Vladislav Sytchenko
28b17d3dbd
Revert "Merge branch 'amd-master-next' into amd-npi-next"
...
This reverts commit 258d79bca7374ead1d19
2020-10-05 13:02:39 -04:00
Aryan Salmanpour
40d44e2c8d
[dtest] move all the cooperative related tests into one location
...
Change-Id: I9b44027d795ebfbf42f78af8e69d26ac8109692a
[ROCm/hip commit: e1cb711e66
2020-10-01 16:01:46 -04:00
German Andryeyev
80bd9632ad
Correct mgpu coop launch test
...
When the original size is devided accross all GPUs rounding can
occur, causing incorrect validation. Readjust the final value
for comparison to the new size accordingly.
Change-Id: I9b42149e33dfcb328de7419e546a0202a69a8610
[ROCm/hip commit: 20f0e36041
2020-05-13 14:39:11 -04:00
Maneesh Gupta
8e137a6ec1
Merge in the rocclr based hip runtime ( #2032 )
...
* Merge master-next changes in master (include vdi development in master branch)
[ROCm/hip commit: a0b5dfd625
2020-04-23 09:12:06 -07:00
Rahul Garg
003d776e72
Rename hipDrvOccupancy to hipModuleOccupancy and match CUDA syntax ( #1943 )
...
[ROCm/hip commit: ba8a556ea9
2020-04-07 14:02:52 +05:30
lthakur
e340a8e921
[dtest] Update hipLaunchCoopMultiKernel.cpp ( #1844 )
...
used reinterpret_cast<uint32_t*> for numBlocks, as expected by hipOccupancyMaxActiveBlocksPerMultiprocessor() api.
[ROCm/hip commit: 4d472b777f
2020-02-04 19:37:38 +05:30
gandryey
42bc78d148
[dtest] RCCL multi device launch test ( #1731 )
...
Simple test for hipLaunchCooperativeKernelMultiDevice API.
[ROCm/hip commit: 48d1f766d5
2020-02-04 08:53:43 +05:30
Vladislav Sytchenko
Aryan Salmanpour
German Andryeyev
Maneesh Gupta
Rahul Garg
lthakur
gandryey