arch-arm: Implementation of SelfHosted Debug Software step

This commit implements SelfHosted Debug Software step as is defined in
Armv8 Reference manual chapter D2.

+ decoder.hh/cc/isa: Checks the software step bit in order to skip the instruction
              before its decode.
+ faults.hh/cc: implemented SoftwareStep exception and proper modification
                of spsr during the invoke of other exceptions
+ isa.cc: Set debug mask if needed during cpsr modification
+ tlb.cc: Checks if software step is in ACTIVE state to avoid trigger
          breakpoint or watchpoint exception
+ self_debug.hh/cc: Implementation of State change and ss bit based during eret.
+ types.hh: Define sofware step flags like step, load or stepped to check the different flags
        that triggering software step should use for the ISS code.
+ pseudo.hh/isa: Triggers the sofware step esception after decode.
+ static_inst.cc: Call debugExceptionReturnsSS durint eret routine.

Change-Id: I3a64507c64842c34c76ad7f6daa5f4306bd55d2c
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30617
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Maintainer: Giacomo Travaglini <giacomo.travaglini@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>

mem-ruby: Support device memories

Adds support for device memories in the system and RubySystem classes.
Devices may register memory ranges with the system class and packets
which originate from the device MasterID will update the device memory
in Ruby. In RubySystem functional access is updated to keep the packets
within the Ruby network they originated from.

Change-Id: I47850df1dc1994485d471ccd9da89e8d88eb0d20
JIRA: https://gem5.atlassian.net/browse/GEM5-470
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29653
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>

stats: add --stats-root option to dump only under some SimObjects

This commit makes it possible to make invocations such as:

gem5.opt se.py --stats-root 'system.cpu[:].dtb' --stats-root 'system.membus'

When --stats-root is given, only stats that are under any of the root
SimObjects get dumped. E.g. the above invocation would dump stats such as:

system.cpu0.dtb.walker.pwrStateResidencyTicks::UNDEFINED
system.cpu1.dtb.walker.pwrStateResidencyTicks::UNDEFINED
system.membus.pwrStateResidencyTicks::UNDEFINED
system.membus.trans_dist::ReadReq

but not for example `system.clk_domain.clock`.

If the --stats-root is given, only new stats as defined at:
Idc8ff448b9f70a796427b4a5231e7371485130b4 get dumped, and old ones are
ignored. The commits following that one have done some initial conversion
work, but many stats are still in the old format.

Change-Id: Iadaef26edf9a678b39f774515600884fbaeec497
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/28628
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>

mem: Fix python3 incompatibility issue in slicc's HTML builder

In python3, an iterator does not have the next() method.
next(iterator) works in both python2.7+ and python3.

Change-Id: Ic1ceb993018a0f37e8d30086a054ffc2e311bb46
Signed-off-by: Hoa Nguyen <hoanguyen@ucdavis.edu>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30874
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>

base: Improve error message occurs when base couldn't open a file

Change-Id: Icaa571216f0eed4527a6aaddcf0c6814ad282c56
Signed-off-by: Hoa Nguyen <hoanguyen@ucdavis.edu>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30794
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>

arch-arm: Implementation of ARMv8 SelfDebug Watchpoints

This change includes ArmV8 SelfDebug Watchpoint implementation
as is described in Armv8 Reference manual D2/G2
The changes specific descriptions are as follow:
+ ArmISA.py: Enable up to 16 DBGWn registers
+ isa.cc: Include in setMiscReg specific cases for DBGWCn registers enable bit
+ miscregs_types.hh: Define DBGWC bitwise types
+ miscregs.hh/cc: Definition of watchpoint registers and its initialization
+ tlb.cc: Call for watchpoint entry point on tlb translation for dtlb.
+ fault.cc/hh: Definition/implementation of Watchpoint exception and
               modification on DataAbort Exception accordingly to handle
               AArch32 Watchpoint exceptions.
+ types.hh: Exception Code for watchpoint.
+ self_debug.cc/hh: Watchpoint check and comparison. Definition and
                    implementation of all the watchpoint auxiliar functions.

Change-Id: If275e4df0d28918dd887ab78166e653da875310a
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/28589
Maintainer: Giacomo Travaglini <giacomo.travaglini@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>

util: Add missing iostream header to util/m5/src/commands.cc

Signed-off-by: Hoa Nguyen <hoanguyen@ucdavis.edu>
Change-Id: I93f99284ecda22c73572cc0ffa8c3be0160ce560
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30734
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Reviewed-by: Gabe Black <gabeblack@google.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Gabe Black <gabeblack@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>

arm: Add a missing "break" in an ARM miscreg decode function.

This change accidentally left out a "break" which gcc found and
complained about.

arch-arm: Implementation of Hardware Breakpoint exception

This change adds in the break based on the assumption that the function
should not fall through that case to the next.

Change-Id: Id728a0c9a504d1b6d231d3fe1e7c5ece05d3ac4d
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30654
Reviewed-by: Jordi Vaquero <jordi.vaquero@metempsy.com>
Maintainer: Giacomo Travaglini <giacomo.travaglini@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>

ext: Remove dead code from results.py

This has been tested with vulture:
https://pypi.org/project/vulture

JIRA: https://gem5.atlassian.net/projects/GEM5/issues/GEM5-533

Change-Id: Ib145f8916fdde9f1571eb71ca2fef3501b48804b
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30244
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>

ext: Remove dead code from main.py

This has been tested with vulture:
https://pypi.org/project/vulture

JIRA: https://gem5.atlassian.net/projects/GEM5/issues/GEM5-533

Change-Id: I5f0fbe6c4f5620503c03dfb1b3c8eb1fac31409e
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30243
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>

ext: Remove dead code from configuration.py

This has been tested with vulture:
https://pypi.org/project/vulture

JIRA: https://gem5.atlassian.net/projects/GEM5/issues/GEM5-533

Change-Id: Ibaf812ace94c2ae0e2115552a87fb506a427bb89
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30242
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>

stats: add option to disable alignment spaces in stats.txt file

The alignment spaces in stats.txt takes up a lot of space and increases
simulation time, this commit adds the option to disable them with:

--stats-file stats.txt?spaces=False

Sample old lines with ?desc=False:

system.cpu.op_class::FloatMultAcc                   0      0.00%     65.92%
system.cpu.op_class::FloatDiv                       0      0.00%     65.92%

Sample new lines with ?desc=False;spaces=False:

system.cpu.op_class::FloatMultAcc 0 0.00% 65.92%
system.cpu.op_class::FloatDiv 0 0.00% 65.92%

On a 1000 dumpstats m5op loop spaces=False reduces:

* size: from 38MB to 20MB
* time: from 4.5s to 3.5s

Change-Id: Ib738b996b5646c329094cf61aaa1d977e844e759
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/28627
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>

arch-arm: Fix minor bug PAUTH comparision with 0

Change-Id: I887e5fa256a8c9cc24f7b9ef1fc0353dea555e82
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30615
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Maintainer: Giacomo Travaglini <giacomo.travaglini@arm.com>

arch-arm: Fix SCR.NS compare to 0

Change-Id: Iba7628640bb222fd21fd067ff60dbe4d34f4b196
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30614
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Maintainer: Giacomo Travaglini <giacomo.travaglini@arm.com>

util: Move the call type implementations into their own subdir.

Change-Id: Ie94c2ef4783b6b5700beb0f0bbeb765ce9b03934
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/27551
Tested-by: kokoro <noreply+kokoro@google.com>
Maintainer: Gabe Black <gabeblack@google.com>
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>

util: c++-ify command line arguments in the m5 utility.

Change-Id: Icfdd95c61ac9937823027563d086e5a690870fb4
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/27550
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Gabe Black <gabeblack@google.com>
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Maintainer: Gabe Black <gabeblack@google.com>

util: c++-ify the call type in the m5 utility.

Use a class to track call type information, and mostly avoid having to
use ifdefs to include or not include support for individual call types.

Change-Id: I731c99e67ea1c511d53431df3f77b4a959919a59
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/27549
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Gabe Black <gabeblack@google.com>
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Maintainer: Gabe Black <gabeblack@google.com>

util: Convert the m5 utility to C++.

This will make it possible to use the googletest unit testing framework,
and will let us use c++ mechanisms to simplify and streamline the code.

Change-Id: I8ab358de47ce6b5c2d601cc0b9f2a694b2037a9b
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/27548
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Gabe Black <gabeblack@google.com>
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Maintainer: Gabe Black <gabeblack@google.com>

util: Pull most code out of m5.c.

By pulling the code out, this code can be tested by unit tests.

Change-Id: I2d0510995d3e97d721f1de3024120f0c90b7a5ba
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/27547
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Gabe Black <gabeblack@google.com>
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Maintainer: Gabe Black <gabeblack@google.com>

python,util: Fixed string decoding in include verifier

The Python2 <-> Python3 port included a decode on a string as part of
the include statement git-hook verifier. This results in a failure. To
fix this issue, the file to be checked is opened in binary mode.

This issue was highlighted by Gabe Black here:
https://gem5-review.googlesource.com/c/public/gem5/+/28588

Change-Id: I9a30ecc24d4741853ed1c2d0c03addf57c3e5b6c
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30336
Reviewed-by: Gabe Black <gabeblack@google.com>
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Gabe Black <gabeblack@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>

sim: Fix -Werror=maybe-uninitialized in system.cc

The patch is simply initializing when to 0 before unserializing
the real value

Change-Id: I4e19eeafa9334116b440948af1943f3835803671
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30594
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>

arch-arm: Fix arm switcheroo regressions

These were failing with the combination of:

https://gem5-review.googlesource.com/c/public/gem5/+/29233

with

https://gem5-review.googlesource.com/c/public/gem5/+/27967

Change-Id: I8d3c3701faf4828e76aaa2cb895b9589f057d370
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30616
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>

sim-se: Ignore chmod syscall

chmod caused crashes in certain MIOpen apps with the newer
version of MIOpen used in the Dockerfile. Ignoring it allows
those apps to finish.

Change-Id: If8d144d64f76ae04f384ebf983024c571b26875e
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30534
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>

util: Update MIOpen version used in Docker

The updated MIOpen version uses rocBLAS instead of MIOpenGEMM for
both convolution and rnn GEMM kernels, which provides a speedup in
simulation.

Change-Id: I4b81f18e95d39fd79b22d0bf92563ede61e44e32
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30494
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>

fastmodel,cpu,sim: Eliminate EndQuiesceEvent and plumbing.

Change-Id: Ifca504bc298c09cbc16ef7cded21da455fb1e118
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/25146
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>

sim: Move guts of quiesce and quiesceTick from ThreadContext to System.

The functions in ThreadContext are now just convenience wrappers.

Change-Id: Ib56c4bdd27e611fb667a8056dfae37065f4034eb
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/25145
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>

arch-arm: Implementation of Hardware Breakpoint exception

This code implementes hardware breakpoint exception as part of
software debug explained in ARMv8 reference manual ChapterD2.

+ ArmISA.py: Modify register to allow up to 15 Breakpoint registers
+ Sconscript: Add new file self_debug
+ faults.cc/hh: Defintion and implementation of HardwareBreakpoint
                exception inheriting ArmFault.
+ isa.cc/hh: ArmISA contains now an attribute pointing to the SelfDebug
             object that will be used to be access SelfDebug infrastructure
             Added special cases for setMiscReg to cache debug enable bits.
+ miscregs.hh/cc: Definition and initialization of DBGDCn and DBGDVn
                  registers.
+ tlb.cc/hh: We include the access to check for breakpoint instruction as
             part of the tlb translation process, checking if it comes from a
             fetch in the itlb
+ types.hh: Definition of new bitwise register types.
+ utility.cc/hh: Definition and implementation of auxiliar functions for
                the selfDebug.
+ self_debug.hh/cc: Main files that include the implemenattion of
            breakpoint checks, selfdebug enable and auxiliar functions.

Change-Id: I0e2a4be7f778de560c512253a9148da61e3e7e7a
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/27967
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Maintainer: Giacomo Travaglini <giacomo.travaglini@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>

gpu-compute: Make headTailMap a std::unordered_map

There is no reason that the headTailMap needs to be
sorted, so let's use a std::unordered_map.

Change-Id: I18641b893352c18ec86e3775c8947a05a6c6547d
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29930
Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
Tested-by: kokoro <noreply+kokoro@google.com>

gpu-compute: Remove unused function hostWakeUp from shader

Change-Id: Ib4415a7c5918da03bbd16fe9adb4dd593dcaa95c
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29929
Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
Tested-by: kokoro <noreply+kokoro@google.com>

arch-gcn3: Fix V_MAD_I32_I24 sign extension

We are not properly sign extending the bits we hack off for
V_MAD_I32_I24.

This fixes rnn_fwdBwd 64 1 1 lstm pte assertion failure.

Change-Id: I2516e5715227cbd822e6a62630674f64f7a109e0
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29928
Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com>
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
Tested-by: kokoro <noreply+kokoro@google.com>

arch-gcn3, gpu-compute: Fix issue when reading const operands

Currently, when an instruction has an operand that reads a const
value, it goes thru the same readMiscReg() api call as other
misc registers (real HW registers, not constant values). There
is an issue, however, when casting from the const values (which are
32b) to higher precision values, like 64b.

This change creates a separate, templated function call to the GPU's
ISA state that will return the correct type.

Change-Id: I41965ebeeed20bb70e919fce5ad94d957b3af802
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29927
Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
Tested-by: kokoro <noreply+kokoro@google.com>

arch-gcn3: Updating implementation of atomics

This changeset is moving the access of the data operand
from initiateAcc to the execute method of atomic instructions.

Change-Id: I1debae302f0b13f79ed2b7a9ed2f6b07fcec5128
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29926
Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
Tested-by: kokoro <noreply+kokoro@google.com>

dev: add support for HSA's barrier bit kernel synchronization

This commit adds support for the HSA's barrier bit version of
synchronization.  This method of synchronization is used for all
HIP benchmarks, and thus is necessary to ensure that multiple
kernels from the same queue are synchronizing properly.

Change-Id: I64f2d311a3970b71194e0555e2b932800df65e98
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29925
Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com>
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
Tested-by: kokoro <noreply+kokoro@google.com>

base: Fix build errors with gcc 10.x

This fixes conditions that perform a redundant check to
see if an unsigned value is greater than or equal to
zero. With gcc 10.x, this generates the following error
because of implicit usage of the "-Werror=type-limits"
flag.

"comparison of unsigned expression in '>= 0' is always true"

Change-Id: Ib1a88035ef5fba410d18de0adf614db4bc634faf
Signed-off-by: Sandipan Das <sandipan@linux.ibm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30474
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>

cpu: Use new InstRecord faulting flag in cpu models

This patch sets the faulting flag in atomic, timing, minor and o3 CPU
models.

It also fixes the minor/timing CPU models which were not respecting the
ExecFaulting flag. This is now checked before calling dump() on the
tracing object, to bring it in line with the other CPU models.

Change-Id: I9c7b64cc5605596eb7fcf25fdecaeac5c4b5e3d7
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30135
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>

sim: Add faulting flag to instruction tracing interface

This patch adds a faulting flag to InstRecord.
This allows tracers to identify that the traced instruction has
faulted, when ExecFaulting is enabled. It can be set with
InstRecord::setFaulting() and read with Instrecord::getFaulting().

Change-Id: I390392d59de930533eab101e96dc4d3c76500748
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30134
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>

scons: Add MARSHAL_XXFLAGS_EXTRA for the marshal object

We already provide to the user the CCFLAGS_EXTRA, LDFLAGS_EXTRA
variables to pass flags to scons when compiling/linking gem5.
Those variables are not passed to the marshal object.
We add an extra pair:

MARSHAL_CCFLAGS_EXTRA, MARSHAL_LDFLAGS_EXTRA

to add flag injection capabilities to the marshal object.

The patch is also renaming base_py_env to marshal_env.
This happens for 2 reasons:

1) At the moment the marshal compilation is the only task
making use of the base python environment.

2) Consistency with the EXTRA variable names added with this patch.
I could have named them as BASE_XXFLAGS_EXTRA, but it seems too much
generic and users might be confused by that, as they might think
the BASE_XXFLAGS_EXTRA is a subset of the XXFLAGS_EXTRA so that
setting it will affect gem5 compilation as well.

Change-Id: I3e420caa897059455ff8f35462db2b38da050e93
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30016
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>

arm: Teach gem5 to recognize the gem5 semihosting immediate values.

These give access to the gem5 extension calls, currently only the pseudo
ops.

Change-Id: I60ece82f1f084791971a2de0b54be2f0d9da243e
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/27246
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Maintainer: Giacomo Travaglini <giacomo.travaglini@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Tested-by: Gem5 Cloud Project GCB service account <345032938727@cloudbuild.gserviceaccount.com>

util: Add a semihosting implementation to the aarch64 m5 utility.

This will allow it to work on CPUs that only support semihosting like
ARM's fastmodels.

Change-Id: I74e536d79d0f77b864e1e4b9d73e265b6d0b1fcb
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/27245
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>

util: Allow overriding the magic address in the m5 utility.

This is useful in situations where the address is hard to know ahead of
time, for instance on ARM systems where the address map is hard to
predict.

The default address is now M5OP_ADDR, or 0 if that's not defined.

Change-Id: I3140e05b04365c1a76e52f8c3dc85f472c230ae4
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/27244
Maintainer: Gabe Black <gabeblack@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>

mem-ruby: add cache hit/miss statistics for TCP and TCC

Change-Id: Ifa6fdbb9dd062a3684b9620eac6683c57e651a72
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30174
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Bradford Beckmann <brad.beckmann@amd.com>
Maintainer: Bradford Beckmann <brad.beckmann@amd.com>

arch-gcn3: Implement instruction v_div_fixup_f32

Instruction v_div_fixup_f32 was unimplemented. The
implementation was added by mimicking v_div_fixup_f64.

Change-Id: I9306b198f327e9fde3414aa1bb2bec20503b1efd
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29924
Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com>
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Reviewed-by: Xianwei Zhang <xianwei.zhang@amd.com>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
Tested-by: kokoro <noreply+kokoro@google.com>

arch-gcn3: Implement instruction v_div_fmas_f32

Instruction v_div_fmas_f32 was unimplemented. The
implementation was added by mimicking v_div_fmas_f64.

Change-Id: I262820a7a66877d140eb99b538715c3cae4d1860
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29923
Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com>
Reviewed-by: Xianwei Zhang <xianwei.zhang@amd.com>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
Tested-by: kokoro <noreply+kokoro@google.com>

arch-gcn3: fix bug with SDWA support

Instructions that use the SDWA field need to use the extra SRC0
register associated with the SDWA instruction instead of the
"default" SRC0 register, since the default SRC0 register contains
the SDWA information when SDWA is being used.  This commit fixes
15de044c to take this into account.  Additionally, this commit
removes reads of the registers from the SDWA helper functions,
since they overwrite any changes made to the destination register.
Finally, this change modifies the instructions that use SDWA to
simplify the flow through the execute() functions.

Change-Id: I3bad83133808dfffc6a4c40bbd49c3d76599e669
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29922
Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com>
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
Tested-by: kokoro <noreply+kokoro@google.com>

tests: remove deprecated hsail gpu_hello

Change-Id: I7e15075e7805af732e89c3269fdff9d65a144219
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29921
Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com>
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Reviewed-by: Xianwei Zhang <xianwei.zhang@amd.com>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>

arch-gcn3: add support for unaligned accesses

Previously, with HSAIL, we were guaranteed by the HSA specification
that the GPU will never issue unaligned accesses.  However, now
that we are directly running GCN this is no longer true.
Accordingly, this commit adds support for unaligned accesses.
Moreover, to reduce the replication of nearly identical
code for the different request types, I also added new helper
functions that are called by all the different memory request
producing instruction types in op_encodings.hh.

Adding support for unaligned instructions requires changing
the statusBitVector used to track the status of the memory
requests for each lane from a bit per lane to an int per lane.
This is necessary because an unaligned access may span multiple
cache lines.  In the worst case, each lane may span multiple
cache lines.  There are corresponding changes in the files that
use the statusBitVector.

Change-Id: I319bf2f0f644083e98ca546d2bfe68cf87a5f967
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29920
Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com>
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
Tested-by: kokoro <noreply+kokoro@google.com>

arch-gcn3: Implement instruction v_div_scale_f32

Instruction v_div_scale_f32 was unimplemented, the
implementation was added by mimicking v_div_scale_f64.

Change-Id: I89cdfd02ab01b5936de0e9f6c41e7f3fc4f10ae1
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29919
Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com>
Reviewed-by: Xianwei Zhang <xianwei.zhang@amd.com>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
Tested-by: kokoro <noreply+kokoro@google.com>

config: fix settings of kernel boundary sync flags

Change-Id: I58a8edc5d324bdcaa84e3d715e2712a43e8ede0d
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29918
Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com>
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Reviewed-by: Xianwei Zhang <xianwei.zhang@amd.com>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
Tested-by: kokoro <noreply+kokoro@google.com>

gpu-compute: enable flexible control of kernel boundary syncs

Kernel end release was turned on for VIPER protocol, which
is in fact write-through based and thus no need to have
release operation. This changeset splits the option
'impl_kern_boundary_sync' into 'impl_kern_launch_acq'
and 'impl_kern_end_rel', and turns off release on VIPER.

Change-Id: I5490019b6765a25bd801cc78fb7445b90eb02a3d
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29917
Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com>
Reviewed-by: Xianwei Zhang <xianwei.zhang@amd.com>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
Tested-by: kokoro <noreply+kokoro@google.com>

gpu-compute: remove recvToken from GM pipe exec

Tokens were previously acquired in GM pipe exec but has been moved to
acqCoalescerToken. This removes the extraneous code which was acquiring
tokens twice, causing them to be depleted and triggering an assertion.

Change-Id: Ic92de8f06cc85828b29c69790bdadde057ef1777
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29916
Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com>
Reviewed-by: Matthew Poremba <matthew.poremba@amd.com>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
Tested-by: kokoro <noreply+kokoro@google.com>

mem-ruby: Add DMA support to MOESI_AMD_Base-dir.sm

This change adds DMA support to the MOESI_AMD_Base-dir.sm,
which is needed to support ROCm apps/GCN3 ISA in the VIPER
ptl. The DMA controller is copied from the MOESI_hammer-dma.sm
with few modifications.

Change-Id: I56141436eee1c8f62c2a0915fa3b63b83bbcbc9a
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29914
Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
Tested-by: kokoro <noreply+kokoro@google.com>

mem-ruby: GCN3 and VIPER integration

This patch modifies the Coalescer and VIPER protocol to support memory
synchronization requests and write-completion responses that are
required by upcoming GCN3 implementation.

VIPER protocol is simplified to be a solely write-through protocol.

Change-Id: Iccfa3d749a0301172a1cc567c59609bb548dace6
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29913
Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com>
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Reviewed-by: Bradford Beckmann <brad.beckmann@amd.com>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
Maintainer: Bradford Beckmann <brad.beckmann@amd.com>
Tested-by: kokoro <noreply+kokoro@google.com>

sim: Initialize stackSize and stackMin in MemState

Initialize _stackSize and _stackMin to the maximum stack size values.
The are setup in each arch's Process::initState and may be uninitialized
until then. If a stack fixup occurs before these are setup, addresses
which are not in the stack might be allocated on the stack. This
prevents that until they are initialized in Process::initState. If an
access occurs before that with these initial values, the stack fixup
will simply allocate a page of memory in the stack space. However, it
will not print the typical info messages about growing the stack during
this time.

Change-Id: I9f9316734f4bf1f773fc538922e83b867731c684
JIRA: https://gem5.atlassian.net/browse/GEM5-629
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30394
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Reviewed-by: Gabe Black <gabeblack@google.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>

arch-arm: Add missing isFirstMicroop flags on uop sequences

Certain micro-op sequences were only setting isLastMicroop flags,
and did not set the isFirstMicroop flag. This adds the missing
setFirstMicroop() calls. This fixes tracing issues (e.g. Tarmac)
of certain micro-opped instruction sequences such as LD1.

Change-Id: I7de3ee2759e2b4e1065a7cbac4186f11227d84be
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30034
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>

cpu: Remove default argument values for the update() method in bpreds.

These defaults are never used. There was an assert in the predictors
until recently which was asserting that one of the arguments didn't
have the default value, I think to verify that the default wasn't used
by accident(?), but it could be used purposefully. That would cause
gem5 to crash and has been removed.

Beyond that, there's no reason to have default values for those
arguments in the first place, so this change removes them. That makes
the code slightly simpler, and avoids them being used by accident.

Additionally, the defalt values of the arguments made the function
signatures inconsistent, even though they were supposed to override
each other.

JIRA: https://gem5.atlassian.net/browse/GEM5-483

Change-Id: I28f8d2048985c12ec9cac018a868a32bfa20dc6c
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30375
Reviewed-by: Hsuan Hsu <hsuan.hsu@mediatek.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Gabe Black <gabeblack@google.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>

ext: Remove dead code from runner.py

This has been tested with vulture:
https://pypi.org/project/vulture

JIRA: https://gem5.atlassian.net/projects/GEM5/issues/GEM5-533

Change-Id: Ic851c3681a40b7e61ee53b81b17df52dc1289e9f
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30240
Maintainer: Bobby R. Bruce <bbruce@ucdavis.edu>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Hoa Nguyen <hoanguyen@ucdavis.edu>

ext: Remove dead code from handlers.py

This has been tested with vulture:
https://pypi.org/project/vulture

JIRA: https://gem5.atlassian.net/projects/GEM5/issues/GEM5-533

Change-Id: If878ea1900e2bcd76646b9860f2cc3f808bc5082
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30239
Maintainer: Bobby R. Bruce <bbruce@ucdavis.edu>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Hoa Nguyen <hoanguyen@ucdavis.edu>

ext: Remove dead code from fixture.py

This has been tested with vulture:
https://pypi.org/project/vulture

JIRA: https://gem5.atlassian.net/projects/GEM5/issues/GEM5-533

Change-Id: Ifa55a846ba22a84a0f684ffbf870506af7c1045c
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30238
Maintainer: Bobby R. Bruce <bbruce@ucdavis.edu>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Hoa Nguyen <hoanguyen@ucdavis.edu>

ext: Remove dead code from loader.py

This has been tested with vulture:
https://pypi.org/project/vulture

JIRA: https://gem5.atlassian.net/projects/GEM5/issues/GEM5-533

Change-Id: I4193eff3ea4194f793547767a47c3ac5a64813fd
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30236
Maintainer: Bobby R. Bruce <bbruce@ucdavis.edu>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Hoa Nguyen <hoanguyen@ucdavis.edu>

ext: Remove dead code from helper.py

This has been tested with vulture:
https://pypi.org/project/vulture/

Change-Id: I32aad410145dd142bba8e0b9ab912e9c2bad6001
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30235
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Reviewed-by: Bobby R. Bruce <bbruce@ucdavis.edu>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>

ext: Remove dead code from test_util.py

JIRA: https://gem5.atlassian.net/projects/GEM5/issues/GEM5-533

Change-Id: I722185e890e25ad04271b476c4d1ffa722cade62
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30216
Maintainer: Bobby R. Bruce <bbruce@ucdavis.edu>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Hoa Nguyen <hoanguyen@ucdavis.edu>

ext: Remove LogWrapper/TestLogWrapper from log.py

This patch is removing:

* LogWrapper (wrapping Log)
* TestLogWrapper (wrapping LogWrapper)

There is now a single Log class to be used for logging

JIRA: https://gem5.atlassian.net/projects/GEM5/issues/GEM5-533

Change-Id: I038298565e2ccbe448664a538f888c96fdce8f4a
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30234
Maintainer: Bobby R. Bruce <bbruce@ucdavis.edu>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Hoa Nguyen <hoanguyen@ucdavis.edu>

ext: Fix the MakeFixture setup

It was simply using an invalid log_call helper

JIRA: https://gem5.atlassian.net/projects/GEM5/issues/GEM5-533

Change-Id: I644b1c902a81a27beb6385690d2e43baf4c0919b
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30218
Maintainer: Bobby R. Bruce <bbruce@ucdavis.edu>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Hoa Nguyen <hoanguyen@ucdavis.edu>

ext: Avoid specifying empty interfaces and embrace duck typing

It turns out no handler is implementing

prehandle()
posthandle()

JIRA: https://gem5.atlassian.net/projects/GEM5/issues/GEM5-533

Change-Id: Ie8d92027f29fc33192fcf0d495fd3c4f6e4075aa
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30217
Maintainer: Bobby R. Bruce <bbruce@ucdavis.edu>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Hoa Nguyen <hoanguyen@ucdavis.edu>

ext: Remove sandbox module from testlib

The sandbox module is providing a sandbox environment for
a specific TestCase via the multiprocessing package.

This isolation/complexity is not strictly needed as testlib is already
forking a new process via subprocess. As it is now, a TestRunner will
generate:

TestRunner -> multiprocessing.Process -> subprocess.Popen
(2 generated procs)

With this patch we are removing the intermediate layer

TestRunner -> subprocess.Popen
(1 generated proc)

JIRA: https://gem5.atlassian.net/projects/GEM5/issues/GEM5-533

Change-Id: Icd5cadbe316653a9269ab098ec4c07f21b864ad3
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30215
Maintainer: Bobby R. Bruce <bbruce@ucdavis.edu>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Hoa Nguyen <hoanguyen@ucdavis.edu>

tests: log_call is not returning any value

JIRA: https://gem5.atlassian.net/projects/GEM5/issues/GEM5-533

Change-Id: I2713ddacc762d614e3992718ea234287d06c179a
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30214
Maintainer: Bobby R. Bruce <bbruce@ucdavis.edu>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Hoa Nguyen <hoanguyen@ucdavis.edu>

mem: fixupAddr should not panic if it fails.

This function should just return false in that case, and its callers
should figure out what to do. Otherwise, when calling tryReadBlob in SE
mode, a failure to read the blob makes gem5 panic instead of just
returning false.

Change-Id: I74b9cb98f595c52300d683842ece68c6031d9b85
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30376
Reviewed-by: Sandipan Das <sandipan@linux.ibm.com>
Reviewed-by: Matthew Poremba <matthew.poremba@amd.com>
Maintainer: Gabe Black <gabeblack@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>

arch,cpu,sim: Eliminate the now empty kernel statistics classes.

This includes the base and ISA specific Kernel::Statistics classes, the
plumbing through ThreadContext to access them, and the switching
header file associated with them.

Change-Id: Ia511a59325b629aa9ccc0e695ddd47ff11916499
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/25149
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>

arch,kern,sim: Move the stats in Kernel::Statistics to Workload.

These are the stats in the base class, not in any derived classes. Only
Alpha has an additional stats. These were not really "kernel"
statistics, they were just applicable primarily in FS. They are
potentially applicable to any simulation, but will probably not be
incremented in SE simulations.

Also this merges these stats from being per thread to being per
workload, ie operating system instance. This is probably more relevant
since exactly what thread within a workload runs which particular
instruction is not very important/predictable, but the aggregate
behavior is. If necessary, this could be adjusted in the future to
split things back out again into stats per thread while keeping them
inside the single workload object.

Change-Id: I130e11a9022bdfcadcfb02c7995871503114cd53
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/25147
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>

arch, gpu-compute: Remove HSAIL related files

Change-Id: Iefba0a38d62da7598bbfe3fe6ff46454d35144b1
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/28410
Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
Tested-by: kokoro <noreply+kokoro@google.com>

mem: Use the new unbound port reporting mechanism in the mem ports.

There was an add-hoc check added to getAddrRanges, but the other methods
would just segfault if they tried to talk to their peers. This change
wraps all the calls in try blocks and catches the exception which the
peer will throw if it's the default and the port is not actually
connected to anything.

Change-Id: Ie46be0230f33f74305c599b251ca319a65ba008d
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30296
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>

mem: Fix latency handling in MemDelay

MemDelay wouldn't consume pre-existing delays in the packet and
therefore the latency it adds would overlap with them. This patch
fixes the MemDelay to properly account for them.

Change-Id: I7330fbf1c8161a21523a0b4aab31c72e34bce650
Signed-off-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30055
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>

sim: Add some helpers to catch and reporting using unbound ports.

If a port is unbound, trying to call its peer will likely cause a
segfault. Rather than check if a port is bound every time you go to use
it, we can instead bind to a default peer which just throws an exception
back to the caller. The caller can catch the exception and report the
error.

This change adds a common new class to throw as the exception, and also
a small utility function which reports the error and dies.

Change-Id: Ia58a2030922c73e2fd7d139822bce38d9b0f2171
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30295
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Gabe Black <gabeblack@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>

arm: Add missing overrides to the ARM interrupt object.

Change-Id: Idddc5267d5eb287a0895a1a2e1631ca9a2e789f3
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30294
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Maintainer: Giacomo Travaglini <giacomo.travaglini@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>

gpu-compute, mem-ruby, configs: Add GCN3 ISA support to GPU model

Change-Id: Ibe46970f3ba25d62ca2ade5cbc2054ad746b2254
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29912
Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com>
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
Tested-by: kokoro <noreply+kokoro@google.com>

base: Delete deletePointer helpers

Now that the calls to deletePointer have been replaced by the use
of smart pointers, they can be safely removed.

Change-Id: I91d8b97f7ba3f64dd9948fd343cf0af969886598
Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/24251
Reviewed-by: Bobby R. Bruce <bbruce@ucdavis.edu>
Maintainer: Bobby R. Bruce <bbruce@ucdavis.edu>
Tested-by: kokoro <noreply+kokoro@google.com>

mem: Add a header latency parameter to the XBar

The XBar uses the concept of Layers to model throughput and
instantiates one Layer per master. As it forwards a packet to and from
master, the corresponding Layer is marked as occupied for a number of
cycles. Requests/responses to/from a master are blocked while the
corresponding Layer is occupied. Previously the delay would be
calculated based on the formula 1 + size / width, which assumes that
the Layer is always occupied for 1 cycle while processing the packet
header. This changes makes the header latency a parameter which
defaults to 1.

Change-Id: I12752ab4415617a94fbd8379bcd2ae8982f91fd8
Signed-off-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30054
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Tested-by: kokoro <noreply+kokoro@google.com>

tests: Use default None argument in makeArmSystem

JIRA: https://gem5.atlassian.net/browse/GEM5-387

Change-Id: I18b1ed360b2d285e4df19b896e692356ef6f8819
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30219
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Gabe Black <gabeblack@google.com>

scons: Fix how partial linking is disabled.

Setting disable_partial part way through the checks for various build
targets is incorrect and will affect targets based on the order they're
checked.

This change moves the check earlier, makes it consistent across all
builds whether fast is included or not, and stops passing it in as an
option to makeEnv since it now applies universally.

By disabling partial linking consistently, we avoid missing bugs where
only the "fast" version of gem5 doesn't build correctly because of the
multitude of g++ bugs having to do with combining LTO and partial
linking.

This also simplifies the logic in the SConscript by having fewer
independently moving parts.

Change-Id: Iff69f39868e948d3b9a5b11ea80bbfed19419b59
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29303
Maintainer: Gabe Black <gabeblack@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Gabe Black <gabeblack@google.com>
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>

mem-ruby: Add a missing override.

Change-Id: I7651ca0f4658ddd49cfd13d9d5f7e430f416f41f
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30254
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>

arch,cpu: Add a setThreadContext method to the ISA class.

Also remove ThreadContext pointer parameters to some of the methods in
the ISA classes.

Change-Id: I8e502b1857d299cb2e759a9734a1df4f65f31efe
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29233
Reviewed-by: Brandon Potter <Brandon.Potter@amd.com>
Maintainer: Gabe Black <gabeblack@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>

arch,cpu: Change setCPU to setThreadContext in Interrupts.

The ThreadContext can be used to access the cpu if needed, and is a
more representative interface to various pieces of state than the CPU
itself. Also convert some of the methods in Interupts to use the
locally stored ThreadContext pointer instead of taking one as an
argument. This makes calling those methods simpler and less error
prone.

Change-Id: I740bd99f92e54e052a618a4ae2927ea1c4ece193
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/28988
Reviewed-by: Gabe Black <gabeblack@google.com>
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Maintainer: Gabe Black <gabeblack@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>

sim-se: Ignore unimplemented system call

System call sched_setaffinity causes crashes when running programs
that use ROCm. Ignoring the system call allows for the programs
to run to completion.

Change-Id: I27c767ef81091789e228d47f2bb5f6fa18f11539
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30154
Reviewed-by: Brandon Potter <Brandon.Potter@amd.com>
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Maintainer: Brandon Potter <Brandon.Potter@amd.com>
Tested-by: kokoro <noreply+kokoro@google.com>

sim: Delete an unused member in the System class.

This was supposed to be deleted as part of the change titled:
arch,cpu,dev,sim,mem: Collect System thread elements into a subclass.

but it was left out of the checked in version somehow.

Change-Id: I0dbb0b4fa6ae29649a80d1cb883e48ad50116c31
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30194
Maintainer: Gabe Black <gabeblack@google.com>
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>

misc: Reverted version information to "develop"

Change-Id: I6ee1bae48f2dd0d868dfbb428e93deeb9ee93083
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29833
Reviewed-by: Bobby R. Bruce <bbruce@ucdavis.edu>
Maintainer: Bobby R. Bruce <bbruce@ucdavis.edu>
Tested-by: kokoro <noreply+kokoro@google.com>

arch,cpu,dev,sim,mem: Collect System thread elements into a subclass.

The System class has a few different arrays of values which each
correspond to a thread of execution based on their position. This
change collects them together into a single class to make managing them
easier and less error prone. It also collects methods for manipulating
those threads as an API for that class.

This class acts as a collection point for thread based state which the
System class can look into to get at all its state. It also acts as an
interface for interacting with threads for other classes. This forces
external consumers to use the API instead of accessing the individual
arrays which improves consistency.

Change-Id: Idc4575c5a0b56fe75f5c497809ad91c22bfe26cc
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/25144
Reviewed-by: Bobby R. Bruce <bbruce@ucdavis.edu>
Maintainer: Bobby R. Bruce <bbruce@ucdavis.edu>
Tested-by: kokoro <noreply+kokoro@google.com>

arch,base,cpu,kerm,sim: Build a symbol table for object files.

Instead of calling into object files after the fact and asking them to
put symbols into a target symbol table, this change makes object files
fill in a symbol table themselves at construction. Then, that table can
be retrieved and used to fill in aggregate tables, masked, moved,
and/or filtered to have only one type of symbol binding.

This simplifies the symbol management API of the object file types
significantly, and makes it easier to deal with symbol tables alongside
binaries in the FS workload classes.

Change-Id: Ic9006ca432033d72589867c93d9c5f8a1d87f73c
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/24787
Reviewed-by: Bobby R. Bruce <bbruce@ucdavis.edu>
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Maintainer: Gabe Black <gabeblack@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>

mem-ruby: Add codes for pure virtual functions for compilation

Change-Id: Ic34f9ccf10ec28d68eed236dc6246e2ae2ef1b89
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/28409
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com>
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>

mem-ruby: update memory interfaces to support GPU ISA

This patch deprecates HSA-based memory request types and adds new
types that can be used by real ISA instructions.

Change-Id: Ie107a69d8a35e9de0853f1407392ad01a8b3e930
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/28408
Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
Tested-by: kokoro <noreply+kokoro@google.com>

mem: Default the SE translating port proxy alloc method to NextPage.

This is what's used in 99% of cases, so it makes sense to make it the
default.

Change-Id: I51535b3387d1c1a0d1d89e77cfca10363388b472
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29399
Reviewed-by: Matthew Poremba <matthew.poremba@amd.com>
Maintainer: Gabe Black <gabeblack@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>

misc: Merge hotfix v20.0.0.2 into develop

Change-Id: Ia0ed6bfb70e2ebcb22274569556d690e315702bd

misc: Updated release notes and version number

Change-Id: Ib8583c23f47010222c08ff5aa9cffb842235c784

mem-ruby: Allow MachineID to be unordered key

Define an std::hash function so that MachineID may be used as a key
type for unordered STL containers.

Change-Id: Ibc3bc78149c69683207d8967542fa6e8d545f75c
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29652
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Reviewed-by: Bobby R. Bruce <bbruce@ucdavis.edu>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>

misc: Remove any reference to the ALPHA ISA

Change-Id: Ie761cd69ae0e8e632ca2b92e63a404e8804f0e6f
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30015
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Reviewed-by: Gabe Black <gabeblack@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>

mem-ruby: Fix Prefetcher to RubyPrefetcher in StateMachine.

After renaming Prefetcher to RubyPrefetcher, the slicc generator
should be updated to correctly initialize the prefetcher with
the controller.

Change-Id: Ia12a4640c35aaedd70a4a14e5a10793b060ba924
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29974
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Bobby R. Bruce <bbruce@ucdavis.edu>
Tested-by: kokoro <noreply+kokoro@google.com>

mem-cache: prevent prefetcher from saturating the write buffer

When the write buffer is full, it still has space to store an additional
number of entries (reserve) equal to the number of MSHRs so that if any
of them requires a writeback this can be handled. Even if the slave port
is blocked, a prefetcher can generate new MSHR entries that may lead to
additional writebacks and eventually saturate the reserve space. This is
solved by checking if the cache is blocked for accesses before
prefetching data.

Change-Id: Iaad04dd6786a09eab7afae4a53d1b1299c341f33
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29615
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>

systemc: Replace include of eventq_impl.hh with eventq.hh.

eventq_impl.hh has been merged back into eventq.hh, but that change
passed another change which started using eventq_impl.hh in systemc.

Change-Id: I2e9be5f993fe6a6712a121cd955b0c56a33c87e3
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30014
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Maintainer: Gabe Black <gabeblack@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>

sim,mem,dev: Merge eventq_impl.hh into eventq.hh.

Having some methods (which are supposed to be inline) defined in another
file which is only included sometimes creates a lot of opportunities for
errors. They no longer need to be separate, so merge them together.

Change-Id: I5846e55f53f59b9c2081680a6441659265a765f7
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29409
Maintainer: Gabe Black <gabeblack@google.com>
Reviewed-by: Gabe Black <gabeblack@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>

base,sim: Move DTRACE into base/debug.hh.

All other considerations aside, DTRACE probably fits best in trace.hh
where it is now, but unfortunately that creates an awkward dependence
between that file and eventq.hh and eventq_impl.hh. DTRACE only depends
on flags in the Debug namespace and a universal macro TRACING_ON, so
even though it won't be alongside the things it's most logically
associated with, it will be alongside all of its dependencies.

An alternative would be to re-implement DTRACE in eventq_impl.hh which
wouldn't be too big of a problem because it's so simple, but it's
cleaner and less error prone to still keep a single definition.

Because base/trace.hh includes base/debug.hh, any consumers expecting to
find DTRACE in base/trace.hh will still get that definition, even though
it's no longer direct.

Change-Id: I0dac83295891630686c3a8038eb54138cf40ab44
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29411
Maintainer: Gabe Black <gabeblack@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>

misc: Make many includes explicit.

A future change will adjust how some includes can be included
transitively. This change fixes up those files so that they include the
headers they need directly, instead of expecting to have them by
accident through other files.

Change-Id: I1f79aa11df2b46bb7018f39c964294c41db4fdac
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29407
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>