ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-03 05:01:25 +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

3
example/ck_tile/21_elementwise/elementwise_example.cpp
View File

@@ -137,8 +137,7 @@ bool run(const ck_tile::ArgParser& arg_parser)
// This is often a multiple of the wavefront size, 64 on CDNA.
// Here, it's explicitly set to 512. This should be consistent with Shape::kBlockSize.
// Shape::kBlockSize would be BlockWarps * warpSize (e.g., 8 * 64 = 512).
constexpr ck_tile::index_t kBlockSize =
ck_tile::get_warp_size() * BlockWarps::at(ck_tile::number<0>{});
const ck_tile::index_t kBlockSize = Kernel::BlockSize();
// kBlockPerCu: Hint for how many workgroups can be scheduled per Compute Unit (CU).
// This can influence occupancy and performance.

3
example/ck_tile/21_elementwise/elementwise_example_add_4d.cpp
View File

@@ -84,8 +84,7 @@ bool run(const ck_tile::ArgParser& arg_parser)
for(auto d : problem_shape)
total_elements *= d;
constexpr ck_tile::index_t kBlockSize =
ck_tile::get_warp_size() * BlockWarps::at(ck_tile::number<0>{});
const ck_tile::index_t kBlockSize = Kernel::BlockSize();
constexpr ck_tile::index_t kBlockPerCu = 2;

3
example/ck_tile/21_elementwise/elementwise_example_transpose.cpp
View File

@@ -89,8 +89,7 @@ bool run(const ck_tile::ArgParser& arg_parser)
ck_tile::index_t total_elements = M * N;
constexpr ck_tile::index_t kBlockSize =
ck_tile::get_warp_size() * BlockWarps::at(ck_tile::number<0>{});
const ck_tile::index_t kBlockSize = Kernel::BlockSize();
constexpr ck_tile::index_t kBlockPerCu = 1;
constexpr ck_tile::index_t elements_per_block = BlockTile::at(ck_tile::number<0>{});
ck_tile::index_t kGridSize = (total_elements + elements_per_block - 1) / elements_per_block;

3
example/ck_tile/21_elementwise/elementwise_example_unary.cpp
View File

@@ -78,8 +78,7 @@ bool run(const ck_tile::ArgParser& arg_parser)
for(auto d : shape)
total_elements *= d;
constexpr ck_tile::index_t kBlockSize =
ck_tile::get_warp_size() * BlockWarps::at(ck_tile::number<0>{});
const ck_tile::index_t kBlockSize = Kernel::BlockSize();
constexpr ck_tile::index_t kBlockPerCu = 1;
constexpr ck_tile::index_t elements_per_block = BlockTile::at(ck_tile::number<0>{});