The fix for SWDEV-329789 moved down the last use of the a
command object pointer in order to prevent a race condition.
However, the previous patch did not move down the release of
that command. By releasing the command early, another thread
could get a command with the same pointer. That second thread
could later submit work to the queue using that new command.
The first thread could then perform a comparison against the
queue's last command using its own now-stale pointer. This
could eventually allow the second thread to skip synchornizing
on the queue. This would result in host synchronizations
completing before their device work was actually complete.
Change-Id: I292b7b369743251ceafe453a4c5cae14a6d01046
[ROCm/clr commit: 6b956f7627]
Using wrapper header file will generate warning message during build time.
Updated the message content to make it more meaningful
Change-Id: I4e0c5e3d845946d9b493d98879ea8e75a92506ee
[ROCm/clr commit: c833a19284]
assert statement were hit silently in Release builds like SWDEV-353548.
Issue only seen in Debug builds
Change-Id: I9f7177806c854d64fcf986e9f6092076d8a05f23
[ROCm/clr commit: 040c416cb1]
HIP_FORCE_QUEUE_PROFILING has been replaced by GPU_FORCE_QUEUE_PROFILING.
Change-Id: Ic32ecdf829a2725ace84e76abab8a81c8790e13f
[ROCm/clr commit: dd49cf0fa0]
- correct condition for flags
- remove check for num of dependency
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: I6efd918e203b57c840d74ee0243f24b0c2c80e21
[ROCm/clr commit: a10df01f81]
HIP_FORCE_QUEUE_PROFILING has been replaced by GPU_FORCE_QUEUE_PROFILING.
Change-Id: Ic8dec4407ef79c27094cb3954e48869075b4732f
[ROCm/clr commit: 97741fe5d4]
If the execution command had a split into multiple HW operations, then runtime has to accumulate time for all operations
Change-Id: Iaba31e96250918d8190bf63adb4c07730fdfefbf
[ROCm/clr commit: 24f5362296]
Hiprtc related libraries are duplicated when installed from build directory
This happens when cmake install libdir is set with lib64 as default and using hard code path "lib" for LIBRARY_DESTINATION
Replaced "lib" with cmake install libdir
Removed the default setting of libdir in source code and its should be controlled via build argument
Change-Id: Icac55eac9427a5088903d01942e6bfd5263a6fc0
[ROCm/clr commit: ba04f95771]
To support both hip and ocl. HIP_FORCE_QUEUE_PROFILING will be replaced with this later on.
Change-Id: I6d3514b1568ff049584ed9fd74bbdb3e4f4bf0c3
[ROCm/clr commit: d92b3a2d90]
Fixed an error in the CMakeLists.txt USE_PERF_API option declaration
that was making it always disabled. Fixing this exposed an issue with
the hip_prof_gen.py script's handling of function variants (for example,
_spt functions) and new HIP_INIT_API_* macros.
Also switched the python interpreter to python3 as python2 may not be
available by default on the build system.
Change-Id: I971fc9edcc746ca63a2bdf4f540e755f9a80fe69
[ROCm/clr commit: 8ac20e5e38]
Replace the custom reader/writer lock with the standard implementation
available in C++17.
Change-Id: I46013b821f13a023a16094830b7f45c4bacf11cb
[ROCm/clr commit: 008aa1c2e1]
- rocr attribute needs to be updated after each iteration
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: I3afb2d7954ef3de37f5f5f9d3cc7757fdacffcec
[ROCm/clr commit: 50e0ddb055]
Sourabh Betigeri
Sarbojit Sarkar
Satyanvesh Dittakavi
Chauncey Hui
Anusha Godavarthy Surya
Yifan Zhang
Joseph Greathouse
Alex Xie
Ranjith Ramakrishnan
pghafari
Ajay
Saleel Kudchadker
Jason Tang
sdashmiz
Jiabao Xie
Alex (Bin) Xie
jie1zhan
Jaydeep Patel
German
kjayapra-amd
Laurent Morichetti