                       # average overall miss latency
+system.cpu.dcache.demand_avg_mshr_miss_latency 35160.256410                       # average overall mshr miss latency
+system.cpu.dcache.demand_hits                71003033                       # number of demand (read+write) hits
+system.cpu.dcache.demand_miss_latency       207788500                       # number of demand (read+write) miss cycles
+system.cpu.dcache.demand_miss_rate           0.000109                       # miss rate for demand accesses
+system.cpu.dcache.demand_misses                  7734                       # number of demand (read+write) misses
+system.cpu.dcache.demand_mshr_hits               5784                       # number of demand (read+write) MSHR hits
+system.cpu.dcache.demand_mshr_miss_latency     68562500                       # number of demand (read+write) MSHR miss cycles
 system.cpu.dcache.demand_mshr_miss_rate      0.000027                       # mshr miss rate for demand accesses
-system.cpu.dcache.demand_mshr_misses             1930                       # number of demand (read+write) MSHR misses
+system.cpu.dcache.demand_mshr_misses             1950                       # number of demand (read+write) MSHR misses
 system.cpu.dcache.fast_writes                       0                       # number of fast writes performed
 system.cpu.dcache.mshr_cap_events                   0                       # number of times MSHR cap was activated
 system.cpu.dcache.no_allocate_misses                0                       # Number of misses that were no-allocate
-system.cpu.dcache.occ_%::0                   0.336507                       # Average percentage of cache occupancy
-system.cpu.dcache.occ_blocks::0           1378.331851                       # Average occupied blocks per context
-system.cpu.dcache.overall_accesses           70938373                       # number of overall (read+write) accesses
-system.cpu.dcache.overall_avg_miss_latency 27057.360406                       # average overall miss latency
-system.cpu.dcache.overall_avg_mshr_miss_latency 35129.274611                       # average overall mshr miss latency
+system.cpu.dcache.occ_%::0                   0.340706                       # Average percentage of cache occupancy
+system.cpu.dcache.occ_blocks::0           1395.531138                       # Average occupied blocks per context
+system.cpu.dcache.overall_accesses           71010767                       # number of overall (read+write) accesses
+system.cpu.dcache.overall_avg_miss_latency 26866.886475                       # average overall miss latency
+system.cpu.dcache.overall_avg_mshr_miss_latency 35160.256410                       # average overall mshr miss latency
 system.cpu.dcache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
-system.cpu.dcache.overall_hits               70932463                       # number of overall hits
-system.cpu.dcache.overall_miss_latency      159909000                       # number of overall miss cycles
-system.cpu.dcache.overall_miss_rate          0.000083                       # miss rate for overall accesses
-system.cpu.dcache.overall_misses                 5910                       # number of overall misses
-system.cpu.dcache.overall_mshr_hits              3980                       # number of overall MSHR hits
-system.cpu.dcache.overall_mshr_miss_latency     67799500                       # number of overall MSHR miss cycles
+system.cpu.dcache.overall_hits               71003033                       # number of overall hits
+system.cpu.dcache.overall_miss_latency      207788500                       # number of overall miss cycles
+system.cpu.dcache.overall_miss_rate          0.000109                       # miss rate for overall accesses
+system.cpu.dcache.overall_misses                 7734                       # number of overall misses
+system.cpu.dcache.overall_mshr_hits              5784                       # number of overall MSHR hits
+system.cpu.dcache.overall_mshr_miss_latency     68562500                       # number of overall MSHR miss cycles
 system.cpu.dcache.overall_mshr_miss_rate     0.000027                       # mshr miss rate for overall accesses
-system.cpu.dcache.overall_mshr_misses            1930                       # number of overall MSHR misses
+system.cpu.dcache.overall_mshr_misses            1950                       # number of overall MSHR misses
 system.cpu.dcache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
 system.cpu.dcache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.dcache.replacements                     47                       # number of replacements
-system.cpu.dcache.sampled_refs                   1930                       # Sample count of references to valid blocks.
+system.cpu.dcache.replacements                     48                       # number of replacements
+system.cpu.dcache.sampled_refs                   1950                       # Sample count of references to valid blocks.
 system.cpu.dcache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
-system.cpu.dcache.tagsinuse               1378.331851                       # Cycle average of tags in use
-system.cpu.dcache.total_refs                 70932463                       # Total number of references to valid blocks.
+system.cpu.dcache.tagsinuse               1395.531138                       # Cycle average of tags in use
+system.cpu.dcache.total_refs                 71003033                       # Total number of references to valid blocks.
 system.cpu.dcache.warmup_cycle                      0                       # Cycle when the warmup percentage was hit.
 system.cpu.dcache.writebacks                       10                       # number of writebacks
-system.cpu.decode.DECODE:BlockedCycles        1914286                       # Number of cycles decode is blocked
-system.cpu.decode.DECODE:DecodedInsts       286005423                       # Number of instructions handled by decode
-system.cpu.decode.DECODE:IdleCycles          48312658                       # Number of cycles decode is idle
-system.cpu.decode.DECODE:RunCycles          169297181                       # Number of cycles decode is running
-system.cpu.decode.DECODE:SquashCycles         7787199                       # Number of cycles decode is squashing
-system.cpu.decode.DECODE:UnblockCycles         653303                       # Number of cycles decode is unblocking
-system.cpu.fetch.Branches                    18022710                       # Number of branches that fetch encountered
-system.cpu.fetch.CacheLines                  18867666                       # Number of cache lines fetched
-system.cpu.fetch.Cycles                     179995924                       # Number of cycles fetch has run and was not squashing or blocked
-system.cpu.fetch.IcacheSquashes                191272                       # Number of outstanding Icache misses that were squashed
-system.cpu.fetch.Insts                      169328996                       # Number of instructions fetch has processed
-system.cpu.fetch.MiscStallCycles                   11                       # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs
-system.cpu.fetch.SquashCycles                 3686154                       # Number of cycles fetch has spent squashing
-system.cpu.fetch.branchRate                  0.079016                       # Number of branch fetches per cycle
-system.cpu.fetch.icacheStallCycles           18867666                       # Number of cycles fetch is stalled on an Icache miss
-system.cpu.fetch.predictedBranches           15975516                       # Number of branches that fetch has predicted taken
-system.cpu.fetch.rate                        0.742377                       # Number of inst fetches per cycle
-system.cpu.fetch.rateDist::samples          227964627                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::mean              1.282286                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::stdev             1.366402                       # Number of instructions fetched each cycle (Total)
+system.cpu.decode.DECODE:BlockedCycles       58788191                       # Number of cycles decode is blocked
+system.cpu.decode.DECODE:DecodedInsts       426377378                       # Number of instructions handled by decode
+system.cpu.decode.DECODE:IdleCycles          67892396                       # Number of cycles decode is idle
+system.cpu.decode.DECODE:RunCycles           61042516                       # Number of cycles decode is running
+system.cpu.decode.DECODE:SquashCycles        23949638                       # Number of cycles decode is squashing
+system.cpu.decode.DECODE:UnblockCycles        5989025                       # Number of cycles decode is unblocking
+system.cpu.fetch.Branches                    25317132                       # Number of branches that fetch encountered
+system.cpu.fetch.CacheLines                  27858568                       # Number of cache lines fetched
+system.cpu.fetch.Cycles                      70494302                       # Number of cycles fetch has run and was not squashing or blocked
+system.cpu.fetch.IcacheSquashes                451015                       # Number of outstanding Icache misses that were squashed
+system.cpu.fetch.Insts                      267008364                       # Number of instructions fetch has processed
+system.cpu.fetch.MiscStallCycles                   61                       # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs
+system.cpu.fetch.SquashCycles                 3227425                       # Number of cycles fetch has spent squashing
+system.cpu.fetch.branchRate                  0.116266                       # Number of branch fetches per cycle
+system.cpu.fetch.icacheStallCycles           27858568                       # Number of cycles fetch is stalled on an Icache miss
+system.cpu.fetch.predictedBranches           19725800                       # Number of branches that fetch has predicted taken
+system.cpu.fetch.rate                        1.226210                       # Number of inst fetches per cycle
+system.cpu.fetch.rateDist::samples          217661766                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::mean              2.006543                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::stdev             3.224025                       # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::underflows               0      0.00%      0.00% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::0                 54957212     24.11%     24.11% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::1                110607036     48.52%     72.63% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::2                 34696842     15.22%     87.85% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::3                 19348316      8.49%     96.33% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::4                  1875902      0.82%     97.16% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::5                  1062317      0.47%     97.62% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::6                   939798      0.41%     98.04% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::7                     1341      0.00%     98.04% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::8                  4475863      1.96%    100.00% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::0                148998369     68.45%     68.45% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::1                  3780164      1.74%     70.19% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::2                  3170889      1.46%     71.65% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::3                  4293321      1.97%     73.62% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::4                  4655999      2.14%     75.76% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::5                  4463846      2.05%     77.81% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::6                  5161555      2.37%     80.18% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::7                  3267808      1.50%     81.68% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::8                 39869815     18.32%    100.00% # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::overflows                0      0.00%    100.00% # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::min_value                0                       # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::max_value                8                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::total            227964627                       # Number of instructions fetched each cycle (Total)
-system.cpu.fp_regfile_reads                   3211744                       # number of floating regfile reads
-system.cpu.fp_regfile_writes                  2048533                       # number of floating regfile writes
-system.cpu.icache.ReadReq_accesses           18867666                       # number of ReadReq accesses(hits+misses)
-system.cpu.icache.ReadReq_avg_miss_latency 25730.265551                       # average ReadReq miss latency
-system.cpu.icache.ReadReq_avg_mshr_miss_latency 22379.751901                       # average ReadReq mshr miss latency
-system.cpu.icache.ReadReq_hits               18862168                       # number of ReadReq hits
-system.cpu.icache.ReadReq_miss_latency      141465000                       # number of ReadReq miss cycles
-system.cpu.icache.ReadReq_miss_rate          0.000291                       # miss rate for ReadReq accesses
-system.cpu.icache.ReadReq_misses                 5498                       # number of ReadReq misses
-system.cpu.icache.ReadReq_mshr_hits               500                       # number of ReadReq MSHR hits
-system.cpu.icache.ReadReq_mshr_miss_latency    111854000                       # number of ReadReq MSHR miss cycles
-system.cpu.icache.ReadReq_mshr_miss_rate     0.000265                       # mshr miss rate for ReadReq accesses
-system.cpu.icache.ReadReq_mshr_misses            4998                       # number of ReadReq MSHR misses
+system.cpu.fetch.rateDist::total            217661766                       # Number of instructions fetched each cycle (Total)
+system.cpu.fp_regfile_reads                   3513078                       # number of floating regfile reads
+system.cpu.fp_regfile_writes                  2177890                       # number of floating regfile writes
+system.cpu.icache.ReadReq_accesses           27858568                       # number of ReadReq accesses(hits+misses)
+system.cpu.icache.ReadReq_avg_miss_latency 25516.664059                       # average ReadReq miss latency
+system.cpu.icache.ReadReq_avg_mshr_miss_latency 22464.816190                       # average ReadReq mshr miss latency
+system.cpu.icache.ReadReq_hits               27852177                       # number of ReadReq hits
+system.cpu.icache.ReadReq_miss_latency      163077000                       # number of ReadReq miss cycles
+system.cpu.icache.ReadReq_miss_rate          0.000229                       # miss rate for ReadReq accesses
+system.cpu.icache.ReadReq_misses                 6391                       # number of ReadReq misses
+system.cpu.icache.ReadReq_mshr_hits              1005                       # number of ReadReq MSHR hits
+system.cpu.icache.ReadReq_mshr_miss_latency    120995500                       # number of ReadReq MSHR miss cycles
+system.cpu.icache.ReadReq_mshr_miss_rate     0.000193                       # mshr miss rate for ReadReq accesses
+system.cpu.icache.ReadReq_mshr_misses            5386                       # number of ReadReq MSHR misses
 system.cpu.icache.avg_blocked_cycles::no_mshrs     no_value                       # average number of cycles each access was blocked
 system.cpu.icache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
-system.cpu.icache.avg_refs                3774.698419                       # Average number of references to valid blocks.
+system.cpu.icache.avg_refs                5171.217416                       # Average number of references to valid blocks.
 system.cpu.icache.blocked::no_mshrs                 0                       # number of cycles access was blocked
 system.cpu.icache.blocked::no_targets               0                       # number of cycles access was blocked
 system.cpu.icache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.icache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.icache.cache_copies                      0                       # number of cache copies performed
-system.cpu.icache.demand_accesses            18867666                       # number of demand (read+write) accesses
-system.cpu.icache.demand_avg_miss_latency 25730.265551                       # average overall miss latency
-system.cpu.icache.demand_avg_mshr_miss_latency 22379.751901                       # average overall mshr miss latency
-system.cpu.icache.demand_hits                18862168                       # number of demand (read+write) hits
-system.cpu.icache.demand_miss_latency       141465000                       # number of demand (read+write) miss cycles
-system.cpu.icache.demand_miss_rate           0.000291                       # miss rate for demand accesses
-system.cpu.icache.demand_misses                  5498                       # number of demand (read+write) misses
-system.cpu.icache.demand_mshr_hits                500                       # number of demand (read+write) MSHR hits
-system.cpu.icache.demand_mshr_miss_latency    111854000                       # number of demand (read+write) MSHR miss cycles
-system.cpu.icache.demand_mshr_miss_rate      0.000265                       # mshr miss rate for demand accesses
-system.cpu.icache.demand_mshr_misses             4998                       # number of demand (read+write) MSHR misses
+system.cpu.icache.demand_accesses            27858568                       # number of demand (read+write) accesses
+system.cpu.icache.demand_avg_miss_latency 25516.664059                       # average overall miss latency
+system.cpu.icache.demand_avg_mshr_miss_latency 22464.816190                       # average overall mshr miss latency
+system.cpu.icache.demand_hits                27852177                       # number of demand (read+write) hits
+system.cpu.icache.demand_miss_latency       163077000                       # number of demand (read+write) miss cycles
+system.cpu.icache.demand_miss_rate           0.000229                       # miss rate for demand accesses
+system.cpu.icache.demand_misses                  6391                       # number of demand (read+write) misses
+system.cpu.icache.demand_mshr_hits               1005                       # number of demand (read+write) MSHR hits
+system.cpu.icache.demand_mshr_miss_latency    120995500                       # number of demand (read+write) MSHR miss cycles
+system.cpu.icache.demand_mshr_miss_rate      0.000193                       # mshr miss rate for demand accesses
+system.cpu.icache.demand_mshr_misses             5386                       # number of demand (read+write) MSHR misses
 system.cpu.icache.fast_writes                       0                       # number of fast writes performed
 system.cpu.icache.mshr_cap_events                   0                       # number of times MSHR cap was activated
 system.cpu.icache.no_allocate_misses                0                       # Number of misses that were no-allocate
-system.cpu.icache.occ_%::0                   0.745890                       # Average percentage of cache occupancy
-system.cpu.icache.occ_blocks::0           1527.583314                       # Average occupied blocks per context
-system.cpu.icache.overall_accesses           18867666                       # number of overall (read+write) accesses
-system.cpu.icache.overall_avg_miss_latency 25730.265551                       # average overall miss latency
-system.cpu.icache.overall_avg_mshr_miss_latency 22379.751901                       # average overall mshr miss latency
+system.cpu.icache.occ_%::0                   0.783470                       # Average percentage of cache occupancy
+system.cpu.icache.occ_blocks::0           1604.546925                       # Average occupied blocks per context
+system.cpu.icache.overall_accesses           27858568                       # number of overall (read+write) accesses
+system.cpu.icache.overall_avg_miss_latency 25516.664059                       # average overall miss latency
+system.cpu.icache.overall_avg_mshr_miss_latency 22464.816190                       # average overall mshr miss latency
 system.cpu.icache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
-system.cpu.icache.overall_hits               18862168                       # number of overall hits
-system.cpu.icache.overall_miss_latency      141465000                       # number of overall miss cycles
-system.cpu.icache.overall_miss_rate          0.000291                       # miss rate for overall accesses
-system.cpu.icache.overall_misses                 5498                       # number of overall misses
-system.cpu.icache.overall_mshr_hits               500                       # number of overall MSHR hits
-system.cpu.icache.overall_mshr_miss_latency    111854000                       # number of overall MSHR miss cycles
-system.cpu.icache.overall_mshr_miss_rate     0.000265                       # mshr miss rate for overall accesses
-system.cpu.icache.overall_mshr_misses            4998                       # number of overall MSHR misses
+system.cpu.icache.overall_hits               27852177                       # number of overall hits
+system.cpu.icache.overall_miss_latency      163077000                       # number of overall miss cycles
+system.cpu.icache.overall_miss_rate          0.000229                       # miss rate for overall accesses
+system.cpu.icache.overall_misses                 6391                       # number of overall misses
+system.cpu.icache.overall_mshr_hits              1005                       # number of overall MSHR hits
+system.cpu.icache.overall_mshr_miss_latency    120995500                       # number of overall MSHR miss cycles
+system.cpu.icache.overall_mshr_miss_rate     0.000193                       # mshr miss rate for overall accesses
+system.cpu.icache.overall_mshr_misses            5386                       # number of overall MSHR misses
 system.cpu.icache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
 system.cpu.icache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.icache.replacements                   3094                       # number of replacements
-system.cpu.icache.sampled_refs                   4997                       # Sample count of references to valid blocks.
+system.cpu.icache.replacements                   3428                       # number of replacements
+system.cpu.icache.sampled_refs                   5386                       # Sample count of references to valid blocks.
 system.cpu.icache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
-system.cpu.icache.tagsinuse               1527.583314                       # Cycle average of tags in use
-system.cpu.icache.total_refs                 18862168                       # Total number of references to valid blocks.
+system.cpu.icache.tagsinuse               1604.546925                       # Cycle average of tags in use
+system.cpu.icache.total_refs                 27852177                       # Total number of references to valid blocks.
 system.cpu.icache.warmup_cycle                      0                       # Cycle when the warmup percentage was hit.
 system.cpu.icache.writebacks                        0                       # number of writebacks
-system.cpu.idleCycles                          125651                       # Total number of cycles that the CPU has spent unscheduled due to idling
-system.cpu.iew.EXEC:branches                 13177188                       # Number of branches executed
+system.cpu.idleCycles                           89183                       # Total number of cycles that the CPU has spent unscheduled due to idling
+system.cpu.iew.EXEC:branches                 15799905                       # Number of branches executed
 system.cpu.iew.EXEC:nop                             0                       # number of nop insts executed
-system.cpu.iew.EXEC:rate                     1.062789                       # Inst execution rate
-system.cpu.iew.EXEC:refs                     86183722                       # number of memory reference insts executed
-system.cpu.iew.EXEC:stores                   21962366                       # Number of stores executed
+system.cpu.iew.EXEC:rate                     1.276995                       # Inst execution rate
+system.cpu.iew.EXEC:refs                     89573185                       # number of memory reference insts executed
+system.cpu.iew.EXEC:stores                   22888685                       # Number of stores executed
 system.cpu.iew.EXEC:swp                             0                       # number of swp insts executed
-system.cpu.iew.WB:consumers                 296340219                       # num instructions consuming a value
-system.cpu.iew.WB:count                     239588905                       # cumulative count of insts written-back
-system.cpu.iew.WB:fanout                     0.644617                       # average fanout of values written-back
+system.cpu.iew.WB:consumers                 372933305                       # num instructions consuming a value
+system.cpu.iew.WB:count                     276026292                       # cumulative count of insts written-back
+system.cpu.iew.WB:fanout                     0.598611                       # average fanout of values written-back
 system.cpu.iew.WB:penalized                         0                       # number of instrctions required to write to 'other' IQ
 system.cpu.iew.WB:penalized_rate                    0                       # fraction of instructions written-back that wrote to 'other' IQ
-system.cpu.iew.WB:producers                 191026075                       # num instructions producing a value
-system.cpu.iew.WB:rate                       1.050413                       # insts written-back per cycle
-system.cpu.iew.WB:sent                      240106417                       # cumulative count of insts sent to commit
-system.cpu.iew.branchMispredicts              3659082                       # Number of branch mispredicts detected at execute
-system.cpu.iew.iewBlockCycles                    1291                       # Number of cycles IEW is blocking
-system.cpu.iew.iewDispLoadInsts              69776556                       # Number of dispatched load instructions
-system.cpu.iew.iewDispNonSpecInsts               1273                       # Number of dispatched non-speculative instructions
-system.cpu.iew.iewDispSquashedInsts           2389686                       # Number of squashed instructions skipped by dispatch
-system.cpu.iew.iewDispStoreInsts             24137923                       # Number of dispatched store instructions
-system.cpu.iew.iewDispatchedInsts           269390730                       # Number of instructions dispatched to IQ
-system.cpu.iew.iewExecLoadInsts              64221356                       # Number of load instructions executed
-system.cpu.iew.iewExecSquashedInsts           3582148                       # Number of squashed instructions skipped in execute
-system.cpu.iew.iewExecutedInsts             242411882                       # Number of executed instructions
-system.cpu.iew.iewIQFullEvents                     27                       # Number of times the IQ has become full, causing a stall
+system.cpu.iew.WB:producers                 223241922                       # num instructions producing a value
+system.cpu.iew.WB:rate                       1.267624                       # insts written-back per cycle
+system.cpu.iew.WB:sent                      277033647                       # cumulative count of insts sent to commit
+system.cpu.iew.branchMispredicts              3251135                       # Number of branch mispredicts detected at execute
+system.cpu.iew.iewBlockCycles                  619969                       # Number of cycles IEW is blocking
+system.cpu.iew.iewDispLoadInsts             106923422                       # Number of dispatched load instructions
+system.cpu.iew.iewDispNonSpecInsts               1424                       # Number of dispatched non-speculative instructions
+system.cpu.iew.iewDispSquashedInsts            171683                       # Number of squashed instructions skipped by dispatch
+system.cpu.iew.iewDispStoreInsts             37463806                       # Number of dispatched store instructions
+system.cpu.iew.iewDispatchedInsts           401512728                       # Number of instructions dispatched to IQ
+system.cpu.iew.iewExecLoadInsts              66684500                       # Number of load instructions executed
+system.cpu.iew.iewExecSquashedInsts           3440679                       # Number of squashed instructions skipped in execute
+system.cpu.iew.iewExecutedInsts             278066855                       # Number of executed instructions
+system.cpu.iew.iewIQFullEvents                 560615                       # Number of times the IQ has become full, causing a stall
 system.cpu.iew.iewIdleCycles                        0                       # Number of cycles IEW is idle
-system.cpu.iew.iewLSQFullEvents                     0                       # Number of times the LSQ has become full, causing a stall
-system.cpu.iew.iewSquashCycles                7787199                       # Number of cycles IEW is squashing
-system.cpu.iew.iewUnblockCycles                   324                       # Number of cycles IEW is unblocking
+system.cpu.iew.iewLSQFullEvents                 30447                       # Number of times the LSQ has become full, causing a stall
+system.cpu.iew.iewSquashCycles               23949638                       # Number of cycles IEW is squashing
+system.cpu.iew.iewUnblockCycles                623802                       # Number of cycles IEW is unblocking
 system.cpu.iew.lsq.thread.0.blockedLoads            0                       # Number of blocked loads due to partial load-store forwarding
 system.cpu.iew.lsq.thread.0.cacheBlocked            0                       # Number of times an access to memory failed due to the cache being blocked
-system.cpu.iew.lsq.thread.0.forwLoads        13515418                       # Number of loads that had data forwarded from stores
-system.cpu.iew.lsq.thread.0.ignoredResponses       128079                       # Number of memory responses ignored because the instruction is squashed
+system.cpu.iew.lsq.thread.0.forwLoads        15985064                       # Number of loads that had data forwarded from stores
+system.cpu.iew.lsq.thread.0.ignoredResponses        21414                       # Number of memory responses ignored because the instruction is squashed
 system.cpu.iew.lsq.thread.0.invAddrLoads            0                       # Number of loads ignored due to an invalid address
 system.cpu.iew.lsq.thread.0.invAddrSwpfs            0                       # Number of software prefetches ignored due to an invalid address
-system.cpu.iew.lsq.thread.0.memOrderViolation       128891                       # Number of memory ordering violations
-system.cpu.iew.lsq.thread.0.rescheduledLoads        44661                       # Number of loads that were rescheduled
-system.cpu.iew.lsq.thread.0.squashedLoads     13126966                       # Number of loads squashed
-system.cpu.iew.lsq.thread.0.squashedStores      3622207                       # Number of stores squashed
-system.cpu.iew.memOrderViolationEvents         128891                       # Number of memory order violations
-system.cpu.iew.predictedNotTakenIncorrect       152659                       # Number of branches that were predicted not taken incorrectly
-system.cpu.iew.predictedTakenIncorrect        3506423                       # Number of branches that were predicted taken incorrectly
-system.cpu.int_regfile_reads                488710459                       # number of integer regfile reads
-system.cpu.int_regfile_writes               250225793                       # number of integer regfile writes
-system.cpu.ipc                               0.970506                       # IPC: Instructions Per Cycle
-system.cpu.ipc_total                         0.970506                       # IPC: Total IPC of All Threads
-system.cpu.iq.ISSUE:FU_type_0::No_OpClass      1179793      0.48%      0.48% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::IntAlu       155739742     63.31%     63.79% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::IntMult              0      0.00%     63.79% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::IntDiv               0      0.00%     63.79% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatAdd       1520188      0.62%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatCmp             0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatCvt             0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatMult            0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatDiv             0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatSqrt            0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdAdd              0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdAddAcc            0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdAlu              0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdCmp              0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdCvt              0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdMisc             0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdMult             0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdMultAcc            0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdShift            0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdShiftAcc            0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdSqrt             0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatAdd            0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatAlu            0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatCmp            0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatCvt            0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatDiv            0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatMisc            0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatMult            0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatMultAcc            0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatSqrt            0      0.00%     64.41% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::MemRead       65456200     26.61%     91.02% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::MemWrite      22098107      8.98%    100.00% # Type of FU issued
+system.cpu.iew.lsq.thread.0.memOrderViolation       187512                       # Number of memory ordering violations
+system.cpu.iew.lsq.thread.0.rescheduledLoads        45117                       # Number of loads that were rescheduled
+system.cpu.iew.lsq.thread.0.squashedLoads     50273832                       # Number of loads squashed
+system.cpu.iew.lsq.thread.0.squashedStores     16948090                       # Number of stores squashed
+system.cpu.iew.memOrderViolationEvents         187512                       # Number of memory order violations
+system.cpu.iew.predictedNotTakenIncorrect       737658                       # Number of branches that were predicted not taken incorrectly
+system.cpu.iew.predictedTakenIncorrect        2513477                       # Number of branches that were predicted taken incorrectly
+system.cpu.int_regfile_reads                514946932                       # number of integer regfile reads
+system.cpu.int_regfile_writes               284476955                       # number of integer regfile writes
+system.cpu.ipc                               1.016588                       # IPC: Instructions Per Cycle
+system.cpu.ipc_total                         1.016588                       # IPC: Total IPC of All Threads
+system.cpu.iq.ISSUE:FU_type_0::No_OpClass      1195391      0.42%      0.42% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::IntAlu       187555358     66.63%     67.05% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::IntMult              0      0.00%     67.05% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::IntDiv               0      0.00%     67.05% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatAdd       1589850      0.56%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatCmp             0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatCvt             0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatMult            0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatDiv             0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatSqrt            0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdAdd              0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdAddAcc            0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdAlu              0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdCmp              0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdCvt              0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdMisc             0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdMult             0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdMultAcc            0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdShift            0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdShiftAcc            0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdSqrt             0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatAdd            0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatAlu            0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatCmp            0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatCvt            0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatDiv            0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatMisc            0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatMult            0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatMultAcc            0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatSqrt            0      0.00%     67.61% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::MemRead       67998663     24.16%     91.77% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::MemWrite      23168272      8.23%    100.00% # Type of FU issued
 system.cpu.iq.ISSUE:FU_type_0::IprAccess            0      0.00%    100.00% # Type of FU issued
 system.cpu.iq.ISSUE:FU_type_0::InstPrefetch            0      0.00%    100.00% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::total        245994030                       # Type of FU issued
-system.cpu.iq.ISSUE:fu_busy_cnt                166267                       # FU busy when requested
-system.cpu.iq.ISSUE:fu_busy_rate             0.000676                       # FU busy rate (busy events/executed inst)
+system.cpu.iq.ISSUE:FU_type_0::total        281507534                       # Type of FU issued
+system.cpu.iq.ISSUE:fu_busy_cnt               2779468                       # FU busy when requested
+system.cpu.iq.ISSUE:fu_busy_rate             0.009874                       # FU busy rate (busy events/executed inst)
 system.cpu.iq.ISSUE:fu_full::No_OpClass             0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::IntAlu                 4      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::IntMult                0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::IntDiv                 0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatAdd               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatCmp               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatCvt               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatMult              0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatDiv               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatSqrt              0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdAdd                0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdAddAcc             0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdAlu                0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdCmp                0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdCvt                0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdMisc               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdMult               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdMultAcc            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdShift              0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdShiftAcc            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdSqrt               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatAdd            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatAlu            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatCmp            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatCvt            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatDiv            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatMisc            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatMult            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatMultAcc            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatSqrt            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::MemRead           131346     79.00%     79.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::MemWrite           34917     21.00%    100.00% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::IntAlu             58461      2.10%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::IntMult                0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::IntDiv                 0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatAdd               0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatCmp               0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatCvt               0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatMult              0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatDiv               0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatSqrt              0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdAdd                0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdAddAcc             0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdAlu                0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdCmp                0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdCvt                0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdMisc               0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdMult               0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdMultAcc            0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdShift              0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdShiftAcc            0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdSqrt               0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatAdd            0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatAlu            0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatCmp            0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatCvt            0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatDiv            0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatMisc            0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatMult            0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatMultAcc            0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatSqrt            0      0.00%      2.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::MemRead          2334735     84.00%     86.10% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::MemWrite          386272     13.90%    100.00% # attempts to use FU when none available
 system.cpu.iq.ISSUE:fu_full::IprAccess              0      0.00%    100.00% # attempts to use FU when none available
 system.cpu.iq.ISSUE:fu_full::InstPrefetch            0      0.00%    100.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:issued_per_cycle::samples    227964627                       # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::mean     1.079089                       # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::stdev     0.987640                       # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::samples    217661766                       # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::mean     1.293326                       # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::stdev     1.357747                       # Number of insts issued each cycle
 system.cpu.iq.ISSUE:issued_per_cycle::underflows            0      0.00%      0.00% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::0      72171112     31.66%     31.66% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::1      90119003     39.53%     71.19% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::2      46322685     20.32%     91.51% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::3      15038489      6.60%     98.11% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::4       3583873      1.57%     99.68% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::5        613391      0.27%     99.95% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::6        102303      0.04%     99.99% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::7         12243      0.01%    100.00% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::8          1528      0.00%    100.00% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::0      75328501     34.61%     34.61% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::1      67045740     30.80%     65.41% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::2      37681009     17.31%     82.72% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::3      20059185      9.22%     91.94% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::4      11722195      5.39%     97.32% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::5       3737927      1.72%     99.04% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::6       1378220      0.63%     99.67% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::7        597426      0.27%     99.95% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::8        111563      0.05%    100.00% # Number of insts issued each cycle
 system.cpu.iq.ISSUE:issued_per_cycle::overflows            0      0.00%    100.00% # Number of insts issued each cycle
 system.cpu.iq.ISSUE:issued_per_cycle::min_value            0                       # Number of insts issued each cycle
 system.cpu.iq.ISSUE:issued_per_cycle::max_value            8                       # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::total    227964627                       # Number of insts issued each cycle
-system.cpu.iq.ISSUE:rate                     1.078494                       # Inst issue rate
-system.cpu.iq.fp_alu_accesses                 2547074                       # Number of floating point alu accesses
-system.cpu.iq.fp_inst_queue_reads             5090153                       # Number of floating instruction queue reads
-system.cpu.iq.fp_inst_queue_wakeup_accesses      2386799                       # Number of floating instruction queue wakeup accesses
-system.cpu.iq.fp_inst_queue_writes            3193028                       # Number of floating instruction queue writes
-system.cpu.iq.int_alu_accesses              242433430                       # Number of integer alu accesses
-system.cpu.iq.int_inst_queue_reads          715029059                       # Number of integer instruction queue reads
-system.cpu.iq.int_inst_queue_wakeup_accesses    237202106                       # Number of integer instruction queue wakeup accesses
-system.cpu.iq.int_inst_queue_writes         313965679                       # Number of integer instruction queue writes
-system.cpu.iq.iqInstsAdded                  269389457                       # Number of instructions added to the IQ (excludes non-spec)
-system.cpu.iq.iqInstsIssued                 245994030                       # Number of instructions issued
-system.cpu.iq.iqNonSpecInstsAdded                1273                       # Number of non-speculative instructions added to the IQ
-system.cpu.iq.iqSquashedInstsExamined        47650161                       # Number of squashed instructions iterated over during squash; mainly for profiling
-system.cpu.iq.iqSquashedInstsIssued               258                       # Number of squashed instructions issued
-system.cpu.iq.iqSquashedNonSpecRemoved             27                       # Number of squashed non-spec instructions that were removed
-system.cpu.iq.iqSquashedOperandsExamined     91534276                       # Number of squashed operands that are examined and possibly removed from graph
-system.cpu.l2cache.ReadExReq_accesses            1576                       # number of ReadExReq accesses(hits+misses)
-system.cpu.l2cache.ReadExReq_avg_miss_latency 34382.484076                       # average ReadExReq miss latency
-system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31064.649682                       # average ReadExReq mshr miss latency
+system.cpu.iq.ISSUE:issued_per_cycle::total    217661766                       # Number of insts issued each cycle
+system.cpu.iq.ISSUE:rate                     1.292796                       # Inst issue rate
+system.cpu.iq.fp_alu_accesses                 2630821                       # Number of floating point alu accesses
+system.cpu.iq.fp_inst_queue_reads             5219937                       # Number of floating instruction queue reads
+system.cpu.iq.fp_inst_queue_wakeup_accesses      2526643                       # Number of floating instruction queue wakeup accesses
+system.cpu.iq.fp_inst_queue_writes            5714467                       # Number of floating instruction queue writes
+system.cpu.iq.int_alu_accesses              280460790                       # Number of integer alu accesses
+system.cpu.iq.int_inst_queue_reads          778290063                       # Number of integer instruction queue reads
+system.cpu.iq.int_inst_queue_wakeup_accesses    273499649                       # Number of integer instruction queue wakeup accesses
+system.cpu.iq.int_inst_queue_writes         575780653                       # Number of integer instruction queue writes
+system.cpu.iq.iqInstsAdded                  401511304                       # Number of instructions added to the IQ (excludes non-spec)
+system.cpu.iq.iqInstsIssued                 281507534                       # Number of instructions issued
+system.cpu.iq.iqNonSpecInstsAdded                1424                       # Number of non-speculative instructions added to the IQ
+system.cpu.iq.iqSquashedInstsExamined       179800569                       # Number of squashed instructions iterated over during squash; mainly for profiling
+system.cpu.iq.iqSquashedInstsIssued             53698                       # Number of squashed instructions issued
+system.cpu.iq.iqSquashedNonSpecRemoved            178                       # Number of squashed non-spec instructions that were removed
+system.cpu.iq.iqSquashedOperandsExamined    375388973                       # Number of squashed operands that are examined and possibly removed from graph
+system.cpu.l2cache.ReadExReq_accesses            1566                       # number of ReadExReq accesses(hits+misses)
+system.cpu.l2cache.ReadExReq_avg_miss_latency 34512.500000                       # average ReadExReq miss latency
+system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31347.756410                       # average ReadExReq mshr miss latency
 system.cpu.l2cache.ReadExReq_hits                   6                       # number of ReadExReq hits
-system.cpu.l2cache.ReadExReq_miss_latency     53980500                       # number of ReadExReq miss cycles
-system.cpu.l2cache.ReadExReq_miss_rate       0.996193                       # miss rate for ReadExReq accesses
-system.cpu.l2cache.ReadExReq_misses              1570                       # number of ReadExReq misses
-system.cpu.l2cache.ReadExReq_mshr_miss_latency     48771500                       # number of ReadExReq MSHR miss cycles
-system.cpu.l2cache.ReadExReq_mshr_miss_rate     0.996193                       # mshr miss rate for ReadExReq accesses
-system.cpu.l2cache.ReadExReq_mshr_misses         1570                       # number of ReadExReq MSHR misses
-system.cpu.l2cache.ReadReq_accesses              5352                       # number of ReadReq accesses(hits+misses)
-system.cpu.l2cache.ReadReq_avg_miss_latency 34258.559622                       # average ReadReq miss latency
-system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31035.566706                       # average ReadReq mshr miss latency
-system.cpu.l2cache.ReadReq_hits                  1964                       # number of ReadReq hits
-system.cpu.l2cache.ReadReq_miss_latency     116068000                       # number of ReadReq miss cycles
-system.cpu.l2cache.ReadReq_miss_rate         0.633034                       # miss rate for ReadReq accesses
-system.cpu.l2cache.ReadReq_misses                3388                       # number of ReadReq misses
-system.cpu.l2cache.ReadReq_mshr_miss_latency    105148500                       # number of ReadReq MSHR miss cycles
-system.cpu.l2cache.ReadReq_mshr_miss_rate     0.633034                       # mshr miss rate for ReadReq accesses
-system.cpu.l2cache.ReadReq_mshr_misses           3388                       # number of ReadReq MSHR misses
+system.cpu.l2cache.ReadExReq_miss_latency     53839500                       # number of ReadExReq miss cycles
+system.cpu.l2cache.ReadExReq_miss_rate       0.996169                       # miss rate for ReadExReq accesses
+system.cpu.l2cache.ReadExReq_misses              1560                       # number of ReadExReq misses
+system.cpu.l2cache.ReadExReq_mshr_miss_latency     48902500                       # number of ReadExReq MSHR miss cycles
+system.cpu.l2cache.ReadExReq_mshr_miss_rate     0.996169                       # mshr miss rate for ReadExReq accesses
+system.cpu.l2cache.ReadExReq_mshr_misses         1560                       # number of ReadExReq MSHR misses
+system.cpu.l2cache.ReadReq_accesses              5770                       # number of ReadReq accesses(hits+misses)
+system.cpu.l2cache.ReadReq_avg_miss_latency 34287.021858                       # average ReadReq miss latency
+system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31043.032787                       # average ReadReq mshr miss latency
+system.cpu.l2cache.ReadReq_hits                  2110                       # number of ReadReq hits
+system.cpu.l2cache.ReadReq_miss_latency     125490500                       # number of ReadReq miss cycles
+system.cpu.l2cache.ReadReq_miss_rate         0.634315                       # miss rate for ReadReq accesses
+system.cpu.l2cache.ReadReq_misses                3660                       # number of ReadReq misses
+system.cpu.l2cache.ReadReq_mshr_miss_latency    113617500                       # number of ReadReq MSHR miss cycles
+system.cpu.l2cache.ReadReq_mshr_miss_rate     0.634315                       # mshr miss rate for ReadReq accesses
+system.cpu.l2cache.ReadReq_mshr_misses           3660                       # number of ReadReq MSHR misses
 system.cpu.l2cache.Writeback_accesses              10                       # number of Writeback accesses(hits+misses)
 system.cpu.l2cache.Writeback_hits                  10                       # number of Writeback hits
 system.cpu.l2cache.avg_blocked_cycles::no_mshrs     no_value                       # average number of cycles each access was blocked
 system.cpu.l2cache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
-system.cpu.l2cache.avg_refs                  0.579180                       # Average number of references to valid blocks.
+system.cpu.l2cache.avg_refs                  0.575873                       # Average number of references to valid blocks.
 system.cpu.l2cache.blocked::no_mshrs                0                       # number of cycles access was blocked
 system.cpu.l2cache.blocked::no_targets              0                       # number of cycles access was blocked
 system.cpu.l2cache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.l2cache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.l2cache.cache_copies                     0                       # number of cache copies performed
-system.cpu.l2cache.demand_accesses               6928                       # number of demand (read+write) accesses
-system.cpu.l2cache.demand_avg_miss_latency 34297.801533                       # average overall miss latency
-system.cpu.l2cache.demand_avg_mshr_miss_latency 31044.776119                       # average overall mshr miss latency
-system.cpu.l2cache.demand_hits                   1970                       # number of demand (read+write) hits
-system.cpu.l2cache.demand_miss_latency      170048500                       # number of demand (read+write) miss cycles
-system.cpu.l2cache.demand_miss_rate          0.715647                       # miss rate for demand accesses
-system.cpu.l2cache.demand_misses                 4958                       # number of demand (read+write) misses
+system.cpu.l2cache.demand_accesses               7336                       # number of demand (read+write) accesses
+system.cpu.l2cache.demand_avg_miss_latency 34354.406130                       # average overall miss latency
+system.cpu.l2cache.demand_avg_mshr_miss_latency 31134.099617                       # average overall mshr miss latency
+system.cpu.l2cache.demand_hits                   2116                       # number of demand (read+write) hits
+system.cpu.l2cache.demand_miss_latency      179330000                       # number of demand (read+write) miss cycles
+system.cpu.l2cache.demand_miss_rate          0.711559                       # miss rate for demand accesses
+system.cpu.l2cache.demand_misses                 5220                       # number of demand (read+write) misses
 system.cpu.l2cache.demand_mshr_hits                 0                       # number of demand (read+write) MSHR hits
-system.cpu.l2cache.demand_mshr_miss_latency    153920000                       # number of demand (read+write) MSHR miss cycles
-system.cpu.l2cache.demand_mshr_miss_rate     0.715647                       # mshr miss rate for demand accesses
-system.cpu.l2cache.demand_mshr_misses            4958                       # number of demand (read+write) MSHR misses
+system.cpu.l2cache.demand_mshr_miss_latency    162520000                       # number of demand (read+write) MSHR miss cycles
+system.cpu.l2cache.demand_mshr_miss_rate     0.711559                       # mshr miss rate for demand accesses
+system.cpu.l2cache.demand_mshr_misses            5220                       # number of demand (read+write) MSHR misses
 system.cpu.l2cache.fast_writes                      0                       # number of fast writes performed
 system.cpu.l2cache.mshr_cap_events                  0                       # number of times MSHR cap was activated
 system.cpu.l2cache.no_allocate_misses               0                       # Number of misses that were no-allocate
-system.cpu.l2cache.occ_%::0                  0.067776                       # Average percentage of cache occupancy
+system.cpu.l2cache.occ_%::0                  0.074027                       # Average percentage of cache occupancy
 system.cpu.l2cache.occ_%::1                  0.000031                       # Average percentage of cache occupancy
-system.cpu.l2cache.occ_blocks::0          2220.891460                       # Average occupied blocks per context
-system.cpu.l2cache.occ_blocks::1             1.016755                       # Average occupied blocks per context
-system.cpu.l2cache.overall_accesses              6928                       # number of overall (read+write) accesses
-system.cpu.l2cache.overall_avg_miss_latency 34297.801533                       # average overall miss latency
-system.cpu.l2cache.overall_avg_mshr_miss_latency 31044.776119                       # average overall mshr miss latency
+system.cpu.l2cache.occ_blocks::0          2425.713909                       # Average occupied blocks per context
+system.cpu.l2cache.occ_blocks::1             1.014918                       # Average occupied blocks per context
+system.cpu.l2cache.overall_accesses              7336                       # number of overall (read+write) accesses
+system.cpu.l2cache.overall_avg_miss_latency 34354.406130                       # average overall miss latency
+system.cpu.l2cache.overall_avg_mshr_miss_latency 31134.099617                       # average overall mshr miss latency
 system.cpu.l2cache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
-system.cpu.l2cache.overall_hits                  1970                       # number of overall hits
-system.cpu.l2cache.overall_miss_latency     170048500                       # number of overall miss cycles
-system.cpu.l2cache.overall_miss_rate         0.715647                       # miss rate for overall accesses
-system.cpu.l2cache.overall_misses                4958                       # number of overall misses
+system.cpu.l2cache.overall_hits                  2116                       # number of overall hits
+system.cpu.l2cache.overall_miss_latency     179330000                       # number of overall miss cycles
+system.cpu.l2cache.overall_miss_rate         0.711559                       # miss rate for overall accesses
+system.cpu.l2cache.overall_misses                5220                       # number of overall misses
 system.cpu.l2cache.overall_mshr_hits                0                       # number of overall MSHR hits
-system.cpu.l2cache.overall_mshr_miss_latency    153920000                       # number of overall MSHR miss cycles
-system.cpu.l2cache.overall_mshr_miss_rate     0.715647                       # mshr miss rate for overall accesses
-system.cpu.l2cache.overall_mshr_misses           4958                       # number of overall MSHR misses
+system.cpu.l2cache.overall_mshr_miss_latency    162520000                       # number of overall MSHR miss cycles
+system.cpu.l2cache.overall_mshr_miss_rate     0.711559                       # mshr miss rate for overall accesses
+system.cpu.l2cache.overall_mshr_misses           5220                       # number of overall MSHR misses
 system.cpu.l2cache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
 system.cpu.l2cache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
 system.cpu.l2cache.replacements                     0                       # number of replacements
-system.cpu.l2cache.sampled_refs                  3391                       # Sample count of references to valid blocks.
+system.cpu.l2cache.sampled_refs                  3664                       # Sample count of references to valid blocks.
 system.cpu.l2cache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
-system.cpu.l2cache.tagsinuse              2221.908214                       # Cycle average of tags in use
-system.cpu.l2cache.total_refs                    1964                       # Total number of references to valid blocks.
+system.cpu.l2cache.tagsinuse              2426.728827                       # Cycle average of tags in use
+system.cpu.l2cache.total_refs                    2110                       # Total number of references to valid blocks.
 system.cpu.l2cache.warmup_cycle                     0                       # Cycle when the warmup percentage was hit.
 system.cpu.l2cache.writebacks                       0                       # number of writebacks
-system.cpu.memDep0.conflictingLoads          28553702                       # Number of conflicting loads.
-system.cpu.memDep0.conflictingStores          6206376                       # Number of conflicting stores.
-system.cpu.memDep0.insertedLoads             69776556                       # Number of loads inserted to the mem dependence unit.
-system.cpu.memDep0.insertedStores            24137923                       # Number of stores inserted to the mem dependence unit.
-system.cpu.misc_regfile_reads               125230087                       # number of misc regfile reads
+system.cpu.memDep0.conflictingLoads          95035235                       # Number of conflicting loads.
+system.cpu.memDep0.conflictingStores         32152607                       # Number of conflicting stores.
+system.cpu.memDep0.insertedLoads            106923422                       # Number of loads inserted to the mem dependence unit.
+system.cpu.memDep0.insertedStores            37463806                       # Number of stores inserted to the mem dependence unit.
+system.cpu.misc_regfile_reads               144601816                       # number of misc regfile reads
 system.cpu.misc_regfile_writes                    844                       # number of misc regfile writes
-system.cpu.numCycles                        228090278                       # number of cpu cycles simulated
+system.cpu.numCycles                        217750949                       # number of cpu cycles simulated
 system.cpu.numWorkItemsCompleted                    0                       # number of work items this cpu completed
 system.cpu.numWorkItemsStarted                      0                       # number of work items this cpu started
-system.cpu.rename.RENAME:BlockCycles            31917                       # Number of cycles rename is blocking
+system.cpu.rename.RENAME:BlockCycles         18951054                       # Number of cycles rename is blocking
 system.cpu.rename.RENAME:CommittedMaps      234363409                       # Number of HB maps that are committed
-system.cpu.rename.RENAME:IQFullEvents          638720                       # Number of times rename has blocked due to IQ full
-system.cpu.rename.RENAME:IdleCycles          52054674                       # Number of cycles rename is idle
-system.cpu.rename.RENAME:LSQFullEvents         682190                       # Number of times rename has blocked due to LSQ full
-system.cpu.rename.RENAME:RenameLookups      732163494                       # Number of register rename lookups that rename has made
-system.cpu.rename.RENAME:RenamedInsts       280433210                       # Number of instructions processed by rename
-system.cpu.rename.RENAME:RenamedOperands    305502440                       # Number of destination operands rename has renamed
-system.cpu.rename.RENAME:RunCycles          166205742                       # Number of cycles rename is running
-system.cpu.rename.RENAME:SquashCycles         7787199                       # Number of cycles rename is squashing
-system.cpu.rename.RENAME:UnblockCycles        1869216                       # Number of cycles rename is unblocking
-system.cpu.rename.RENAME:UndoneMaps          71139031                       # Number of HB maps that are undone due to squashing
-system.cpu.rename.RENAME:fp_rename_lookups      7184355                       # Number of floating rename lookups
-system.cpu.rename.RENAME:int_rename_lookups    724979139                       # Number of integer rename lookups
-system.cpu.rename.RENAME:serializeStallCycles        15879                       # count of cycles rename stalled for serializing inst
-system.cpu.rename.RENAME:serializingInsts         1273                       # count of serializing insts renamed
-system.cpu.rename.RENAME:skidInsts            3670415                       # count of insts added to the skid buffer
-system.cpu.rename.RENAME:tempSerializingInsts         1276                       # count of temporary serializing insts renamed
-system.cpu.rob.rob_reads                    488844527                       # The number of ROB reads
-system.cpu.rob.rob_writes                   546568715                       # The number of ROB writes
-system.cpu.timesIdled                            2341                       # Number of times that the entire CPU went into an idle state and unscheduled itself
+system.cpu.rename.RENAME:IQFullEvents        22087788                       # Number of times rename has blocked due to IQ full
+system.cpu.rename.RENAME:IdleCycles          75841753                       # Number of cycles rename is idle
+system.cpu.rename.RENAME:LSQFullEvents       16619805                       # Number of times rename has blocked due to LSQ full
+system.cpu.rename.RENAME:ROBFullEvents              9                       # Number of times rename has blocked due to ROB full
+system.cpu.rename.RENAME:RenameLookups     1071149424                       # Number of register rename lookups that rename has made
+system.cpu.rename.RENAME:RenamedInsts       415976206                       # Number of instructions processed by rename
+system.cpu.rename.RENAME:RenamedOperands    437655168                       # Number of destination operands rename has renamed
+system.cpu.rename.RENAME:RunCycles           58179410                       # Number of cycles rename is running
+system.cpu.rename.RENAME:SquashCycles        23949638                       # Number of cycles rename is squashing
+system.cpu.rename.RENAME:UnblockCycles       40717504                       # Number of cycles rename is unblocking
+system.cpu.rename.RENAME:UndoneMaps         203291759                       # Number of HB maps that are undone due to squashing
+system.cpu.rename.RENAME:fp_rename_lookups     11132052                       # Number of floating rename lookups
+system.cpu.rename.RENAME:int_rename_lookups   1060017372                       # Number of integer rename lookups
+system.cpu.rename.RENAME:serializeStallCycles        22407                       # count of cycles rename stalled for serializing inst
+system.cpu.rename.RENAME:serializingInsts         1440                       # count of serializing insts renamed
+system.cpu.rename.RENAME:skidInsts           84366850                       # count of insts added to the skid buffer
+system.cpu.rename.RENAME:tempSerializingInsts         1310                       # count of temporary serializing insts renamed
+system.cpu.rob.rob_reads                    592991425                       # The number of ROB reads
+system.cpu.rob.rob_writes                   827053987                       # The number of ROB writes
+system.cpu.timesIdled                            1919                       # Number of times that the entire CPU went into an idle state and unscheduled itself
 system.cpu.workload.PROG:num_syscalls             400                       # Number of system calls
 
 ---------- End Simulation Statistics   ----------
index b2dde915e8e082b16dcd9a10da96f1905a53ec29..1943466e8bca7627ff627779bde29e65189839de 100755 (executable)
@@ -5,13 +5,13 @@ The Regents of The University of Michigan
 All Rights Reserved
 
 
-M5 compiled Feb  8 2011 00:58:32
-M5 revision 705a4d351a43 7939 default qtip resforflagsstats.patch tip
-M5 started Feb  8 2011 00:58:34
+M5 compiled Feb 12 2011 02:22:23
+M5 revision 5e76f9de6972 7961 default qtip tip x86branchdetectstats.patch
+M5 started Feb 12 2011 02:22:27
 M5 executing on burrito
-command line: build/X86_SE/m5.fast -d build/X86_SE/tests/fast/quick/00.hello/x86/linux/o3-timing -re tests/run.py build/X86_SE/tests/fast/quick/00.hello/x86/linux/o3-timing
+command line: build/X86_SE/m5.opt -d build/X86_SE/tests/opt/quick/00.hello/x86/linux/o3-timing -re tests/run.py build/X86_SE/tests/opt/quick/00.hello/x86/linux/o3-timing
 Global frequency set at 1000000000000 ticks per second
 info: Entering event queue @ 0.  Starting simulation...
 info: Increasing stack size by one page.
 Hello world!
-Exiting @ tick 13637500 because target called exit()
+Exiting @ tick 11421500 because target called exit()
index bdaed3ceca3c7601d5839aed5d25425f9ba08cc1..c2dfaa3ff4d66220aca12bcc1038b254f1871bf6 100644 (file)
@@ -1,41 +1,41 @@
 
 ---------- Begin Simulation Statistics ----------
-host_inst_rate                                  59245                       # Simulator instruction rate (inst/s)
-host_mem_usage                                 228168                       # Number of bytes of host memory used
-host_seconds                                     0.17                       # Real time elapsed on the host
-host_tick_rate                               82238527                       # Simulator tick rate (ticks/s)
+host_inst_rate                                  47598                       # Simulator instruction rate (inst/s)
+host_mem_usage                                 231896                       # Number of bytes of host memory used
+host_seconds                                     0.21                       # Real time elapsed on the host
+host_tick_rate                               55349277                       # Simulator tick rate (ticks/s)
 sim_freq                                 1000000000000                       # Frequency of simulated ticks
 sim_insts                                        9809                       # Number of instructions simulated
-sim_seconds                                  0.000014                       # Number of seconds simulated
-sim_ticks                                    13637500                       # Number of ticks simulated
+sim_seconds                                  0.000011                       # Number of seconds simulated
+sim_ticks                                    11421500                       # Number of ticks simulated
 system.cpu.BPredUnit.BTBCorrect                     0                       # Number of correct BTB predictions (this stat may not work properly.
-system.cpu.BPredUnit.BTBHits                      715                       # Number of BTB hits
-system.cpu.BPredUnit.BTBLookups                  1829                       # Number of BTB lookups
+system.cpu.BPredUnit.BTBHits                      944                       # Number of BTB hits
+system.cpu.BPredUnit.BTBLookups                  2550                       # Number of BTB lookups
 system.cpu.BPredUnit.RASInCorrect                   0                       # Number of incorrect RAS predictions.
-system.cpu.BPredUnit.condIncorrect                455                       # Number of conditional branches incorrect
-system.cpu.BPredUnit.condPredicted               1876                       # Number of conditional branches predicted
-system.cpu.BPredUnit.lookups                     1876                       # Number of BP lookups
+system.cpu.BPredUnit.condIncorrect                485                       # Number of conditional branches incorrect
+system.cpu.BPredUnit.condPredicted               2777                       # Number of conditional branches predicted
+system.cpu.BPredUnit.lookups                     2777                       # Number of BP lookups
 system.cpu.BPredUnit.usedRAS                        0                       # Number of times the RAS was used to get a target.
 system.cpu.commit.COM:branches                   1214                       # Number of branches committed
-system.cpu.commit.COM:bw_lim_events                22                       # number cycles where commit BW limit reached
+system.cpu.commit.COM:bw_lim_events               139                       # number cycles where commit BW limit reached
 system.cpu.commit.COM:bw_limited                    0                       # number of insts not committed due to BW limits
-system.cpu.commit.COM:committed_per_cycle::samples        15018                       # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::mean     0.653150                       # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::stdev     1.090994                       # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::samples        11906                       # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::mean     0.823870                       # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::stdev     1.588166                       # Number of insts commited each cycle
 system.cpu.commit.COM:committed_per_cycle::underflows            0      0.00%      0.00% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::0         9552     63.60%     63.60% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::1         2996     19.95%     83.55% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::2         1196      7.96%     91.52% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::3          909      6.05%     97.57% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::4          244      1.62%     99.19% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::5           60      0.40%     99.59% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::6           31      0.21%     99.80% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::7            8      0.05%     99.85% # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::8           22      0.15%    100.00% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::0         8274     69.49%     69.49% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::1         1230     10.33%     79.83% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::2          588      4.94%     84.76% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::3          963      8.09%     92.85% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::4          395      3.32%     96.17% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::5          136      1.14%     97.31% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::6          125      1.05%     98.36% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::7           56      0.47%     98.83% # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::8          139      1.17%    100.00% # Number of insts commited each cycle
 system.cpu.commit.COM:committed_per_cycle::overflows            0      0.00%    100.00% # Number of insts commited each cycle
 system.cpu.commit.COM:committed_per_cycle::min_value            0                       # Number of insts commited each cycle
 system.cpu.commit.COM:committed_per_cycle::max_value            8                       # Number of insts commited each cycle
-system.cpu.commit.COM:committed_per_cycle::total        15018                       # Number of insts commited each cycle
+system.cpu.commit.COM:committed_per_cycle::total        11906                       # Number of insts commited each cycle
 system.cpu.commit.COM:count                      9809                       # Number of instructions committed
 system.cpu.commit.COM:fp_insts                      0                       # Number of committed floating point instructions.
 system.cpu.commit.COM:function_calls                0                       # Number of function calls committed.
@@ -44,416 +44,417 @@ system.cpu.commit.COM:loads                      1056                       # Nu
 system.cpu.commit.COM:membars                       0                       # Number of memory barriers committed
 system.cpu.commit.COM:refs                       1990                       # Number of memory references committed
 system.cpu.commit.COM:swp_count                     0                       # Number of s/w prefetches committed
-system.cpu.commit.branchMispredicts               455                       # The number of times a branch was mispredicted
+system.cpu.commit.branchMispredicts               485                       # The number of times a branch was mispredicted
 system.cpu.commit.commitCommittedInsts           9809                       # The number of committed instructions
 system.cpu.commit.commitNonSpecStalls              13                       # The number of times commit has been forced to stall to communicate backwards
-system.cpu.commit.commitSquashedInsts            3810                       # The number of squashed insts skipped by commit
+system.cpu.commit.commitSquashedInsts            9374                       # The number of squashed insts skipped by commit
 system.cpu.committedInsts                        9809                       # Number of Instructions Simulated
 system.cpu.committedInsts_total                  9809                       # Number of Instructions Simulated
-system.cpu.cpi                               2.780712                       # CPI: Cycles Per Instruction
-system.cpu.cpi_total                         2.780712                       # CPI: Total CPI of All Threads
-system.cpu.dcache.ReadReq_accesses               1299                       # number of ReadReq accesses(hits+misses)
-system.cpu.dcache.ReadReq_avg_miss_latency 34989.361702                       # average ReadReq miss latency
-system.cpu.dcache.ReadReq_avg_mshr_miss_latency 34992.307692                       # average ReadReq mshr miss latency
-system.cpu.dcache.ReadReq_hits                   1205                       # number of ReadReq hits
-system.cpu.dcache.ReadReq_miss_latency        3289000                       # number of ReadReq miss cycles
-system.cpu.dcache.ReadReq_miss_rate          0.072363                       # miss rate for ReadReq accesses
-system.cpu.dcache.ReadReq_misses                   94                       # number of ReadReq misses
-system.cpu.dcache.ReadReq_mshr_hits                29                       # number of ReadReq MSHR hits
-system.cpu.dcache.ReadReq_mshr_miss_latency      2274500                       # number of ReadReq MSHR miss cycles
-system.cpu.dcache.ReadReq_mshr_miss_rate     0.050038                       # mshr miss rate for ReadReq accesses
-system.cpu.dcache.ReadReq_mshr_misses              65                       # number of ReadReq MSHR misses
+system.cpu.cpi                               2.328882                       # CPI: Cycles Per Instruction
+system.cpu.cpi_total                         2.328882                       # CPI: Total CPI of All Threads
+system.cpu.dcache.ReadReq_accesses               1541                       # number of ReadReq accesses(hits+misses)
+system.cpu.dcache.ReadReq_avg_miss_latency 34473.684211                       # average ReadReq miss latency
+system.cpu.dcache.ReadReq_avg_mshr_miss_latency 35119.402985                       # average ReadReq mshr miss latency
+system.cpu.dcache.ReadReq_hits                   1427                       # number of ReadReq hits
+system.cpu.dcache.ReadReq_miss_latency        3930000                       # number of ReadReq miss cycles
+system.cpu.dcache.ReadReq_miss_rate          0.073978                       # miss rate for ReadReq accesses
+system.cpu.dcache.ReadReq_misses                  114                       # number of ReadReq misses
+system.cpu.dcache.ReadReq_mshr_hits                47                       # number of ReadReq MSHR hits
+system.cpu.dcache.ReadReq_mshr_miss_latency      2353000                       # number of ReadReq MSHR miss cycles
+system.cpu.dcache.ReadReq_mshr_miss_rate     0.043478                       # mshr miss rate for ReadReq accesses
+system.cpu.dcache.ReadReq_mshr_misses              67                       # number of ReadReq MSHR misses
 system.cpu.dcache.WriteReq_accesses               934                       # number of WriteReq accesses(hits+misses)
-system.cpu.dcache.WriteReq_avg_miss_latency 33138.977636                       # average WriteReq miss latency
-system.cpu.dcache.WriteReq_avg_mshr_miss_latency 35814.102564                       # average WriteReq mshr miss latency
+system.cpu.dcache.WriteReq_avg_miss_latency 34089.456869                       # average WriteReq miss latency
+system.cpu.dcache.WriteReq_avg_mshr_miss_latency 36012.987013                       # average WriteReq mshr miss latency
 system.cpu.dcache.WriteReq_hits                   621                       # number of WriteReq hits
-system.cpu.dcache.WriteReq_miss_latency      10372500                       # number of WriteReq miss cycles
+system.cpu.dcache.WriteReq_miss_latency      10670000                       # number of WriteReq miss cycles
 system.cpu.dcache.WriteReq_miss_rate         0.335118                       # miss rate for WriteReq accesses
 system.cpu.dcache.WriteReq_misses                 313                       # number of WriteReq misses
-system.cpu.dcache.WriteReq_mshr_hits              235                       # number of WriteReq MSHR hits
-system.cpu.dcache.WriteReq_mshr_miss_latency      2793500                       # number of WriteReq MSHR miss cycles
-system.cpu.dcache.WriteReq_mshr_miss_rate     0.083512                       # mshr miss rate for WriteReq accesses
-system.cpu.dcache.WriteReq_mshr_misses             78                       # number of WriteReq MSHR misses
+system.cpu.dcache.WriteReq_mshr_hits              236                       # number of WriteReq MSHR hits
+system.cpu.dcache.WriteReq_mshr_miss_latency      2773000                       # number of WriteReq MSHR miss cycles
+system.cpu.dcache.WriteReq_mshr_miss_rate     0.082441                       # mshr miss rate for WriteReq accesses
+system.cpu.dcache.WriteReq_mshr_misses             77                       # number of WriteReq MSHR misses
 system.cpu.dcache.avg_blocked_cycles::no_mshrs     no_value                       # average number of cycles each access was blocked
 system.cpu.dcache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
-system.cpu.dcache.avg_refs                  12.859155                       # Average number of references to valid blocks.
+system.cpu.dcache.avg_refs                  14.321678                       # Average number of references to valid blocks.
 system.cpu.dcache.blocked::no_mshrs                 0                       # number of cycles access was blocked
 system.cpu.dcache.blocked::no_targets               0                       # number of cycles access was blocked
 system.cpu.dcache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.dcache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.dcache.cache_copies                      0                       # number of cache copies performed
-system.cpu.dcache.demand_accesses                2233                       # number of demand (read+write) accesses
-system.cpu.dcache.demand_avg_miss_latency 33566.339066                       # average overall miss latency
-system.cpu.dcache.demand_avg_mshr_miss_latency 35440.559441                       # average overall mshr miss latency
-system.cpu.dcache.demand_hits                    1826                       # number of demand (read+write) hits
-system.cpu.dcache.demand_miss_latency        13661500                       # number of demand (read+write) miss cycles
-system.cpu.dcache.demand_miss_rate           0.182266                       # miss rate for demand accesses
-system.cpu.dcache.demand_misses                   407                       # number of demand (read+write) misses
-system.cpu.dcache.demand_mshr_hits                264                       # number of demand (read+write) MSHR hits
-system.cpu.dcache.demand_mshr_miss_latency      5068000                       # number of demand (read+write) MSHR miss cycles
-system.cpu.dcache.demand_mshr_miss_rate      0.064039                       # mshr miss rate for demand accesses
-system.cpu.dcache.demand_mshr_misses              143                       # number of demand (read+write) MSHR misses
+system.cpu.dcache.demand_accesses                2475                       # number of demand (read+write) accesses
+system.cpu.dcache.demand_avg_miss_latency 34192.037471                       # average overall miss latency
+system.cpu.dcache.demand_avg_mshr_miss_latency 35597.222222                       # average overall mshr miss latency
+system.cpu.dcache.demand_hits                    2048                       # number of demand (read+write) hits
+system.cpu.dcache.demand_miss_latency        14600000                       # number of demand (read+write) miss cycles
+system.cpu.dcache.demand_miss_rate           0.172525                       # miss rate for demand accesses
+system.cpu.dcache.demand_misses                   427                       # number of demand (read+write) misses
+system.cpu.dcache.demand_mshr_hits                283                       # number of demand (read+write) MSHR hits
+system.cpu.dcache.demand_mshr_miss_latency      5126000                       # number of demand (read+write) MSHR miss cycles
+system.cpu.dcache.demand_mshr_miss_rate      0.058182                       # mshr miss rate for demand accesses
+system.cpu.dcache.demand_mshr_misses              144                       # number of demand (read+write) MSHR misses
 system.cpu.dcache.fast_writes                       0                       # number of fast writes performed
 system.cpu.dcache.mshr_cap_events                   0                       # number of times MSHR cap was activated
 system.cpu.dcache.no_allocate_misses                0                       # Number of misses that were no-allocate
-system.cpu.dcache.occ_%::0                   0.021266                       # Average percentage of cache occupancy
-system.cpu.dcache.occ_blocks::0             87.104239                       # Average occupied blocks per context
-system.cpu.dcache.overall_accesses               2233                       # number of overall (read+write) accesses
-system.cpu.dcache.overall_avg_miss_latency 33566.339066                       # average overall miss latency
-system.cpu.dcache.overall_avg_mshr_miss_latency 35440.559441                       # average overall mshr miss latency
+system.cpu.dcache.occ_%::0                   0.020970                       # Average percentage of cache occupancy
+system.cpu.dcache.occ_blocks::0             85.892970                       # Average occupied blocks per context
+system.cpu.dcache.overall_accesses               2475                       # number of overall (read+write) accesses
+system.cpu.dcache.overall_avg_miss_latency 34192.037471                       # average overall miss latency
+system.cpu.dcache.overall_avg_mshr_miss_latency 35597.222222                       # average overall mshr miss latency
 system.cpu.dcache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
-system.cpu.dcache.overall_hits                   1826                       # number of overall hits
-system.cpu.dcache.overall_miss_latency       13661500                       # number of overall miss cycles
-system.cpu.dcache.overall_miss_rate          0.182266                       # miss rate for overall accesses
-system.cpu.dcache.overall_misses                  407                       # number of overall misses
-system.cpu.dcache.overall_mshr_hits               264                       # number of overall MSHR hits
-system.cpu.dcache.overall_mshr_miss_latency      5068000                       # number of overall MSHR miss cycles
-system.cpu.dcache.overall_mshr_miss_rate     0.064039                       # mshr miss rate for overall accesses
-system.cpu.dcache.overall_mshr_misses             143                       # number of overall MSHR misses
+system.cpu.dcache.overall_hits                   2048                       # number of overall hits
+system.cpu.dcache.overall_miss_latency       14600000                       # number of overall miss cycles
+system.cpu.dcache.overall_miss_rate          0.172525                       # miss rate for overall accesses
+system.cpu.dcache.overall_misses                  427                       # number of overall misses
+system.cpu.dcache.overall_mshr_hits               283                       # number of overall MSHR hits
+system.cpu.dcache.overall_mshr_miss_latency      5126000                       # number of overall MSHR miss cycles
+system.cpu.dcache.overall_mshr_miss_rate     0.058182                       # mshr miss rate for overall accesses
+system.cpu.dcache.overall_mshr_misses             144                       # number of overall MSHR misses
 system.cpu.dcache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
 system.cpu.dcache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
 system.cpu.dcache.replacements                      0                       # number of replacements
-system.cpu.dcache.sampled_refs                    142                       # Sample count of references to valid blocks.
+system.cpu.dcache.sampled_refs                    143                       # Sample count of references to valid blocks.
 system.cpu.dcache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
-system.cpu.dcache.tagsinuse                 87.104239                       # Cycle average of tags in use
-system.cpu.dcache.total_refs                     1826                       # Total number of references to valid blocks.
+system.cpu.dcache.tagsinuse                 85.892970                       # Cycle average of tags in use
+system.cpu.dcache.total_refs                     2048                       # Total number of references to valid blocks.
 system.cpu.dcache.warmup_cycle                      0                       # Cycle when the warmup percentage was hit.
 system.cpu.dcache.writebacks                        0                       # number of writebacks
-system.cpu.decode.DECODE:BlockedCycles            420                       # Number of cycles decode is blocked
-system.cpu.decode.DECODE:DecodedInsts           15296                       # Number of instructions handled by decode
-system.cpu.decode.DECODE:IdleCycles              6181                       # Number of cycles decode is idle
-system.cpu.decode.DECODE:RunCycles               8360                       # Number of cycles decode is running
-system.cpu.decode.DECODE:SquashCycles             701                       # Number of cycles decode is squashing
-system.cpu.decode.DECODE:UnblockCycles             57                       # Number of cycles decode is unblocking
-system.cpu.fetch.Branches                        1876                       # Number of branches that fetch encountered
-system.cpu.fetch.CacheLines                      1264                       # Number of cache lines fetched
-system.cpu.fetch.Cycles                          9026                       # Number of cycles fetch has run and was not squashing or blocked
-system.cpu.fetch.IcacheSquashes                   121                       # Number of outstanding Icache misses that were squashed
-system.cpu.fetch.Insts                           8825                       # Number of instructions fetch has processed
-system.cpu.fetch.MiscStallCycles                    2                       # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs
-system.cpu.fetch.SquashCycles                     464                       # Number of cycles fetch has spent squashing
-system.cpu.fetch.branchRate                  0.068778                       # Number of branch fetches per cycle
-system.cpu.fetch.icacheStallCycles               1264                       # Number of cycles fetch is stalled on an Icache miss
-system.cpu.fetch.predictedBranches                715                       # Number of branches that fetch has predicted taken
-system.cpu.fetch.rate                        0.323545                       # Number of inst fetches per cycle
-system.cpu.fetch.rateDist::samples              15719                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::mean              1.009352                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::stdev             1.179835                       # Number of instructions fetched each cycle (Total)
+system.cpu.decode.DECODE:BlockedCycles           1367                       # Number of cycles decode is blocked
+system.cpu.decode.DECODE:DecodedInsts           22275                       # Number of instructions handled by decode
+system.cpu.decode.DECODE:IdleCycles              7155                       # Number of cycles decode is idle
+system.cpu.decode.DECODE:RunCycles               3308                       # Number of cycles decode is running
+system.cpu.decode.DECODE:SquashCycles            1504                       # Number of cycles decode is squashing
+system.cpu.decode.DECODE:UnblockCycles             76                       # Number of cycles decode is unblocking
+system.cpu.fetch.Branches                        2777                       # Number of branches that fetch encountered
+system.cpu.fetch.CacheLines                      1732                       # Number of cache lines fetched
+system.cpu.fetch.Cycles                          3623                       # Number of cycles fetch has run and was not squashing or blocked
+system.cpu.fetch.IcacheSquashes                   245                       # Number of outstanding Icache misses that were squashed
+system.cpu.fetch.Insts                          12976                       # Number of instructions fetch has processed
+system.cpu.fetch.MiscStallCycles                    4                       # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs
+system.cpu.fetch.SquashCycles                     508                       # Number of cycles fetch has spent squashing
+system.cpu.fetch.branchRate                  0.121564                       # Number of branch fetches per cycle
+system.cpu.fetch.icacheStallCycles               1732                       # Number of cycles fetch is stalled on an Icache miss
+system.cpu.fetch.predictedBranches                944                       # Number of branches that fetch has predicted taken
+system.cpu.fetch.rate                        0.568027                       # Number of inst fetches per cycle
+system.cpu.fetch.rateDist::samples              13410                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::mean              1.734526                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::stdev             3.109133                       # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::underflows               0      0.00%      0.00% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::0                     7007     44.58%     44.58% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::1                     4504     28.65%     73.23% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::2                     1838     11.69%     84.92% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::3                     2072     13.18%     98.10% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::4                       57      0.36%     98.47% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::5                      222      1.41%     99.88% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::6                        6      0.04%     99.92% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::7                        8      0.05%     99.97% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::8                        5      0.03%    100.00% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::0                     9877     73.65%     73.65% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::1                      162      1.21%     74.86% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::2                      123      0.92%     75.78% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::3                      227      1.69%     77.47% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::4                      192      1.43%     78.90% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::5                      174      1.30%     80.20% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::6                      266      1.98%     82.18% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::7                      175      1.30%     83.49% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::8                     2214     16.51%    100.00% # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::overflows                0      0.00%    100.00% # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::min_value                0                       # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::max_value                8                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::total                15719                       # Number of instructions fetched each cycle (Total)
-system.cpu.fp_regfile_reads                         2                       # number of floating regfile reads
-system.cpu.icache.ReadReq_accesses               1264                       # number of ReadReq accesses(hits+misses)
-system.cpu.icache.ReadReq_avg_miss_latency 37405.594406                       # average ReadReq miss latency
-system.cpu.icache.ReadReq_avg_mshr_miss_latency 35046.332046                       # average ReadReq mshr miss latency
-system.cpu.icache.ReadReq_hits                    978                       # number of ReadReq hits
-system.cpu.icache.ReadReq_miss_latency       10698000                       # number of ReadReq miss cycles
-system.cpu.icache.ReadReq_miss_rate          0.226266                       # miss rate for ReadReq accesses
-system.cpu.icache.ReadReq_misses                  286                       # number of ReadReq misses
-system.cpu.icache.ReadReq_mshr_hits                27                       # number of ReadReq MSHR hits
-system.cpu.icache.ReadReq_mshr_miss_latency      9077000                       # number of ReadReq MSHR miss cycles
-system.cpu.icache.ReadReq_mshr_miss_rate     0.204905                       # mshr miss rate for ReadReq accesses
-system.cpu.icache.ReadReq_mshr_misses             259                       # number of ReadReq MSHR misses
+system.cpu.fetch.rateDist::total                13410                       # Number of instructions fetched each cycle (Total)
+system.cpu.fp_regfile_reads                         4                       # number of floating regfile reads
+system.cpu.icache.ReadReq_accesses               1732                       # number of ReadReq accesses(hits+misses)
+system.cpu.icache.ReadReq_avg_miss_latency 36454.794521                       # average ReadReq miss latency
+system.cpu.icache.ReadReq_avg_mshr_miss_latency 35105.084746                       # average ReadReq mshr miss latency
+system.cpu.icache.ReadReq_hits                   1367                       # number of ReadReq hits
+system.cpu.icache.ReadReq_miss_latency       13306000                       # number of ReadReq miss cycles
+system.cpu.icache.ReadReq_miss_rate          0.210739                       # miss rate for ReadReq accesses
+system.cpu.icache.ReadReq_misses                  365                       # number of ReadReq misses
+system.cpu.icache.ReadReq_mshr_hits                70                       # number of ReadReq MSHR hits
+system.cpu.icache.ReadReq_mshr_miss_latency     10356000                       # number of ReadReq MSHR miss cycles
+system.cpu.icache.ReadReq_mshr_miss_rate     0.170323                       # mshr miss rate for ReadReq accesses
+system.cpu.icache.ReadReq_mshr_misses             295                       # number of ReadReq MSHR misses
 system.cpu.icache.avg_blocked_cycles::no_mshrs     no_value                       # average number of cycles each access was blocked
 system.cpu.icache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
-system.cpu.icache.avg_refs                   3.776062                       # Average number of references to valid blocks.
+system.cpu.icache.avg_refs                   4.633898                       # Average number of references to valid blocks.
 system.cpu.icache.blocked::no_mshrs                 0                       # number of cycles access was blocked
 system.cpu.icache.blocked::no_targets               0                       # number of cycles access was blocked
 system.cpu.icache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.icache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.icache.cache_copies                      0                       # number of cache copies performed
-system.cpu.icache.demand_accesses                1264                       # number of demand (read+write) accesses
-system.cpu.icache.demand_avg_miss_latency 37405.594406                       # average overall miss latency
-system.cpu.icache.demand_avg_mshr_miss_latency 35046.332046                       # average overall mshr miss latency
-system.cpu.icache.demand_hits                     978                       # number of demand (read+write) hits
-system.cpu.icache.demand_miss_latency        10698000                       # number of demand (read+write) miss cycles
-system.cpu.icache.demand_miss_rate           0.226266                       # miss rate for demand accesses
-system.cpu.icache.demand_misses                   286                       # number of demand (read+write) misses
-system.cpu.icache.demand_mshr_hits                 27                       # number of demand (read+write) MSHR hits
-system.cpu.icache.demand_mshr_miss_latency      9077000                       # number of demand (read+write) MSHR miss cycles
-system.cpu.icache.demand_mshr_miss_rate      0.204905                       # mshr miss rate for demand accesses
-system.cpu.icache.demand_mshr_misses              259                       # number of demand (read+write) MSHR misses
+system.cpu.icache.demand_accesses                1732                       # number of demand (read+write) accesses
+system.cpu.icache.demand_avg_miss_latency 36454.794521                       # average overall miss latency
+system.cpu.icache.demand_avg_mshr_miss_latency 35105.084746                       # average overall mshr miss latency
+system.cpu.icache.demand_hits                    1367                       # number of demand (read+write) hits
+system.cpu.icache.demand_miss_latency        13306000                       # number of demand (read+write) miss cycles
+system.cpu.icache.demand_miss_rate           0.210739                       # miss rate for demand accesses
+system.cpu.icache.demand_misses                   365                       # number of demand (read+write) misses
+system.cpu.icache.demand_mshr_hits                 70                       # number of demand (read+write) MSHR hits
+system.cpu.icache.demand_mshr_miss_latency     10356000                       # number of demand (read+write) MSHR miss cycles
+system.cpu.icache.demand_mshr_miss_rate      0.170323                       # mshr miss rate for demand accesses
+system.cpu.icache.demand_mshr_misses              295                       # number of demand (read+write) MSHR misses
 system.cpu.icache.fast_writes                       0                       # number of fast writes performed
 system.cpu.icache.mshr_cap_events                   0                       # number of times MSHR cap was activated
 system.cpu.icache.no_allocate_misses                0                       # Number of misses that were no-allocate
-system.cpu.icache.occ_%::0                   0.062320                       # Average percentage of cache occupancy
-system.cpu.icache.occ_blocks::0            127.631724                       # Average occupied blocks per context
-system.cpu.icache.overall_accesses               1264                       # number of overall (read+write) accesses
-system.cpu.icache.overall_avg_miss_latency 37405.594406                       # average overall miss latency
-system.cpu.icache.overall_avg_mshr_miss_latency 35046.332046                       # average overall mshr miss latency
+system.cpu.icache.occ_%::0                   0.070726                       # Average percentage of cache occupancy
+system.cpu.icache.occ_blocks::0            144.846093                       # Average occupied blocks per context
+system.cpu.icache.overall_accesses               1732                       # number of overall (read+write) accesses
+system.cpu.icache.overall_avg_miss_latency 36454.794521                       # average overall miss latency
+system.cpu.icache.overall_avg_mshr_miss_latency 35105.084746                       # average overall mshr miss latency
 system.cpu.icache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
-system.cpu.icache.overall_hits                    978                       # number of overall hits
-system.cpu.icache.overall_miss_latency       10698000                       # number of overall miss cycles
-system.cpu.icache.overall_miss_rate          0.226266                       # miss rate for overall accesses
-system.cpu.icache.overall_misses                  286                       # number of overall misses
-system.cpu.icache.overall_mshr_hits                27                       # number of overall MSHR hits
-system.cpu.icache.overall_mshr_miss_latency      9077000                       # number of overall MSHR miss cycles
-system.cpu.icache.overall_mshr_miss_rate     0.204905                       # mshr miss rate for overall accesses
-system.cpu.icache.overall_mshr_misses             259                       # number of overall MSHR misses
+system.cpu.icache.overall_hits                   1367                       # number of overall hits
+system.cpu.icache.overall_miss_latency       13306000                       # number of overall miss cycles
+system.cpu.icache.overall_miss_rate          0.210739                       # miss rate for overall accesses
+system.cpu.icache.overall_misses                  365                       # number of overall misses
+system.cpu.icache.overall_mshr_hits                70                       # number of overall MSHR hits
+system.cpu.icache.overall_mshr_miss_latency     10356000                       # number of overall MSHR miss cycles
+system.cpu.icache.overall_mshr_miss_rate     0.170323                       # mshr miss rate for overall accesses
+system.cpu.icache.overall_mshr_misses             295                       # number of overall MSHR misses
 system.cpu.icache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
 system.cpu.icache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
 system.cpu.icache.replacements                      0                       # number of replacements
-system.cpu.icache.sampled_refs                    259                       # Sample count of references to valid blocks.
+system.cpu.icache.sampled_refs                    295                       # Sample count of references to valid blocks.
 system.cpu.icache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
-system.cpu.icache.tagsinuse                127.631724                       # Cycle average of tags in use
-system.cpu.icache.total_refs                      978                       # Total number of references to valid blocks.
+system.cpu.icache.tagsinuse                144.846093                       # Cycle average of tags in use
+system.cpu.icache.total_refs                     1367                       # Total number of references to valid blocks.
 system.cpu.icache.warmup_cycle                      0                       # Cycle when the warmup percentage was hit.
 system.cpu.icache.writebacks                        0                       # number of writebacks
-system.cpu.idleCycles                           11557                       # Total number of cycles that the CPU has spent unscheduled due to idling
-system.cpu.iew.EXEC:branches                     1339                       # Number of branches executed
+system.cpu.idleCycles                            9434                       # Total number of cycles that the CPU has spent unscheduled due to idling
+system.cpu.iew.EXEC:branches                     1551                       # Number of branches executed
 system.cpu.iew.EXEC:nop                             0                       # number of nop insts executed
-system.cpu.iew.EXEC:rate                     0.445373                       # Inst execution rate
-system.cpu.iew.EXEC:refs                         2437                       # number of memory reference insts executed
-system.cpu.iew.EXEC:stores                       1088                       # Number of stores executed
+system.cpu.iew.EXEC:rate                     0.676151                       # Inst execution rate
+system.cpu.iew.EXEC:refs                         2971                       # number of memory reference insts executed
+system.cpu.iew.EXEC:stores                       1306                       # Number of stores executed
 system.cpu.iew.EXEC:swp                             0                       # number of swp insts executed
-system.cpu.iew.WB:consumers                      9192                       # num instructions consuming a value
-system.cpu.iew.WB:count                         11991                       # cumulative count of insts written-back
-system.cpu.iew.WB:fanout                     0.803198                       # average fanout of values written-back
+system.cpu.iew.WB:consumers                     14704                       # num instructions consuming a value
+system.cpu.iew.WB:count                         15138                       # cumulative count of insts written-back
+system.cpu.iew.WB:fanout                     0.679747                       # average fanout of values written-back
 system.cpu.iew.WB:penalized                         0                       # number of instrctions required to write to 'other' IQ
 system.cpu.iew.WB:penalized_rate                    0                       # fraction of instructions written-back that wrote to 'other' IQ
-system.cpu.iew.WB:producers                      7383                       # num instructions producing a value
-system.cpu.iew.WB:rate                       0.439617                       # insts written-back per cycle
-system.cpu.iew.WB:sent                          12024                       # cumulative count of insts sent to commit
-system.cpu.iew.branchMispredicts                  474                       # Number of branch mispredicts detected at execute
-system.cpu.iew.iewBlockCycles                      40                       # Number of cycles IEW is blocking
-system.cpu.iew.iewDispLoadInsts                  1510                       # Number of dispatched load instructions
-system.cpu.iew.iewDispNonSpecInsts                 16                       # Number of dispatched non-speculative instructions
-system.cpu.iew.iewDispSquashedInsts               424                       # Number of squashed instructions skipped by dispatch
-system.cpu.iew.iewDispStoreInsts                 1230                       # Number of dispatched store instructions
-system.cpu.iew.iewDispatchedInsts               13620                       # Number of instructions dispatched to IQ
-system.cpu.iew.iewExecLoadInsts                  1349                       # Number of load instructions executed
-system.cpu.iew.iewExecSquashedInsts               556                       # Number of squashed instructions skipped in execute
-system.cpu.iew.iewExecutedInsts                 12148                       # Number of executed instructions
-system.cpu.iew.iewIQFullEvents                      2                       # Number of times the IQ has become full, causing a stall
+system.cpu.iew.WB:producers                      9995                       # num instructions producing a value
+system.cpu.iew.WB:rate                       0.662669                       # insts written-back per cycle
+system.cpu.iew.WB:sent                          15263                       # cumulative count of insts sent to commit
+system.cpu.iew.branchMispredicts                  565                       # Number of branch mispredicts detected at execute
+system.cpu.iew.iewBlockCycles                     187                       # Number of cycles IEW is blocking
+system.cpu.iew.iewDispLoadInsts                  2105                       # Number of dispatched load instructions
+system.cpu.iew.iewDispNonSpecInsts                 30                       # Number of dispatched non-speculative instructions
+system.cpu.iew.iewDispSquashedInsts               207                       # Number of squashed instructions skipped by dispatch
+system.cpu.iew.iewDispStoreInsts                 1639                       # Number of dispatched store instructions
+system.cpu.iew.iewDispatchedInsts               19184                       # Number of instructions dispatched to IQ
+system.cpu.iew.iewExecLoadInsts                  1665                       # Number of load instructions executed
+system.cpu.iew.iewExecSquashedInsts               710                       # Number of squashed instructions skipped in execute
+system.cpu.iew.iewExecutedInsts                 15446                       # Number of executed instructions
+system.cpu.iew.iewIQFullEvents                     12                       # Number of times the IQ has become full, causing a stall
 system.cpu.iew.iewIdleCycles                        0                       # Number of cycles IEW is idle
 system.cpu.iew.iewLSQFullEvents                     0                       # Number of times the LSQ has become full, causing a stall
-system.cpu.iew.iewSquashCycles                    701                       # Number of cycles IEW is squashing
-system.cpu.iew.iewUnblockCycles                     5                       # Number of cycles IEW is unblocking
+system.cpu.iew.iewSquashCycles                   1504                       # Number of cycles IEW is squashing
+system.cpu.iew.iewUnblockCycles                    20                       # Number of cycles IEW is unblocking
 system.cpu.iew.lsq.thread.0.blockedLoads            0                       # Number of blocked loads due to partial load-store forwarding
 system.cpu.iew.lsq.thread.0.cacheBlocked            0                       # Number of times an access to memory failed due to the cache being blocked
-system.cpu.iew.lsq.thread.0.forwLoads              23                       # Number of loads that had data forwarded from stores
-system.cpu.iew.lsq.thread.0.ignoredResponses            1                       # Number of memory responses ignored because the instruction is squashed
+system.cpu.iew.lsq.thread.0.forwLoads              68                       # Number of loads that had data forwarded from stores
+system.cpu.iew.lsq.thread.0.ignoredResponses           12                       # Number of memory responses ignored because the instruction is squashed
 system.cpu.iew.lsq.thread.0.invAddrLoads            0                       # Number of loads ignored due to an invalid address
 system.cpu.iew.lsq.thread.0.invAddrSwpfs            0                       # Number of software prefetches ignored due to an invalid address
-system.cpu.iew.lsq.thread.0.memOrderViolation           10                       # Number of memory ordering violations
-system.cpu.iew.lsq.thread.0.rescheduledLoads            0                       # Number of loads that were rescheduled
-system.cpu.iew.lsq.thread.0.squashedLoads          454                       # Number of loads squashed
-system.cpu.iew.lsq.thread.0.squashedStores          296                       # Number of stores squashed
-system.cpu.iew.memOrderViolationEvents             10                       # Number of memory order violations
-system.cpu.iew.predictedNotTakenIncorrect          385                       # Number of branches that were predicted not taken incorrectly
-system.cpu.iew.predictedTakenIncorrect             89                       # Number of branches that were predicted taken incorrectly
-system.cpu.int_regfile_reads                    19557                       # number of integer regfile reads
-system.cpu.int_regfile_writes                   11326                       # number of integer regfile writes
-system.cpu.ipc                               0.359620                       # IPC: Instructions Per Cycle
-system.cpu.ipc_total                         0.359620                       # IPC: Total IPC of All Threads
-system.cpu.iq.ISSUE:FU_type_0::No_OpClass            3      0.02%      0.02% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::IntAlu           10141     79.83%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::IntMult              0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::IntDiv               0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatAdd             0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatCmp             0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatCvt             0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatMult            0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatDiv             0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::FloatSqrt            0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdAdd              0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdAddAcc            0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdAlu              0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdCmp              0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdCvt              0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdMisc             0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdMult             0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdMultAcc            0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdShift            0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdShiftAcc            0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdSqrt             0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatAdd            0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatAlu            0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatCmp            0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatCvt            0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatDiv            0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatMisc            0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatMult            0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatMultAcc            0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::SimdFloatSqrt            0      0.00%     79.85% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::MemRead           1414     11.13%     90.98% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::MemWrite          1146      9.02%    100.00% # Type of FU issued
+system.cpu.iew.lsq.thread.0.memOrderViolation           31                       # Number of memory ordering violations
+system.cpu.iew.lsq.thread.0.rescheduledLoads            1                       # Number of loads that were rescheduled
+system.cpu.iew.lsq.thread.0.squashedLoads         1049                       # Number of loads squashed
+system.cpu.iew.lsq.thread.0.squashedStores          705                       # Number of stores squashed
+system.cpu.iew.memOrderViolationEvents             31                       # Number of memory order violations
+system.cpu.iew.predictedNotTakenIncorrect          496                       # Number of branches that were predicted not taken incorrectly
+system.cpu.iew.predictedTakenIncorrect             69                       # Number of branches that were predicted taken incorrectly
+system.cpu.int_regfile_reads                    23051                       # number of integer regfile reads
+system.cpu.int_regfile_writes                   14062                       # number of integer regfile writes
+system.cpu.ipc                               0.429391                       # IPC: Instructions Per Cycle
+system.cpu.ipc_total                         0.429391                       # IPC: Total IPC of All Threads
+system.cpu.iq.ISSUE:FU_type_0::No_OpClass            4      0.02%      0.02% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::IntAlu           12967     80.26%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::IntMult              0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::IntDiv               0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatAdd             0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatCmp             0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatCvt             0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatMult            0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatDiv             0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::FloatSqrt            0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdAdd              0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdAddAcc            0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdAlu              0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdCmp              0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdCvt              0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdMisc             0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdMult             0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdMultAcc            0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdShift            0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdShiftAcc            0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdSqrt             0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatAdd            0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatAlu            0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatCmp            0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatCvt            0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatDiv            0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatMisc            0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatMult            0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatMultAcc            0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::SimdFloatSqrt            0      0.00%     80.29% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::MemRead           1786     11.05%     91.34% # Type of FU issued
+system.cpu.iq.ISSUE:FU_type_0::MemWrite          1399      8.66%    100.00% # Type of FU issued
 system.cpu.iq.ISSUE:FU_type_0::IprAccess            0      0.00%    100.00% # Type of FU issued
 system.cpu.iq.ISSUE:FU_type_0::InstPrefetch            0      0.00%    100.00% # Type of FU issued
-system.cpu.iq.ISSUE:FU_type_0::total            12704                       # Type of FU issued
-system.cpu.iq.ISSUE:fu_busy_cnt                     4                       # FU busy when requested
-system.cpu.iq.ISSUE:fu_busy_rate             0.000315                       # FU busy rate (busy events/executed inst)
+system.cpu.iq.ISSUE:FU_type_0::total            16156                       # Type of FU issued
+system.cpu.iq.ISSUE:fu_busy_cnt                   142                       # FU busy when requested
+system.cpu.iq.ISSUE:fu_busy_rate             0.008789                       # FU busy rate (busy events/executed inst)
 system.cpu.iq.ISSUE:fu_full::No_OpClass             0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::IntAlu                 0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::IntMult                0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::IntDiv                 0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatAdd               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatCmp               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatCvt               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatMult              0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatDiv               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::FloatSqrt              0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdAdd                0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdAddAcc             0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdAlu                0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdCmp                0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdCvt                0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdMisc               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdMult               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdMultAcc            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdShift              0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdShiftAcc            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdSqrt               0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatAdd            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatAlu            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatCmp            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatCvt            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatDiv            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatMisc            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatMult            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatMultAcc            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::SimdFloatSqrt            0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::MemRead                4    100.00%    100.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:fu_full::MemWrite               0      0.00%    100.00% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::IntAlu                97     68.31%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::IntMult                0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::IntDiv                 0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatAdd               0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatCmp               0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatCvt               0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatMult              0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatDiv               0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::FloatSqrt              0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdAdd                0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdAddAcc             0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdAlu                0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdCmp                0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdCvt                0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdMisc               0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdMult               0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdMultAcc            0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdShift              0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdShiftAcc            0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdSqrt               0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatAdd            0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatAlu            0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatCmp            0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatCvt            0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatDiv            0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatMisc            0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatMult            0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatMultAcc            0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::SimdFloatSqrt            0      0.00%     68.31% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::MemRead               26     18.31%     86.62% # attempts to use FU when none available
+system.cpu.iq.ISSUE:fu_full::MemWrite              19     13.38%    100.00% # attempts to use FU when none available
 system.cpu.iq.ISSUE:fu_full::IprAccess              0      0.00%    100.00% # attempts to use FU when none available
 system.cpu.iq.ISSUE:fu_full::InstPrefetch            0      0.00%    100.00% # attempts to use FU when none available
-system.cpu.iq.ISSUE:issued_per_cycle::samples        15719                       # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::mean     0.808194                       # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::stdev     0.980491                       # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::samples        13410                       # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::mean     1.204773                       # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::stdev     1.912582                       # Number of insts issued each cycle
 system.cpu.iq.ISSUE:issued_per_cycle::underflows            0      0.00%      0.00% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::0          7896     50.23%     50.23% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::1          4146     26.38%     76.61% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::2          2688     17.10%     93.71% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::3           806      5.13%     98.84% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::4           156      0.99%     99.83% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::5            22      0.14%     99.97% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::6             5      0.03%    100.00% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::7             0      0.00%    100.00% # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::8             0      0.00%    100.00% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::0          8282     61.76%     61.76% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::1          1307      9.75%     71.51% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::2           986      7.35%     78.86% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::3           745      5.56%     84.41% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::4           787      5.87%     90.28% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::5           588      4.38%     94.67% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::6           498      3.71%     98.38% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::7           170      1.27%     99.65% # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::8            47      0.35%    100.00% # Number of insts issued each cycle
 system.cpu.iq.ISSUE:issued_per_cycle::overflows            0      0.00%    100.00% # Number of insts issued each cycle
 system.cpu.iq.ISSUE:issued_per_cycle::min_value            0                       # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::max_value            6                       # Number of insts issued each cycle
-system.cpu.iq.ISSUE:issued_per_cycle::total        15719                       # Number of insts issued each cycle
-system.cpu.iq.ISSUE:rate                     0.465757                       # Inst issue rate
-system.cpu.iq.fp_alu_accesses                       4                       # Number of floating point alu accesses
-system.cpu.iq.fp_inst_queue_reads                   8                       # Number of floating instruction queue reads
-system.cpu.iq.fp_inst_queue_wakeup_accesses            2                       # Number of floating instruction queue wakeup accesses
-system.cpu.iq.fp_inst_queue_writes                  8                       # Number of floating instruction queue writes
-system.cpu.iq.int_alu_accesses                  12701                       # Number of integer alu accesses
-system.cpu.iq.int_inst_queue_reads              41124                       # Number of integer instruction queue reads
-system.cpu.iq.int_inst_queue_wakeup_accesses        11989                       # Number of integer instruction queue wakeup accesses
-system.cpu.iq.int_inst_queue_writes             16903                       # Number of integer instruction queue writes
-system.cpu.iq.iqInstsAdded                      13604                       # Number of instructions added to the IQ (excludes non-spec)
-system.cpu.iq.iqInstsIssued                     12704                       # Number of instructions issued
-system.cpu.iq.iqNonSpecInstsAdded                  16                       # Number of non-speculative instructions added to the IQ
-system.cpu.iq.iqSquashedInstsExamined            3282                       # Number of squashed instructions iterated over during squash; mainly for profiling
-system.cpu.iq.iqSquashedInstsIssued                 1                       # Number of squashed instructions issued
-system.cpu.iq.iqSquashedNonSpecRemoved              3                       # Number of squashed non-spec instructions that were removed
-system.cpu.iq.iqSquashedOperandsExamined         3903                       # Number of squashed operands that are examined and possibly removed from graph
-system.cpu.l2cache.ReadExReq_accesses              78                       # number of ReadExReq accesses(hits+misses)
-system.cpu.l2cache.ReadExReq_avg_miss_latency 34512.820513                       # average ReadExReq miss latency
-system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31358.974359                       # average ReadExReq mshr miss latency
-system.cpu.l2cache.ReadExReq_miss_latency      2692000                       # number of ReadExReq miss cycles
+system.cpu.iq.ISSUE:issued_per_cycle::max_value            8                       # Number of insts issued each cycle
+system.cpu.iq.ISSUE:issued_per_cycle::total        13410                       # Number of insts issued each cycle
+system.cpu.iq.ISSUE:rate                     0.707232                       # Inst issue rate
+system.cpu.iq.fp_alu_accesses                       5                       # Number of floating point alu accesses
+system.cpu.iq.fp_inst_queue_reads                   9                       # Number of floating instruction queue reads
+system.cpu.iq.fp_inst_queue_wakeup_accesses            4                       # Number of floating instruction queue wakeup accesses
+system.cpu.iq.fp_inst_queue_writes                  4                       # Number of floating instruction queue writes
+system.cpu.iq.int_alu_accesses                  16289                       # Number of integer alu accesses
+system.cpu.iq.int_inst_queue_reads              45908                       # Number of integer instruction queue reads
+system.cpu.iq.int_inst_queue_wakeup_accesses        15134                       # Number of integer instruction queue wakeup accesses
+system.cpu.iq.int_inst_queue_writes             27963                       # Number of integer instruction queue writes
+system.cpu.iq.iqInstsAdded                      19154                       # Number of instructions added to the IQ (excludes non-spec)
+system.cpu.iq.iqInstsIssued                     16156                       # Number of instructions issued
+system.cpu.iq.iqNonSpecInstsAdded                  30                       # Number of non-speculative instructions added to the IQ
+system.cpu.iq.iqSquashedInstsExamined            8758                       # Number of squashed instructions iterated over during squash; mainly for profiling
+system.cpu.iq.iqSquashedInstsIssued                53                       # Number of squashed instructions issued
+system.cpu.iq.iqSquashedNonSpecRemoved             17                       # Number of squashed non-spec instructions that were removed
+system.cpu.iq.iqSquashedOperandsExamined        11067                       # Number of squashed operands that are examined and possibly removed from graph
+system.cpu.l2cache.ReadExReq_accesses              77                       # number of ReadExReq accesses(hits+misses)
+system.cpu.l2cache.ReadExReq_avg_miss_latency 34616.883117                       # average ReadExReq miss latency
+system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31389.610390                       # average ReadExReq mshr miss latency
+system.cpu.l2cache.ReadExReq_miss_latency      2665500                       # number of ReadExReq miss cycles
 system.cpu.l2cache.ReadExReq_miss_rate              1                       # miss rate for ReadExReq accesses
-system.cpu.l2cache.ReadExReq_misses                78                       # number of ReadExReq misses
-system.cpu.l2cache.ReadExReq_mshr_miss_latency      2446000                       # number of ReadExReq MSHR miss cycles
+system.cpu.l2cache.ReadExReq_misses                77                       # number of ReadExReq misses
+system.cpu.l2cache.ReadExReq_mshr_miss_latency      2417000                       # number of ReadExReq MSHR miss cycles
 system.cpu.l2cache.ReadExReq_mshr_miss_rate            1                       # mshr miss rate for ReadExReq accesses
-system.cpu.l2cache.ReadExReq_mshr_misses           78                       # number of ReadExReq MSHR misses
-system.cpu.l2cache.ReadReq_accesses               324                       # number of ReadReq accesses(hits+misses)
-system.cpu.l2cache.ReadReq_avg_miss_latency 34181.677019                       # average ReadReq miss latency
-system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 30998.447205                       # average ReadReq mshr miss latency
+system.cpu.l2cache.ReadExReq_mshr_misses           77                       # number of ReadExReq MSHR misses
+system.cpu.l2cache.ReadReq_accesses               362                       # number of ReadReq accesses(hits+misses)
+system.cpu.l2cache.ReadReq_avg_miss_latency 34245.833333                       # average ReadReq miss latency
+system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31040.277778                       # average ReadReq mshr miss latency
 system.cpu.l2cache.ReadReq_hits                     2                       # number of ReadReq hits
-system.cpu.l2cache.ReadReq_miss_latency      11006500                       # number of ReadReq miss cycles
-system.cpu.l2cache.ReadReq_miss_rate         0.993827                       # miss rate for ReadReq accesses
-system.cpu.l2cache.ReadReq_misses                 322                       # number of ReadReq misses
-system.cpu.l2cache.ReadReq_mshr_miss_latency      9981500                       # number of ReadReq MSHR miss cycles
-system.cpu.l2cache.ReadReq_mshr_miss_rate     0.993827                       # mshr miss rate for ReadReq accesses
-system.cpu.l2cache.ReadReq_mshr_misses            322                       # number of ReadReq MSHR misses
+system.cpu.l2cache.ReadReq_miss_latency      12328500                       # number of ReadReq miss cycles
+system.cpu.l2cache.ReadReq_miss_rate         0.994475                       # miss rate for ReadReq accesses
+system.cpu.l2cache.ReadReq_misses                 360                       # number of ReadReq misses
+system.cpu.l2cache.ReadReq_mshr_miss_latency     11174500                       # number of ReadReq MSHR miss cycles
+system.cpu.l2cache.ReadReq_mshr_miss_rate     0.994475                       # mshr miss rate for ReadReq accesses
+system.cpu.l2cache.ReadReq_mshr_misses            360                       # number of ReadReq MSHR misses
 system.cpu.l2cache.avg_blocked_cycles::no_mshrs     no_value                       # average number of cycles each access was blocked
 system.cpu.l2cache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
-system.cpu.l2cache.avg_refs                  0.006231                       # Average number of references to valid blocks.
+system.cpu.l2cache.avg_refs                  0.005571                       # Average number of references to valid blocks.
 system.cpu.l2cache.blocked::no_mshrs                0                       # number of cycles access was blocked
 system.cpu.l2cache.blocked::no_targets              0                       # number of cycles access was blocked
 system.cpu.l2cache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.l2cache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.l2cache.cache_copies                     0                       # number of cache copies performed
-system.cpu.l2cache.demand_accesses                402                       # number of demand (read+write) accesses
-system.cpu.l2cache.demand_avg_miss_latency 34246.250000                       # average overall miss latency
-system.cpu.l2cache.demand_avg_mshr_miss_latency 31068.750000                       # average overall mshr miss latency
+system.cpu.l2cache.demand_accesses                439                       # number of demand (read+write) accesses
+system.cpu.l2cache.demand_avg_miss_latency 34311.212815                       # average overall miss latency
+system.cpu.l2cache.demand_avg_mshr_miss_latency 31101.830664                       # average overall mshr miss latency
 system.cpu.l2cache.demand_hits                      2                       # number of demand (read+write) hits
-system.cpu.l2cache.demand_miss_latency       13698500                       # number of demand (read+write) miss cycles
-system.cpu.l2cache.demand_miss_rate          0.995025                       # miss rate for demand accesses
-system.cpu.l2cache.demand_misses                  400                       # number of demand (read+write) misses
+system.cpu.l2cache.demand_miss_latency       14994000                       # number of demand (read+write) miss cycles
+system.cpu.l2cache.demand_miss_rate          0.995444                       # miss rate for demand accesses
+system.cpu.l2cache.demand_misses                  437                       # number of demand (read+write) misses
 system.cpu.l2cache.demand_mshr_hits                 0                       # number of demand (read+write) MSHR hits
-system.cpu.l2cache.demand_mshr_miss_latency     12427500                       # number of demand (read+write) MSHR miss cycles
-system.cpu.l2cache.demand_mshr_miss_rate     0.995025                       # mshr miss rate for demand accesses
-system.cpu.l2cache.demand_mshr_misses             400                       # number of demand (read+write) MSHR misses
+system.cpu.l2cache.demand_mshr_miss_latency     13591500                       # number of demand (read+write) MSHR miss cycles
+system.cpu.l2cache.demand_mshr_miss_rate     0.995444                       # mshr miss rate for demand accesses
+system.cpu.l2cache.demand_mshr_misses             437                       # number of demand (read+write) MSHR misses
 system.cpu.l2cache.fast_writes                      0                       # number of fast writes performed
 system.cpu.l2cache.mshr_cap_events                  0                       # number of times MSHR cap was activated
 system.cpu.l2cache.no_allocate_misses               0                       # Number of misses that were no-allocate
-system.cpu.l2cache.occ_%::0                  0.004917                       # Average percentage of cache occupancy
-system.cpu.l2cache.occ_blocks::0           161.123348                       # Average occupied blocks per context
-system.cpu.l2cache.overall_accesses               402                       # number of overall (read+write) accesses
-system.cpu.l2cache.overall_avg_miss_latency 34246.250000                       # average overall miss latency
-system.cpu.l2cache.overall_avg_mshr_miss_latency 31068.750000                       # average overall mshr miss latency
+system.cpu.l2cache.occ_%::0                  0.005436                       # Average percentage of cache occupancy
+system.cpu.l2cache.occ_blocks::0           178.138745                       # Average occupied blocks per context
+system.cpu.l2cache.overall_accesses               439                       # number of overall (read+write) accesses
+system.cpu.l2cache.overall_avg_miss_latency 34311.212815                       # average overall miss latency
+system.cpu.l2cache.overall_avg_mshr_miss_latency 31101.830664                       # average overall mshr miss latency
 system.cpu.l2cache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
 system.cpu.l2cache.overall_hits                     2                       # number of overall hits
-system.cpu.l2cache.overall_miss_latency      13698500                       # number of overall miss cycles
-system.cpu.l2cache.overall_miss_rate         0.995025                       # miss rate for overall accesses
-system.cpu.l2cache.overall_misses                 400                       # number of overall misses
+system.cpu.l2cache.overall_miss_latency      14994000                       # number of overall miss cycles
+system.cpu.l2cache.overall_miss_rate         0.995444                       # miss rate for overall accesses
+system.cpu.l2cache.overall_misses                 437                       # number of overall misses
 system.cpu.l2cache.overall_mshr_hits                0                       # number of overall MSHR hits
-system.cpu.l2cache.overall_mshr_miss_latency     12427500                       # number of overall MSHR miss cycles
-system.cpu.l2cache.overall_mshr_miss_rate     0.995025                       # mshr miss rate for overall accesses
-system.cpu.l2cache.overall_mshr_misses            400                       # number of overall MSHR misses
+system.cpu.l2cache.overall_mshr_miss_latency     13591500                       # number of overall MSHR miss cycles
+system.cpu.l2cache.overall_mshr_miss_rate     0.995444                       # mshr miss rate for overall accesses
+system.cpu.l2cache.overall_mshr_misses            437                       # number of overall MSHR misses
 system.cpu.l2cache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
 system.cpu.l2cache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
 system.cpu.l2cache.replacements                     0                       # number of replacements
-system.cpu.l2cache.sampled_refs                   321                       # Sample count of references to valid blocks.
+system.cpu.l2cache.sampled_refs                   359                       # Sample count of references to valid blocks.
 system.cpu.l2cache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
-system.cpu.l2cache.tagsinuse               161.123348                       # Cycle average of tags in use
+system.cpu.l2cache.tagsinuse               178.138745                       # Cycle average of tags in use
 system.cpu.l2cache.total_refs                       2                       # Total number of references to valid blocks.
 system.cpu.l2cache.warmup_cycle                     0                       # Cycle when the warmup percentage was hit.
 system.cpu.l2cache.writebacks                       0                       # number of writebacks
-system.cpu.memDep0.conflictingLoads                 7                       # Number of conflicting loads.
-system.cpu.memDep0.conflictingStores                2                       # Number of conflicting stores.
-system.cpu.memDep0.insertedLoads                 1510                       # Number of loads inserted to the mem dependence unit.
-system.cpu.memDep0.insertedStores                1230                       # Number of stores inserted to the mem dependence unit.
-system.cpu.misc_regfile_reads                    5444                       # number of misc regfile reads
-system.cpu.numCycles                            27276                       # number of cpu cycles simulated
+system.cpu.memDep0.conflictingLoads                24                       # Number of conflicting loads.
+system.cpu.memDep0.conflictingStores                3                       # Number of conflicting stores.
+system.cpu.memDep0.insertedLoads                 2105                       # Number of loads inserted to the mem dependence unit.
+system.cpu.memDep0.insertedStores                1639                       # Number of stores inserted to the mem dependence unit.
+system.cpu.misc_regfile_reads                    6857                       # number of misc regfile reads
+system.cpu.numCycles                            22844                       # number of cpu cycles simulated
 system.cpu.numWorkItemsCompleted                    0                       # number of work items this cpu completed
 system.cpu.numWorkItemsStarted                      0                       # number of work items this cpu started
-system.cpu.rename.RENAME:BlockCycles               87                       # Number of cycles rename is blocking
+system.cpu.rename.RENAME:BlockCycles              565                       # Number of cycles rename is blocking
 system.cpu.rename.RENAME:CommittedMaps           9368                       # Number of HB maps that are committed
-system.cpu.rename.RENAME:IQFullEvents               6                       # Number of times rename has blocked due to IQ full
-system.cpu.rename.RENAME:IdleCycles              6548                       # Number of cycles rename is idle
-system.cpu.rename.RENAME:LSQFullEvents             15                       # Number of times rename has blocked due to LSQ full
-system.cpu.rename.RENAME:RenameLookups          31415                       # Number of register rename lookups that rename has made
-system.cpu.rename.RENAME:RenamedInsts           14729                       # Number of instructions processed by rename
-system.cpu.rename.RENAME:RenamedOperands        13866                       # Number of destination operands rename has renamed
-system.cpu.rename.RENAME:RunCycles               8021                       # Number of cycles rename is running
-system.cpu.rename.RENAME:SquashCycles             701                       # Number of cycles rename is squashing
-system.cpu.rename.RENAME:UnblockCycles            105                       # Number of cycles rename is unblocking
-system.cpu.rename.RENAME:UndoneMaps              4498                       # Number of HB maps that are undone due to squashing
+system.cpu.rename.RENAME:IQFullEvents              51                       # Number of times rename has blocked due to IQ full
+system.cpu.rename.RENAME:IdleCycles              7399                       # Number of cycles rename is idle
+system.cpu.rename.RENAME:LSQFullEvents            247                       # Number of times rename has blocked due to LSQ full
+system.cpu.rename.RENAME:ROBFullEvents              3                       # Number of times rename has blocked due to ROB full
+system.cpu.rename.RENAME:RenameLookups          44700                       # Number of register rename lookups that rename has made
+system.cpu.rename.RENAME:RenamedInsts           21187                       # Number of instructions processed by rename
+system.cpu.rename.RENAME:RenamedOperands        19905                       # Number of destination operands rename has renamed
+system.cpu.rename.RENAME:RunCycles               3124                       # Number of cycles rename is running
+system.cpu.rename.RENAME:SquashCycles            1504                       # Number of cycles rename is squashing
+system.cpu.rename.RENAME:UnblockCycles            378                       # Number of cycles rename is unblocking
+system.cpu.rename.RENAME:UndoneMaps             10537                       # Number of HB maps that are undone due to squashing
 system.cpu.rename.RENAME:fp_rename_lookups           16                       # Number of floating rename lookups
-system.cpu.rename.RENAME:int_rename_lookups        31399                       # Number of integer rename lookups
-system.cpu.rename.RENAME:serializeStallCycles          257                       # count of cycles rename stalled for serializing inst
-system.cpu.rename.RENAME:serializingInsts           19                       # count of serializing insts renamed
-system.cpu.rename.RENAME:skidInsts                159                       # count of insts added to the skid buffer
-system.cpu.rename.RENAME:tempSerializingInsts           16                       # count of temporary serializing insts renamed
-system.cpu.rob.rob_reads                        28615                       # The number of ROB reads
-system.cpu.rob.rob_writes                       27943                       # The number of ROB writes
-system.cpu.timesIdled                             206                       # Number of times that the entire CPU went into an idle state and unscheduled itself
+system.cpu.rename.RENAME:int_rename_lookups        44684                       # Number of integer rename lookups
+system.cpu.rename.RENAME:serializeStallCycles          440                       # count of cycles rename stalled for serializing inst
+system.cpu.rename.RENAME:serializingInsts           32                       # count of serializing insts renamed
+system.cpu.rename.RENAME:skidInsts               1476                       # count of insts added to the skid buffer
+system.cpu.rename.RENAME:tempSerializingInsts           31                       # count of temporary serializing insts renamed
+system.cpu.rob.rob_reads                        30950                       # The number of ROB reads
+system.cpu.rob.rob_writes                       39896                       # The number of ROB writes
+system.cpu.timesIdled                             184                       # Number of times that the entire CPU went into an idle state and unscheduled itself
 system.cpu.workload.PROG:num_syscalls              11                       # Number of system calls
 
 ---------- End Simulation Statistics   ----------