ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-18 03:49:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '8b56ffb6aea4dd5e3c531912ee6b2258398606ee' into develop

Browse Source
This commit is contained in:
assistant-librarian[bot]
2026-02-03 03:12:05 +00:00
parent 9c38bf0527
commit f27120c60e
2 changed files with 7 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
Jenkinsfile vendored
View File

@@ -581,7 +581,7 @@ def cmake_build(Map conf=[:]){
if (params.NINJA_BUILD_TRACE) {
echo "running ninja build trace"
}
if ((params.RUN_BUILDER_TESTS || params.RUN_FULL_CONV_TILE_TESTS) && !setup_args.contains("-DCK_CXX_STANDARD=") && !setup_args.contains("gfx10") && !setup_args.contains("gfx11")) {
if (params.RUN_BUILDER_TESTS && !setup_args.contains("-DCK_CXX_STANDARD=") && !setup_args.contains("gfx10") && !setup_args.contains("gfx11")) {
setup_args = " -D CK_EXPERIMENTAL_BUILDER=ON " + setup_args
}
setup_cmd = conf.get(
@@ -1428,8 +1428,8 @@ pipeline {
agent{ label rocmnode("gfx90a")}
environment{
setup_args = "NO_CK_BUILD"
execute_args = """ python3 ../experimental/builder/src/generate_instances.py --mode=profiler && \
../script/cmake-ck-dev.sh ../ gfx90a && \
execute_args = """ python3 ../experimental/grouped_convolution_tile_instances/generate_instances.py --mode=profiler && \
cmake .. --preset dev-gfx90a -D CK_EXPERIMENTAL_BUILDER=ON && \
make -j64 test_grouped_convnd_fwd_tile && \
./bin/test_grouped_convnd_fwd_tile"""
}

5
include/ck/tensor_operation/gpu/block/blockwise_gemm_dpp.hpp
View File

@@ -63,7 +63,10 @@ struct BlockwiseGemmDpp_ak0mak1_bk0nbk1_m0n0m1n1m2n2
true>
c_thread_buf_;
__host__ __device__ constexpr auto& GetCThreadBuffer() { return c_thread_buf_; }
__host__ __device__ constexpr auto& GetCThreadBuffer() [[clang::lifetimebound]]
{
return c_thread_buf_;
}
__device__ static auto GetWaveIdx()
{