ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-20 06:49:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

[CK_TILE] fix example reduces, permute and elementwise on gfx11 & gfx12 (#2810)

Browse Source 
1. Refine Reduce2dShape to support both wave32 and wave64
2. Fix example reduce, permute and elementwise on gfx11 and gfx12

---------

Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
This commit is contained in:
linqunAMD
2025-09-11 12:41:20 +08:00
committed by GitHub
parent 80a61afb9b
commit 0b9a638f26
11 changed files with 38 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
example/ck_tile/03_gemm/gemm_splitk_two_stage_reduce.cpp
View File

@@ -343,7 +343,6 @@ float reduce_stage2(const GemmSplitKHostArgs& args, const ck_tile::stream_config
using WarpTile = ck_tile::sequence<32, 128>;
using ThreadTile = ck_tile::sequence<8, 8>;
constexpr ck_tile::index_t kBlockSize = 256;
constexpr ck_tile::index_t kBlockPerCu = 1;
ck_tile::index_t kGridSize = (output_size + BlockTile::at(ck_tile::number<0>{}) - 1) /
@@ -352,7 +351,8 @@ float reduce_stage2(const GemmSplitKHostArgs& args, const ck_tile::stream_config
using Shape = ck_tile::Reduce2dShape<BlockWarps, BlockTile, WarpTile, ThreadTile>;
using Problem =
ck_tile::Reduce2dProblem<CDataType, ComputeDataType, CDataType, Shape, ReduceOp>;
using Kernel = ck_tile::Reduce<Problem>;
using Kernel = ck_tile::Reduce<Problem>;
const ck_tile::index_t kBlockSize = Kernel::BlockSize();
if(!Kernel::IsSupportedArgument(reduce_dim_size, workspace_strides))
{
@@ -992,7 +992,11 @@ int main(int argc, char* argv[])
try
{
#if CK_TILE_USE_WMMA
return !run_gemm_example<GemmConfigComputeV3_WMMA>(arg_parser);
#else
return !run_gemm_example<GemmConfigComputeV3>(arg_parser);
#endif
}
catch(const std::runtime_error& e)
{