ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-11 08:50:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

[Navi3x] Fix Gridwise_multiple_d operation (#649)

Browse Source 
* Add CMake Option "USE_OPT_NAVI3X"

* fix bug
This commit is contained in:
Haocong WANG
2023-03-24 00:22:10 +08:00
committed by GitHub
parent fe96e8fbf2
commit e5376be4ac
2 changed files with 12 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_wmma_cshuffle.hpp
View File

@@ -431,6 +431,9 @@ struct GridwiseGemmMultipleD_k0mk1_k0nk1_mn_wmma_cshuffle
constexpr auto b_block_desc_k0perblock_nperblock_k1 =
GetBBlockDescriptor_K0PerBlock_NPerBlock_K1();
constexpr auto cshuffle_block_desc_mshrepeat_mpershrepeat_nshrepeat_npershrepeat =
GetCShuffleBlockDescriptor_MShRepeat_MPerShRepeat_NShRepeat_NPerShRepeat();
constexpr auto max_lds_align = K1;
constexpr auto a_block_space_size_aligned = math::integer_least_multiple(
@@ -439,8 +442,13 @@ struct GridwiseGemmMultipleD_k0mk1_k0nk1_mn_wmma_cshuffle
constexpr auto b_block_space_size_aligned = math::integer_least_multiple(
b_block_desc_k0perblock_nperblock_k1.GetElementSpaceSize(), max_lds_align);
return (a_block_space_size_aligned * sizeof(ADataType) +
b_block_space_size_aligned * sizeof(BDataType));
constexpr auto c_block_space_size_aligned = math::integer_least_multiple(
cshuffle_block_desc_mshrepeat_mpershrepeat_nshrepeat_npershrepeat.GetElementSpaceSize(),
max_lds_align);
return math::max((a_block_space_size_aligned * sizeof(ADataType) +
b_block_space_size_aligned * sizeof(BDataType)),
c_block_space_size_aligned * sizeof(CShuffleDataType));
}
// block_id to matrix tile idx (m0, n0) mapping are controlled by {M01, N01}