ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-14 02:02:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '7f912909ca2c3cedfa1c6397d75daba4903a6d0d' into develop

Browse Source
This commit is contained in:
assistant-librarian[bot]
2026-01-14 21:07:55 +00:00
parent 0211adaff3
commit 5386db55e1
5 changed files with 22 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
.github/CODEOWNERS vendored
View File

@@ -1,8 +1,8 @@
* @illsilin @carlushuang @qianfengz @aosewski @poyenc @geyyer @bartekxk @andriy-ca @afagaj @asleepzzz @tenpercent @ThomasNing @coderfeli @aska-0096 @cgmillette @shumway @vidyasagar-amd
* @illsilin @carlushuang @qianfengz @aosewski @poyenc @geyyer @bartekxk @andriy-ca @afagaj @asleepzzz @tenpercent @ThomasNing @coderfeli @cgmillette @shumway @vidyasagar-amd @vpietila-amd @Snektron
# Documentation files
docs/ @ROCm/rocm-documentation @illsilin @carlushuang @qianfengz @aosewski @poyenc @geyyer @bartekxk @andriy-ca @afagaj @asleepzzz @ThomasNing @coderfeli @aska-0096 @cgmillette @shumway @vidyasagar-amd @ddembeckAMD
*.md @ROCm/rocm-documentation @illsilin @carlushuang @qianfengz @aosewski @poyenc @geyyer @bartekxk @andriy-ca @afagaj @asleepzzz @ThomasNing @coderfeli @aska-0096 @cgmillette @shumway @vidyasagar-amd @ddembeckAMD
*.rst @ROCm/rocm-documentation @illsilin @carlushuang @qianfengz @aosewski @poyenc @geyyer @bartekxk @andriy-ca @afagaj @asleepzzz @ThomasNing @coderfeli @aska-0096 @cgmillette @shumway @vidyasagar-amd @ddembeckAMD
.readthedocs.yaml @ROCm/rocm-documentation @illsilin @carlushuang @qianfengz @aosewski @poyenc @geyyer @bartekxk @andriy-ca @afagaj @asleepzzz @ThomasNing @coderfeli @aska-0096 @cgmillette @shumway @vidyasagar-amd @ddembeckAMD
docs/ @ROCm/rocm-documentation @illsilin @carlushuang @qianfengz @aosewski @poyenc @geyyer @bartekxk @andriy-ca @afagaj @asleepzzz @ThomasNing @coderfeli @cgmillette @shumway @vidyasagar-amd @ddembeckAMD @vpietila-amd @Snektron
*.md @ROCm/rocm-documentation @illsilin @carlushuang @qianfengz @aosewski @poyenc @geyyer @bartekxk @andriy-ca @afagaj @asleepzzz @ThomasNing @coderfeli @cgmillette @shumway @vidyasagar-amd @ddembeckAMD @vpietila-amd @Snektron
*.rst @ROCm/rocm-documentation @illsilin @carlushuang @qianfengz @aosewski @poyenc @geyyer @bartekxk @andriy-ca @afagaj @asleepzzz @ThomasNing @coderfeli @cgmillette @shumway @vidyasagar-amd @ddembeckAMD @vpietila-amd @Snektron
.readthedocs.yaml @ROCm/rocm-documentation @illsilin @carlushuang @qianfengz @aosewski @poyenc @geyyer @bartekxk @andriy-ca @afagaj @asleepzzz @ThomasNing @coderfeli @cgmillette @shumway @vidyasagar-amd @ddembeckAMD @vpietila-amd @Snektron
# Header directory for Doxygen documentation
library/include/ @ROCm/rocm-documentation @illsilin @carlushuang @qianfengz @aosewski @poyenc @geyyer @bartekxk @andriy-ca @afagaj @asleepzzz @ThomasNing @coderfeli @aska-0096 @cgmillette @shumway @vidyasagar-amd
library/include/ @ROCm/rocm-documentation @illsilin @carlushuang @qianfengz @aosewski @poyenc @geyyer @bartekxk @andriy-ca @afagaj @asleepzzz @ThomasNing @coderfeli @cgmillette @shumway @vidyasagar-amd @vpietila-amd @Snektron

4
include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_wmma_cshuffle_v3.hpp
View File

@@ -314,6 +314,10 @@ struct DeviceBatchedGemmMultiD_Wmma_CShuffleV3
{
ActiveWorkgroupsPerCU()
{
if(!ck::is_gfx11_supported() && !ck::is_gfx12_supported())
{
return;
}
constexpr int dynamic_smem_size = 0;
int max_occupancy = 0;

4
include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_two_stage_wmma_cshuffle_v3.hpp
View File

@@ -466,6 +466,10 @@ struct DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3
{
ActiveWorkgroupsPerCU()
{
if(!ck::is_gfx11_supported() && !ck::is_gfx12_supported())
{
return;
}
constexpr int dynamic_smem_size = 0;
constexpr index_t minimum_occupancy =
BlkGemmPipeSched == BlockGemmPipelineScheduler::Intrawave ? 1 : 2;

4
include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_wmma_cshuffle_v3.hpp
View File

@@ -415,6 +415,10 @@ struct DeviceGroupedConvBwdWeight_Wmma_CShuffleV3
{
ActiveWorkgroupsPerCU()
{
if(!ck::is_gfx11_supported() && !ck::is_gfx12_supported())
{
return;
}
constexpr int dynamic_smem_size = 0;
constexpr index_t minimum_occupancy =
BlkGemmPipeSched == BlockGemmPipelineScheduler::Intrawave ? 1 : 2;

7
test/ck_tile/gemm_streamk/CMakeLists.txt
View File

@@ -23,9 +23,10 @@ if(GPU_TARGETS MATCHES "gfx90a|gfx942|gfx950")
#TODO: support all arches
#TODO: current c-shuffle only supports C layout as R
add_gtest_executable(test_ck_tile_streamk_tile_partitioner test_streamk_tile_partitioner.cpp)
add_gtest_executable(test_ck_tile_streamk_reduction
${CMAKE_CURRENT_SOURCE_DIR}/smoke_tests/test_gemm_streamk_fp16_reduction.cpp
test_gemm_streamk_util.cpp)
# TODO: Renable once transient bug for reduction is resolved.
# add_gtest_executable(test_ck_tile_streamk_reduction
# ${CMAKE_CURRENT_SOURCE_DIR}/smoke_tests/test_gemm_streamk_fp16_reduction.cpp
# test_gemm_streamk_util.cpp)
add_gtest_executable(test_ck_tile_streamk_smoke
${CMAKE_CURRENT_SOURCE_DIR}/smoke_tests/test_gemm_streamk_fp16_persistent.cpp
${CMAKE_CURRENT_SOURCE_DIR}/smoke_tests/test_gemm_streamk_bf16_persistent.cpp