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]
- add user obj APIs for creating release and retain of user onbjects
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: I0bf2999c77e44269565b27c31c7c1461f8a160a2
[ROCm/clr commit: 2c010dec17]
The cmake file command with REAL_PATH option is supported from cmake version 3.19 onwards
Issue reported in cmake version 3.17. get_filename_component is supported since 3.4 onwards
The command gives REALPATH with symlinks resolved - /opt/rocm-ver/lib/cmake/hip/hip-config.cmake
So need to move four level up to get ROCM PATH
Verfied by printing the variables
Change made so that default initializaton of ROCM PATH is executed if there is no ROCM_PATH set in ENV
Change-Id: Ibfff584eeb154bd73a568a842f28143d5ed72458
[ROCm/clr commit: d60787bdb2]
- if flags are not supported
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: Id7570d2c5f3d1169da33561f05c278dcd1834db6
[ROCm/clr commit: 58c5e17c5f]
- hiprtcCompileProgram should create isa with temp name when
program name is not provided along with --save-temps option
Change-Id: I47974e2ac56336c851531622ff7d2a3ffb53455e
[ROCm/clr commit: 958b97b433]
- Don't pass uint32_t arguments by reference.
- Use nullptr instead of NULL.
- Don't add frivolous typedefs.
- Use correct types when available instead of generic integral types.
- Make all roctracer callbacks extern "C" to prepare for a future change
that will be removing their declaration from hip_runtime_api.h.
- Rename cb/sem sync and release functions -> reader_lock/writer_lock
acquire and release.
Change-Id: If203fee077d421a9782fcd34607a413b8c3dcfc8
[ROCm/clr commit: 9f09ca929e]
When acquiring the reader's lock (sem_sync()...sem_release()), it is
possible for a writer to squeeze by if the reader goes into sync_wait().
The writer could re-acquire the entry.sync between entry.sem > 0 and
entry.sync = 0.
void sync_wait(uint32_t id) {
sem_decrement(id);
while (entry(id).sync.load()) {}
// <--- HERE
sem_increment(id);
}
This could result in both the reader and the writer accessing
{ callback, arg } at the same time, and the reader could read
inconsistent data, for example: { new callback, old arg }.
The solution is to re-test entry.sync when returning from sync_wait():
void sem_sync(uint32_t id) {
sem_increment(id);
- if (entry(id).sync.load() == true) sync_wait(id);
+ while (entry(id).sync.load() == true) sync_wait(id);
}
Change-Id: I22f74f4cb9a5f027aac8aa4ed3e633acc19df4b8
[ROCm/clr commit: 6f78083f2a]
As per the requirements in SWDEV-287540, config files should not have hard coded /opt/rocm path
Instead of setting ROCM_PATH to /opt/rocm, used hip-config file path to find the rocm path
Validated by printing the CONFIG_PATH and is coming as/opt/rocm-ver/lib/cmake/hip/hip-config.cmake
So need four level up,with file name in the path
Change-Id: Iac01d3a0c0168138c777551165705ed56cf6c3b1
[ROCm/clr commit: f61a87ebb2]
This reverts commit d12900e000.
Reason for revert: Moved out to future release
Change-Id: I36b046c8681371baa9e0ccb69d46dad633ee5706
[ROCm/clr commit: d328d72fab]
- test should allow first calling get function
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: I365cd6210a01fd5ae3620711694bdc52e0f90b19
[ROCm/clr commit: 66bde8f336]
- hiprtcAddLinkData should accept 0 or null as input name
- hiprtcLinkCreate should accept 0 or null as options ptr
- hiprtcCompile should send -fgpu-rdc option to comgr if its present in the options
Change-Id: I84f6e36df5c99b719ee9c67dfc1b4dbcfd8e3172
[ROCm/clr commit: ee27685ac4]
- Implement CUDA mappings for stream ordered memory allocator and memory pool APIs
Change-Id: I2434118ff043527ec7c3389cd5175e1e21d032bf
[ROCm/clr commit: 9f4214b587]
kjayapra-amd
pghafari
Laurent Morichetti
Satyanvesh Dittakavi
Sarbojit Sarkar
Jaydeep Patel
sdashmiz
Ajay
Ranjith Ramakrishnan
Tao Sang
Maneesh Gupta
Jason Tang
haoyuan2
Anusha Godavarthy Surya
Rakesh Roy