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

[rocm-libraries] ROCm/rocm-libraries#4594 (commit 1fce4cb)

Browse Source 
[CK_TILE] MX GEMM non-preshuffled RCR layout

## Motivation

Implements a GEMM with MX scaling for fp4 and fp8 in non-preshuffled
layouts using async pipeline.

## Technical Details

<!-- Explain the changes along with any relevant GitHub links. -->

## Test Plan

<!-- Explain any relevant testing done to verify this PR. -->

## Test Result

<!-- Briefly summarize test outcomes. -->

## Submission Checklist

- [ ] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
This commit is contained in:
Sami Remes
2026-03-10 20:12:43 +00:00
committed by assistant-librarian[bot]
parent b8def2c724
commit 8f27f65d44
40 changed files with 2729 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
include/ck_tile/ops/gemm_quant/pipeline/gemm_abquant_pipeline_ag_bg_cr_v3.hpp
View File

@@ -127,7 +127,12 @@ struct ABQuantGemmPipelineAgBgCrCompV3 : public BaseGemmPipelineAgBgCrCompV3<Pro
CK_TILE_HOST_DEVICE static constexpr index_t GetSmemSize()
{
return Policy::template GetSmemSize<Problem>();
// We are not storing the original packed type in LDS, so we need to multiply the smem size
// by the packed size.
constexpr index_t smem_size_a = Policy::template GetSmemSizeA<Problem>() * APackedSize;
constexpr index_t smem_size_b = Policy::template GetSmemSizeB<Problem>() * BPackedSize;
return smem_size_a + smem_size_b;
}
CK_TILE_HOST static std::string Print()

7
include/ck_tile/ops/gemm_quant/pipeline/gemm_aquant_pipeline_ag_bg_cr_mem.hpp
View File

@@ -106,7 +106,12 @@ struct AQuantGemmPipelineAgBgCrMem : public BaseGemmPipelineAgBgCrMem<Problem>
CK_TILE_HOST_DEVICE static constexpr index_t GetSmemSize()
{
return Policy::template GetSmemSize<Problem>();
// We are not storing the original packed type in LDS, so we need to multiply the smem size
// by the packed size.
constexpr index_t smem_size_a = Policy::template GetSmemSizeA<Problem>() * APackedSize;
constexpr index_t smem_size_b = Policy::template GetSmemSizeB<Problem>() * BPackedSize;
return smem_size_a + smem_size_b;
}
CK_TILE_HOST static std::string Print()

7
include/ck_tile/ops/gemm_quant/pipeline/gemm_aquant_pipeline_ag_bg_cr_v3.hpp
View File

@@ -102,7 +102,12 @@ struct AQuantGemmPipelineAgBgCrCompV3 : public BaseGemmPipelineAgBgCrCompV3<Prob
CK_TILE_HOST_DEVICE static constexpr index_t GetSmemSize()
{
return Policy::template GetSmemSize<Problem>();
// We are not storing the original packed type in LDS, so we need to multiply the smem size
// by the packed size.
constexpr index_t smem_size_a = Policy::template GetSmemSizeA<Problem>() * APackedSize;
constexpr index_t smem_size_b = Policy::template GetSmemSizeB<Problem>() * BPackedSize;
return smem_size_a + smem_size_b;
}
CK_TILE_HOST static std::string Print()

7
include/ck_tile/ops/gemm_quant/pipeline/gemm_bquant_pipeline_ag_bg_cr_v3.hpp
View File

@@ -115,7 +115,12 @@ struct BQuantGemmPipelineAgBgCrCompV3 : public BaseGemmPipelineAgBgCrCompV3<Prob
CK_TILE_HOST_DEVICE static constexpr index_t GetSmemSize()
{
return Policy::template GetSmemSize<Problem>();
// We are not storing the original packed type in LDS, so we need to multiply the smem size
// by the packed size.
constexpr index_t smem_size_a = Policy::template GetSmemSizeA<Problem>() * APackedSize;
constexpr index_t smem_size_b = Policy::template GetSmemSizeB<Problem>() * BPackedSize;
return smem_size_a + smem_size_b;
}
CK_TILE_HOST static std::string Print()

5
include/ck_tile/ops/gemm_quant/pipeline/gemm_microscale_pipeline_ag_bg_cr_v3.hpp
View File

@@ -112,7 +112,10 @@ struct MicroscaleGemmPipelineAgBgCrCompV3 : public BaseGemmPipelineAgBgCrCompV3<
CK_TILE_HOST_DEVICE static constexpr index_t GetSmemSize()
{
return Policy::template GetSmemSize<Problem>();
constexpr index_t smem_size_a = Policy::template GetSmemSizeA<Problem>();
constexpr index_t smem_size_b = Policy::template GetSmemSizeB<Problem>();
return smem_size_a + smem_size_b;
}
CK_TILE_HOST static std::string Print()