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

[CK_TILE]fix elementwise example in gfx11/12 (#2676)

Browse Source 
* fix elementwise examples

* improve the robust

* fix ck_tile's elementwise test

* update elementwise test
This commit is contained in:
joyeamd
2025-08-14 06:21:46 +08:00
committed by GitHub
parent a6f4029276
commit bcc38deff7
6 changed files with 12 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
include/ck_tile/ops/elementwise/pipeline/elementwise_shape.hpp
View File

@@ -14,13 +14,14 @@ struct ElementWiseShape
static constexpr index_t kWarpM = WarpTile::at(number<0>{});
static constexpr index_t kVectorM = 16 / sizeof(ComputeDataType);
static constexpr index_t kVectorM =
min(static_cast<index_t>(16 / sizeof(ComputeDataType)), kWarpM / get_warp_size());
static constexpr index_t kWarpPerBlockM = BlockWarps::at(number<0>{});
static constexpr index_t kThreadPerWarpM = kWarpM / kVectorM;
static constexpr index_t kThreadPerWarpM = get_warp_size();
static constexpr index_t kRepeatM = kBlockM / (kWarpPerBlockM * kWarpM);
static constexpr index_t kRepeatM = kBlockM / (kWarpPerBlockM * kVectorM * kThreadPerWarpM);
static constexpr index_t kBlockSize =
ck_tile::get_warp_size() * reduce_on_sequence(BlockWarps{}, multiplies{}, number<1>{});