Fix the following failed tests on NV,
hipCGMultiGridGroupType
hipCGMultiGridGroupTypeViaBaseType
hipCGMultiGridGroupTypeViaPublicApi
1. Fix wrong logic in kernel for both AMD and NV.
2. Remove unnecessary hipDeviceSynchronize().
3. In hipCGMultiGridGroupTypeViaBaseType.cpp, change
multi_grid_group as thread_group which is originally expected.
4. hipFree(syncResultD) is fixed as hipHostFree(syncResultD)
5. Optimize some host codes.
Change-Id: I3fe6dac35a7b14bab12adf397b7885df83d28059
[ROCm/hip commit: c57e0f8fe5]
Enable cooperativeGrps/cooperative_streams on NV.
Add test cases of the least/half/full capacity.
Verify data in terms of AMD/NV devices.
Optimize codes
Change-Id: I3fe6dbc35b7b24abb11adf297b7885df83d28154
[ROCm/hip commit: 67b3681d26]
Add the new extension to HIP for quering coherency mode.
The new enum hipMemRangeAttributeCoherencyMode can be used in
hipMemRangeGetAttribute(s), which will return one of the following
values:
hipMemRangeCoherencyModeFineGrain, hipMemRangeCoherencyModeCoarseGrain,
hipMemRangeCoherencyModeIndeterminate
Change-Id: I8717873c254888ea69facc1178d3682e8747c3a7
[ROCm/hip commit: 1f53fbea8f]
Migrated malloc related files under memory folder into catch2 framework
Change-Id: I5aa07fc8148bdf6bef135947091aaf1d3c54663b
[ROCm/hip commit: 05e230f5c1]
Add test cases for filter modes: hipFilterModePoint and hipFilterModeLinear
Change-Id: I3fe6dbc35a7b14aab12adf297b7885df83d28056
[ROCm/hip commit: 48d8040b06]
Change return type from int to unsigned int.
It is correctly documented in hip-math-api.md but not at the place where this PR is updating the documentation.
[ROCm/hip commit: 7eaa45d2d5]
Migrated all hipMemcpy related APIs to CATCH2 framework by optmizing
the code and moving the stress related tests to stress folder.
Change-Id: Id47669b49304c35d1a68fabdaaf3f6e3ab0428a5
[ROCm/hip commit: 346a77b4c0]
1. In kernel/hipDynamicShared
Fix shared memory size and type mismatch in host and kernel.
2. In kernel/hipDynamicShared2
Cuda kernels relying on shared memory allocations over 48 KB require
to explicitly set size using hipFuncSetAttribute().
Change-Id: I4248b6cebd3dc156f9d5d427e1897da22fb964ed
[ROCm/hip commit: 5b739b0373]
make hipIpcOpenEventHandle has the same behavour of cudaIpcOpenEventHandle.
Add Api usages.
Change-Id: I4248b2cebd3de156f9d5d427e1797da22fb964eb
[ROCm/hip commit: c053d60282]
1.Fix hipModuleNegative failure on all NV GPUs
a.Add signal handler for signal sent by cuda functions.
b.Make hipModuleGetGlobal match cuModuleGetGlobal behavour.
That is, if one of the first two parameters is nullptr, ignore it.
2.Fix hipModuleLoadDataMultThreaded failure on NV RTX5000
Improve lamda function.
Change-Id: I3fe6dbc35a7a14aa9119df197b7885df83d28047
[ROCm/hip commit: ae30c5cd6b]
Currently hip_prof_str.h does not include any header files. All HIP
declarations are being resolved by accident.
Pushing it to the end of hip_runtime_api.h will allow it to include the
definition of GLuint.
Change-Id: Ibb33b93cc7eab2028ba96f166bcb06f2f079feef
[ROCm/hip commit: d3b06fd5a6]
Enable NV printf DTests as many as possible.
Fix the bugs due to behavour difference between
Hip-Rocclr and Cuda.
Add hipLimitPrintfFifoSize.
Change-Id: I3fe6dbc35a7a140a9919df197b7885df83d28049
[ROCm/hip commit: 586165ebc2]
Migrated functional and negative scenarios of
hipMemcpyAtoH and
hipMemcpyHtoA APIs to catch2 framework
Change-Id: I68bb37d99fc371b8803e64ebf1533c0870b14fab
[ROCm/hip commit: bdc90769fb]
Changes contain Device files under "hip/tests/src/runtimeApi/device" migrated to Catch2 and some additional device tests.
Change-Id: Ie88adc3c32c2079456b14e029cfc6c319b48d8f6
[ROCm/hip commit: 44e1ae449a]
Julia Jiang
TomSang
gandryey
dkrottap
Satyanvesh Dittakavi
ansurya
René Widera
gilbertlee-amd
Nagy-Egri Máté Ferenc
Harmen Stoppels
arjun-raj-kuppala
Rahul Garg
DURGESH KROTTAPALLI
Sourabh Betigeri
Satyanvesh Dittakavi
anusha GodavarthySurya
kjayapra-amd
Jatin Chaudhary
jujiang
Sarbojit Sarkar
Vladislav Sytchenko
Christophe Paquot
sumanthtg
Aaron En Ye Shi