ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-14 10:09:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

Support for swizzle and transpose for MFMA_16x16x32_F16/BF16 (#2172)

Browse Source 
* Changes for updating tile distribution for shuffle and transpose

* Fixed swizzle and transpose, removed comments

* clang formatted

* Adding support for bf16 type

* Addressing review comments

[ROCm/composable_kernel commit: d8faf1c6a1]
This commit is contained in:
Khushbu Agarwal
2025-05-10 22:40:05 -07:00
committed by GitHub
parent 689e959a0f
commit 8108567dc1
1 changed files with 12 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
include/ck_tile/ops/gemm/warp/warp_gemm.hpp
View File

@@ -77,6 +77,18 @@ using WarpGemmMfmaF16F16F32M16N16K32TransposedCDistribution =
2>>;
#endif
#if defined(__gfx950__)
using WarpGemmMfmaF16F16F32M16N16K32SwizzleBTransposedCDistribution =
WarpGemmImpl<WarpGemmAtrributeMfmaTransposedCDistribution_SwizzleB<
WarpGemmAttributeMfmaImplF16F16F32M16N16K32<WGAttrCtlEnum::Default_>,
1>>;
using WarpGemmMfmaBf16Bf16F32M16N16K32SwizzleBTransposedCDistribution =
WarpGemmImpl<WarpGemmAtrributeMfmaTransposedCDistribution_SwizzleB<
WarpGemmAttributeMfmaImplBf16Bf16F32M16N16K32<WGAttrCtlEnum::Default_>,
1>>;
#endif
#if defined(__gfx950__)
using WarpGemmMfmaF16F16F32M32N32K16SwizzleBTransposedCDistribution =
WarpGemmImpl<WarpGemmAtrributeMfmaTransposedCDistribution_SwizzleB<