ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-16 19:09:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '5d67d82a0bb6dbf5f82f3b4ba2e9188eb838b927' into develop

Browse Source
This commit is contained in:
assistant-librarian[bot]
2025-12-02 11:12:35 +00:00
parent ae8f3a3b19
commit be7c12a132
2 changed files with 506 additions and 410 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
include/ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_v4.hpp
View File

@@ -23,7 +23,8 @@ struct BaseGemmPipelineAgBgCrCompV4
CK_TILE_HOST_DEVICE static constexpr bool BlockHasHotloop(index_t num_loop)
{
return num_loop > PrefetchStages;
constexpr index_t HotLoopGlobalReads = 2;
return num_loop >= (HotLoopGlobalReads + PrefetchStages);
}
CK_TILE_HOST_DEVICE static constexpr TailNumber GetBlockLoopTailNum(index_t num_loop)

913
include/ck_tile/ops/grouped_convolution/utils/transform_conv_bwd_data_to_gemm.hpp
View File

File diff suppressed because it is too large Load Diff