ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-19 20:40:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

Support transposed C tile in Aquant (#2679)

Browse Source 
The performance of Aquant has increased after enabling transposed C.

Do not need to exchange AQ elements among lanes after enabling
transposed C as one thread only holds data from one row.

[ROCm/composable_kernel commit: 428090f749]
This commit is contained in:
Cong Ma
2025-08-28 14:28:09 -06:00
committed by GitHub
parent e4010d5ea1
commit 37daef0e83
10 changed files with 276 additions and 154 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
test/ck_tile/gemm_block_scale/test_run_gemm_aquant_example.inc
View File

@@ -90,6 +90,7 @@ float gemm_calc_aquant(const ck_tile::AQuantGemmHostArgs& args, const ck_tile::s
CodegenGemmShape,
CodegenGemmTraits,
QuantGroupSize,
transposed_warp_gemm,
ComputeDataType,
ck_tile::GemmPipelineScheduler::Intrawave,
has_hot_loop_v,