Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Navi3x] Fix Gridwise_multiple_d operation #649

Merged
merged 3 commits into from
Mar 23, 2023
Merged

[Navi3x] Fix Gridwise_multiple_d operation #649

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b6029f9
Add CMake Option "USE_OPT_NAVI3X"
aska-0096 Mar 22, 2023
6c97a1e
Merge branch 'develop' of https://github.com/ROCmSoftwarePlatform/com…
aska-0096 Mar 23, 2023
71f5dd1
fix bug
aska-0096 Mar 23, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions example/30_grouped_conv_fwd_multiple_d/run_grouped_conv_fwd_bias_relu_add_wmma_example.inc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,8 +74,8 @@ using DeviceConvFwdInstance =
8, // BBlockTransferSrcScalarPerVector
8, // BBlockTransferDstScalarPerVector_BK1
true, // BBlockLdsExtraN
1,
1,
4,
2,
S<1, 32, 1, 8>,
8>;

Expand Down
12 changes: 10 additions & 2 deletions include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_wmma_cshuffle.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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(
Expand All @@ -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}
Expand Down