ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-15 10:37:44 +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>

[ROCm/composable_kernel commit: 9fcc1ee9fd]
This commit is contained in:
linqunAMD
2025-08-19 01:08:31 +08:00
committed by GitHub
parent 13bfcba04c
commit 615ca9842d
113 changed files with 610 additions and 531 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
example/ck_tile/18_flatmm/flatmm_basic.cpp
View File

@@ -101,7 +101,6 @@ float flatmm_calc(const ck_tile::FlatmmHostArgs<>& args, const ck_tile::stream_c
DsLayout,
ELayout,
CDEElementWise,
CodegenPipelineProblem::kBlockSize,
TilePartitioner::MPerBlock,
TilePartitioner::NPerBlock,
FlatmmConfig::M_Warp,
@@ -119,8 +118,8 @@ float flatmm_calc(const ck_tile::FlatmmHostArgs<>& args, const ck_tile::stream_c
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))
{
@@ -171,15 +170,13 @@ float flatmm_calc(const ck_tile::FlatmmHostArgs<>& args, const ck_tile::stream_c
ave_time = ck_tile::launch_kernel_time_mask(
s,
run_flush_cache,
ck_tile::make_kernel<blocks.x, FlatmmConfig::kBlockPerCu>(
Kernel{}, grids, blocks, 0, kargs));
ck_tile::make_kernel<FlatmmConfig::kBlockPerCu>(Kernel{}, grids, blocks, 0, kargs));
}
else
{
ave_time =
ck_tile::launch_kernel(s,
ck_tile::make_kernel<blocks.x, FlatmmConfig::kBlockPerCu>(
Kernel{}, grids, blocks, 0, kargs));
ave_time = ck_tile::launch_kernel(
s,
ck_tile::make_kernel<FlatmmConfig::kBlockPerCu>(Kernel{}, grids, blocks, 0, kargs));
}
return ave_time;
};