ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-04 13:41:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

Support Wave32 in CK_TILE - Part 1 (#2594)

Browse Source 
* Support wave32/wave64 in CK_TILE - Part 1

* remove blocksize in kernel launch

* fix build error

* fix clang format

* fix clang format 2

* fix clang format 3

* fix fmha build error

* fix fmha build 2

* fix fmha build 3

* fix build error 4

* address review comment

* update change log

* replace KernelBlockSize with kBlockSize

* fix CI fail

* fix clang format

* address review comment and rebase code.

* fix universal test fail

---------

Co-authored-by: Lin, Qun <Quentin.Lin+amdeng@amd.com>
Co-authored-by: Thomas Ning <Thomas.Ning@amd.com>
This commit is contained in:
linqunAMD
2025-08-19 01:08:31 +08:00
committed by GitHub
parent 26d3300930
commit 9fcc1ee9fd
113 changed files with 610 additions and 531 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
test/ck_tile/gemm/test_gemm_pipeline_util.hpp
View File

@@ -10,6 +10,7 @@
#include "ck_tile/host/kernel_launch.hpp"
#include "ck_tile/ops/epilogue.hpp"
#include "ck_tile/ops/gemm.hpp"
#include "ck_tile/core/numeric/math.hpp"
template <typename ADataType, typename BDataType, typename AccDataType, typename CDataType>
auto calculate_rtol_atol(const ck_tile::index_t K,
@@ -184,7 +185,6 @@ class TestCkTileGemmPipeline : public ::testing::Test
DsLayout,
CLayout,
ck_tile::element_wise::PassThrough,
GemmPipeline::BlockSize,
TilePartitioner::MPerBlock,
TilePartitioner::NPerBlock,
M_Warp,
@@ -207,7 +207,7 @@ class TestCkTileGemmPipeline : public ::testing::Test
{
grids = Kernel::GridSize(args.M, args.N, args.k_batch);
}
constexpr dim3 blocks = Kernel::BlockSize();
dim3 blocks = Kernel::BlockSize();
if(!Kernel::IsSupportedArgument(kargs))
{
@@ -222,7 +222,7 @@ class TestCkTileGemmPipeline : public ::testing::Test
}
ck_tile::launch_kernel(
s, ck_tile::make_kernel<blocks.x, kBlockPerCu>(Kernel{}, grids, blocks, 0, kargs));
s, ck_tile::make_kernel<kBlockPerCu>(Kernel{}, grids, blocks, 0, kargs));
};
const auto RunSplitk = [&](const auto has_hot_loop_, const auto tail_number_) {