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

5
example/ck_tile/06_permute/alternative_impl/matrix_core_swizzle_kernel.hpp
View File

@@ -1,5 +1,5 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
#pragma once
@@ -115,11 +115,12 @@ struct matrix_core_swizzle_kernel
__host__ void operator()(const ck_tile::stream_config& s) const
{
ck_tile::kentry<BLOCK_SIZE, 1, kernel><<<grids, BLOCK_SIZE, 0, s.stream_id_>>>(a);
ck_tile::kentry<1, kernel><<<grids, BLOCK_SIZE, 0, s.stream_id_>>>(a);
}
struct kernel
{
static constexpr int kBlockSize = BLOCK_SIZE;
__device__ static constexpr auto get_src_dist()
{
using namespace ck_tile;

24
example/ck_tile/06_permute/permute.cpp
View File

@@ -53,11 +53,11 @@ float permute(permute_traits t, permute_args a, const ck_tile::stream_config& s)
auto kargs = Kernel::MakeKargs(a);
const dim3 grids = Kernel::GridSize(a);
constexpr dim3 blocks = Kernel::BlockSize();
const dim3 grids = Kernel::GridSize(a);
const dim3 blocks = Kernel::BlockSize();
float ave_time = ck_tile::launch_kernel(
s, ck_tile::make_kernel<blocks.x, 1>(Kernel{}, grids, blocks, 0, kargs));
float ave_time =
ck_tile::launch_kernel(s, ck_tile::make_kernel<1>(Kernel{}, grids, blocks, 0, kargs));
return ave_time;
}
@@ -69,11 +69,11 @@ float permute(permute_traits t, permute_args a, const ck_tile::stream_config& s)
auto kargs = Kernel::MakeKargs(a);
const dim3 grids = Kernel::GridSize(a);
constexpr dim3 blocks = Kernel::BlockSize();
const dim3 grids = Kernel::GridSize(a);
const dim3 blocks = Kernel::BlockSize();
float ave_time = ck_tile::launch_kernel(
s, ck_tile::make_kernel<blocks.x, 1>(Kernel{}, grids, blocks, 0, kargs));
float ave_time =
ck_tile::launch_kernel(s, ck_tile::make_kernel<1>(Kernel{}, grids, blocks, 0, kargs));
return ave_time;
}
@@ -85,11 +85,11 @@ float permute(permute_traits t, permute_args a, const ck_tile::stream_config& s)
auto kargs = Kernel::MakeKargs(a);
const dim3 grids = Kernel::GridSize(a);
constexpr dim3 blocks = Kernel::BlockSize();
const dim3 grids = Kernel::GridSize(a);
const dim3 blocks = Kernel::BlockSize();
float ave_time = ck_tile::launch_kernel(
s, ck_tile::make_kernel<blocks.x, 1>(Kernel{}, grids, blocks, 0, kargs));
float ave_time =
ck_tile::launch_kernel(s, ck_tile::make_kernel<1>(Kernel{}, grids, blocks, 0, kargs));
return ave_time;
}