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

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

12
include/ck_tile/host/kernel_launch.hpp
View File

@@ -15,9 +15,9 @@
namespace ck_tile {
template <int MaxThreadPerBlock, int MinBlockPerCu, typename Kernel, typename... Args>
template <int MinBlockPerCu, typename Kernel, typename... Args>
#if CK_TILE_USE_LAUNCH_BOUNDS
__launch_bounds__(MaxThreadPerBlock, MinBlockPerCu)
__launch_bounds__(Kernel::kBlockSize, MinBlockPerCu)
#endif
__global__ void kentry(Args... args)
{
@@ -35,15 +35,11 @@ __launch_bounds__(MaxThreadPerBlock, MinBlockPerCu)
//
// the "static __device__ operator()(some_arg)" is the entry point of KernelImpl
//
template <int MaxThreadPerBlock = CK_TILE_MAX_THREAD_PER_BLOCK,
int MinBlockPerCu = CK_TILE_MIN_BLOCK_PER_CU,
typename KernelImpl,
typename... Args>
template <int MinBlockPerCu = CK_TILE_MIN_BLOCK_PER_CU, typename KernelImpl, typename... Args>
CK_TILE_HOST auto
make_kernel(KernelImpl /*f*/, dim3 grid_dim, dim3 block_dim, std::size_t lds_byte, Args... args)
{
const auto kernel = kentry<MaxThreadPerBlock, MinBlockPerCu, KernelImpl, Args...>;
const auto kernel = kentry<MinBlockPerCu, KernelImpl, Args...>;
return [=](const stream_config& s) {
kernel<<<grid_dim, block_dim, lds_byte, s.stream_id_>>>(args...);
};