ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-02 12:41:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

[CK TILE] Refactor GemmKernel to be reused by other GEMM related operators (#1730)

Browse Source 
* Gemm Kernel Refactor part1

* Gemm Kernel Refactor common gemm pipeline part2

* [CK TILE] Refactor batched gemm to reuse GemmKernel

* [CK TILE] Refactor GemmKernel - review changes part1

* [CK TILE] Refactor GemmKernel - references fix

* [CK TILE] Refactor GemmKernel - naming changes, add problem

* [CK_TILE] Refactor GemmKernel - update tests

* [CK_TILE] Refactor GemmKernel - review changes

* [CK_TILE] Refactor GemmKernel - update test

* [CK_TILE] Refactor GemmKernel - constness fixes

* [CK_TILE] Refactor GemmKernel - update tests
This commit is contained in:
aledudek
2024-12-18 17:52:46 +01:00
committed by GitHub
parent 1c1b336371
commit 453ca37347
10 changed files with 297 additions and 368 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
example/ck_tile/03_gemm/gemm_basic.cpp
View File

@@ -15,7 +15,7 @@
#include "gemm_basic.hpp"
template <typename ALayout, typename BLayout, typename CLayout>
float gemm_calc(const gemm_basic_args& args, const ck_tile::stream_config& s)
float gemm_calc(const ck_tile::GemmHostArgs& args, const ck_tile::stream_config& s)
{
// The kPadM, kPadN, kPadK & kBlockPerCu should also come from the Codegen part.
constexpr bool kPadM = false;
@@ -79,17 +79,9 @@ float gemm_calc(const gemm_basic_args& args, const ck_tile::stream_config& s)
// Now we only use the BlockGemmASmemBSmemCRegV1DefaultPolicy.
using Kernel = ck_tile::GemmKernel<TilePartitioner, CodegenGemmPipeline, GemmEpilogue>;
auto kargs = Kernel::MakeKargs(args.p_a,
args.p_b,
args.p_c,
args.M,
args.N,
args.K,
args.stride_A,
args.stride_B,
args.stride_C);
auto kargs = Kernel::MakeKernelArgs(args);
const dim3 grids = Kernel::GridSize(args.M, args.N, args.kbatch);
const dim3 grids = Kernel::GridSize(args.M, args.N, args.k_batch);
constexpr dim3 blocks = Kernel::BlockSize();
if(!Kernel::IsSupportedArgument(kargs))