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

22
test/ck_tile/memory_copy/test_copy.cpp
View File

@@ -76,17 +76,17 @@ class TestCkTileMemoryCopy : public ::testing::TestWithParam<std::tuple<int, int
constexpr ck_tile::index_t kBlockSize = 128;
constexpr ck_tile::index_t kBlockPerCu = 1;
auto ms = launch_kernel(ck_tile::stream_config{nullptr, true},
ck_tile::make_kernel<kBlockSize, kBlockPerCu>(
Kernel{},
kGridSize,
kBlockSize,
0,
static_cast<XDataType*>(x_buf.GetDeviceBuffer()),
static_cast<YDataType*>(y_buf.GetDeviceBuffer()),
m,
n,
warp_id));
auto ms = launch_kernel(
ck_tile::stream_config{nullptr, true},
ck_tile::make_kernel<kBlockPerCu>(Kernel{},
kGridSize,
kBlockSize,
0,
static_cast<XDataType*>(x_buf.GetDeviceBuffer()),
static_cast<YDataType*>(y_buf.GetDeviceBuffer()),
m,
n,
warp_id));
auto bytes = 2 * m * n * sizeof(DataType);
std::cout << "elapsed: " << ms << " (ms)" << std::endl;

3
test/ck_tile/memory_copy/test_copy.hpp
View File

@@ -64,7 +64,8 @@ struct TileCopy
using Problem = ck_tile::remove_cvref_t<Problem_>;
using XDataType = typename Problem::XDataType;
static constexpr bool AsyncCopy = Problem::AsyncCopy;
static constexpr index_t kBlockSize = Problem::BlockShape::BlockSize;
static constexpr bool AsyncCopy = Problem::AsyncCopy;
template <typename Problem>
CK_TILE_DEVICE static constexpr auto MakeDRAMDistribution()