ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-20 14:59:17 +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

1
tile_engine/ops/gemm_multi_d/gemm_multi_d_codegen_utils.py
View File

@@ -56,7 +56,6 @@ CSHUFFLE_EPILOGUE = """
DsLayout,
ELayout,
CDEElementWise,
GemmPipelineProblem::kBlockSize,
TilePartitioner::MPerBlock,
TilePartitioner::NPerBlock,
WarpM,

6
tile_engine/ops/gemm_multi_d/gemm_multi_d_instance_builder.py
View File

@@ -443,8 +443,8 @@ struct GemmKernelMultiD {{
using Kernel = ck_tile::GemmKernelMultiD<TilePartitioner, GemmPipeline, GemmEpilogue>;
auto kargs = Kernel::MakeKernelArgs(args);
const dim3 grids = Kernel::GridSize(args.M, args.N, args.k_batch);
constexpr dim3 blocks = Kernel::BlockSize();
const dim3 grids = Kernel::GridSize(args.M, args.N, args.k_batch);
const dim3 blocks = Kernel::BlockSize();
if(!Kernel::IsSupportedArgument(kargs))
{{
@@ -460,7 +460,7 @@ struct GemmKernelMultiD {{
}}
ave_time = ck_tile::launch_kernel(stream,
ck_tile::make_kernel<blocks.x, kBlockPerCu>(
ck_tile::make_kernel<kBlockPerCu>(
Kernel{{}}, grids, blocks, 0, kargs));
return ave_time;