HSA signal callback order is undefined. Make sure start event is
also done before calculating the elapsed time.
Change-Id: Ic69bfe336b20cd62ef35194261a5d0d234bc65ce
[ROCm/clr commit: 910d8bdfde]
HSA signal callback order is undefined. Make sure start event is
also done before calculating the elapsed time.
Change-Id: Ic69bfe336b20cd62ef35194261a5d0d234bc65ce
Add libhiprtc-builtins library to packaging/hip-rocclr.
Depends on part 1 patch to compute/ec/hipamd.
Change-Id: I366d7f1868c868f5d6b02363c7e78ff399e06b19
[ROCm/hip commit: fdbb8f10bd]
Add libhiprtc-builtins library to packaging/hip-rocclr.
Depends on part 1 patch to compute/ec/hipamd.
Change-Id: I366d7f1868c868f5d6b02363c7e78ff399e06b19
Add the CMake support for generating the hiprtc-builtins
library. Replaces the previous execution of shell script.
For backwards compatibility, link hiprtc pre-processed
object to amdhip64, and support versioning in name.
Add libcmt.lib to Windows link step, due to manually
generated .obj from llvm-mc.
Change-Id: I267be3cf4b241840b35f7f27a0b8659530108b0e
[ROCm/clr commit: c42308e2e5]
Add the CMake support for generating the hiprtc-builtins
library. Replaces the previous execution of shell script.
For backwards compatibility, link hiprtc pre-processed
object to amdhip64, and support versioning in name.
Add libcmt.lib to Windows link step, due to manually
generated .obj from llvm-mc.
Change-Id: I267be3cf4b241840b35f7f27a0b8659530108b0e
Certain special signals do not carry their updates via their signal
value. These signals are wrappers around special KFD events, of
which the only current instance informs about VM faults. We either
need to check each signal for this special event type or rely on
the checking done in hsa_amd_signal_wait_any. Since there will always
be a small number of these signals it doesn't make much since to
penalize the performance path with this check. Additionally we know
that the signal indicated by hsa_amd_signal_wait_any is satisfied so
don't need to recheck it's conditions.
Change-Id: I9fc6298300ad543d823ecd28ca8fab4ad26c23ef
Certain special signals do not carry their updates via their signal
value. These signals are wrappers around special KFD events, of
which the only current instance informs about VM faults. We either
need to check each signal for this special event type or rely on
the checking done in hsa_amd_signal_wait_any. Since there will always
be a small number of these signals it doesn't make much since to
penalize the performance path with this check. Additionally we know
that the signal indicated by hsa_amd_signal_wait_any is satisfied so
don't need to recheck it's conditions.
Change-Id: I9fc6298300ad543d823ecd28ca8fab4ad26c23ef
[ROCm/ROCR-Runtime commit: 3d6a18b67c]
Clang now warns about set but unused variables. It also now
recognizes -Wno-error=unused-but-set-variable so this patch moves
that option back to the general options list.
Change-Id: Id800e87eb688b9441b14380e2246ad586179f31a
Clang now warns about set but unused variables. It also now
recognizes -Wno-error=unused-but-set-variable so this patch moves
that option back to the general options list.
Change-Id: Id800e87eb688b9441b14380e2246ad586179f31a
[ROCm/ROCR-Runtime commit: 26808295f8]
If the user decides to use a non-hipcc or non-clang++
compiler, we should skip the version checking.
Change-Id: I1424585c606ec0c63103f512161eb88cac27d71d
[ROCm/hip commit: 7a43de757e]
If the user decides to use a non-hipcc or non-clang++
compiler, we should skip the version checking.
Change-Id: I1424585c606ec0c63103f512161eb88cac27d71d
Add the hipcc.bat and hipconfig.bat files previously
only residing in P4 to CMake builds. Ship this .bat
file as part of bin directory on Windows.
Change-Id: I2822e1419f1f6a0a6cdde9e292231995a83df77d
[ROCm/hip commit: a6d568b9ca]
Add the hipcc.bat and hipconfig.bat files previously
only residing in P4 to CMake builds. Ship this .bat
file as part of bin directory on Windows.
Change-Id: I2822e1419f1f6a0a6cdde9e292231995a83df77d
The rdcd uses another thread to listen the GPU events. That thread
runs in a tight loop which consume 100% CPU.
The fix will add a sleep to yield CPU.
Bug: SWDEV-291576
Change-Id: I7996720aab4a80346d79b1c73ee532d2abcd93cc
The rdcd uses another thread to listen the GPU events. That thread
runs in a tight loop which consume 100% CPU.
The fix will add a sleep to yield CPU.
Bug: SWDEV-291576
Change-Id: I7996720aab4a80346d79b1c73ee532d2abcd93cc
[ROCm/rdc commit: 5a4bf97327]
In file included from /extra/lmoriche/hip-vdi/hip/rocclr/hip_internal.hpp:25,
from /extra/lmoriche/hip-vdi/hip/rocclr/hip_hmm.cpp:22:
/extra/lmoriche/hip-vdi/hip/rocclr/hip_prof_api.h: In constructor ‘api_callbacks_table_t::api_callbacks_table_t()’:
/extra/lmoriche/hip-vdi/hip/rocclr/hip_prof_api.h:72:59: warning: ‘void* memset(void*, int, size_t)’ clearing an object of type ‘struct api_callbacks_table_t::hip_cb_table_t’ with no trivial copy-assignment; use value-initialization instead [-Wclass-memaccess]
72 | memset(&callbacks_table_, 0, sizeof(callbacks_table_));
| ^
/extra/lmoriche/hip-vdi/hip/rocclr/hip_prof_api.h:67:10: note: ‘struct api_callbacks_table_t::hip_cb_table_t’ declared here
67 | struct hip_cb_table_t {
| ^~~~~~~~~~~~~~
Address the above warning by providing default initialization of the
api_callbacks_table_t::hip_cb_table_t class members.
Change-Id: I69ea7c390c28cf3f8aec57f23566d6a3061a0365
[ROCm/clr commit: 0f7a47a95f]
In file included from /extra/lmoriche/hip-vdi/hip/rocclr/hip_internal.hpp:25,
from /extra/lmoriche/hip-vdi/hip/rocclr/hip_hmm.cpp:22:
/extra/lmoriche/hip-vdi/hip/rocclr/hip_prof_api.h: In constructor ‘api_callbacks_table_t::api_callbacks_table_t()’:
/extra/lmoriche/hip-vdi/hip/rocclr/hip_prof_api.h:72:59: warning: ‘void* memset(void*, int, size_t)’ clearing an object of type ‘struct api_callbacks_table_t::hip_cb_table_t’ with no trivial copy-assignment; use value-initialization instead [-Wclass-memaccess]
72 | memset(&callbacks_table_, 0, sizeof(callbacks_table_));
| ^
/extra/lmoriche/hip-vdi/hip/rocclr/hip_prof_api.h:67:10: note: ‘struct api_callbacks_table_t::hip_cb_table_t’ declared here
67 | struct hip_cb_table_t {
| ^~~~~~~~~~~~~~
Address the above warning by providing default initialization of the
api_callbacks_table_t::hip_cb_table_t class members.
Change-Id: I69ea7c390c28cf3f8aec57f23566d6a3061a0365
There is no OUTPUT_FILE option for add_custom_command (it is an option
for execute_process). Instead, redirect stdout to the output file.
Change-Id: Ic649bc6c4f709c3c42166500a72fce5014690a47
[ROCm/clr commit: f3a54f0823]
There is no OUTPUT_FILE option for add_custom_command (it is an option
for execute_process). Instead, redirect stdout to the output file.
Change-Id: Ic649bc6c4f709c3c42166500a72fce5014690a47
Fix compiling error of hipLaunchCoopMultiKernel on
NV A100.
Fix test failure on all NV devices.
Change-Id: Iba20caa0e9021480378625506197384c275a3289
[ROCm/hip commit: f70b109cc3]
Anusha GodavarthySurya
German Andryeyev
Aaron En Ye Shi
Jatin Chaudhary
Sean Keely
Julia Jiang
Vladislav Sytchenko
Maneesh Gupta
Sarbojit Sarkar
Bill(Shuzhou) Liu
Christophe Paquot
Tao Sang