ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-03 13:11:25 +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

20
include/ck_tile/ops/gemm_group_quant/kernel/gemm_aquant_kernel.hpp
View File

@@ -99,15 +99,15 @@ struct AQuantGemmKernelArgs
template <typename TilePartitioner_, typename GemmPipeline_, typename EpiloguePipeline_>
struct AQuantGemmKernel
{
using TilePartitioner = remove_cvref_t<TilePartitioner_>;
using GemmPipeline = remove_cvref_t<GemmPipeline_>;
using EpiloguePipeline = remove_cvref_t<EpiloguePipeline_>;
using ALayout = remove_cvref_t<typename GemmPipeline::ALayout>;
using AQLayout = remove_cvref_t<typename GemmPipeline::AQLayout>;
using BLayout = remove_cvref_t<typename GemmPipeline::BLayout>;
using CLayout = remove_cvref_t<typename GemmPipeline::CLayout>;
static constexpr index_t KernelBlockSize = GemmPipeline::BlockSize;
static constexpr bool Preshuffle = GemmPipeline::Preshuffle;
using TilePartitioner = remove_cvref_t<TilePartitioner_>;
using GemmPipeline = remove_cvref_t<GemmPipeline_>;
using EpiloguePipeline = remove_cvref_t<EpiloguePipeline_>;
using ALayout = remove_cvref_t<typename GemmPipeline::ALayout>;
using AQLayout = remove_cvref_t<typename GemmPipeline::AQLayout>;
using BLayout = remove_cvref_t<typename GemmPipeline::BLayout>;
using CLayout = remove_cvref_t<typename GemmPipeline::CLayout>;
static constexpr index_t kBlockSize = GemmPipeline::BlockSize;
static constexpr bool Preshuffle = GemmPipeline::Preshuffle;
using ADataType = remove_cvref_t<typename GemmPipeline::ADataType>;
using AQDataType = remove_cvref_t<typename GemmPipeline::AQDataType>;
@@ -131,7 +131,7 @@ struct AQuantGemmKernel
return dim3(TilePartitioner::GridSize(M, N), 1, KBatch);
}
CK_TILE_HOST static constexpr auto BlockSize() { return dim3(KernelBlockSize); }
CK_TILE_HOST static constexpr auto BlockSize() { return dim3(kBlockSize); }
CK_TILE_HOST static constexpr AQuantGemmKernelArgs
MakeKernelArgs(const AQuantGemmHostArgs& hostArgs)