Skip to content

GitLab

"torchvision/git@developer.sourcefind.cn:OpenDAS/vision.git" did not exist on "99ace645b081e4d160ed6eab81b8dea99aafd340"
Commit 982e59b3 authored by ltqin's avatar ltqin
Browse files

Merge branch 'develop' into conv_splitk_f32

parents f683fed7 a4f24233
Hide whitespace changes
Inline Side-by-side
Showing with 5 additions and 2 deletions
composable_kernel/include/tensor_operation/blockwise_gemm_xdlops.hpp
View file @ 982e59b3
...@@ -157,10 +157,13 @@ struct BlockwiseGemmXdlops_k0mk1_k0nk1_m0n0m1n1m2m3m4n2_v1 ...@@ -157,10 +157,13 @@ struct BlockwiseGemmXdlops_k0mk1_k0nk1_m0n0m1n1m2m3m4n2_v1
__host__ __device__ static constexpr auto __host__ __device__ static constexpr auto
MakeCGridDescriptor_M0_N0_M1_N1_M2_M3_M4_N2(const CGridDesc_M_N& c_grid_desc_m_n) MakeCGridDescriptor_M0_N0_M1_N1_M2_M3_M4_N2(const CGridDesc_M_N& c_grid_desc_m_n)
{ {
const auto M = c_grid_desc_m_n.GetLength(I0);
const auto N = c_grid_desc_m_n.GetLength(I1);
const auto c_grid_desc_m0_n0_m1_n1_m2_n2 = transform_tensor_descriptor( const auto c_grid_desc_m0_n0_m1_n1_m2_n2 = transform_tensor_descriptor(
c_grid_desc_m_n, c_grid_desc_m_n,
make_tuple(make_unmerge_transform(make_tuple(MRepeat, MWaves, MPerXDL)), make_tuple(make_unmerge_transform(make_tuple(M / (MWaves * MPerXDL), MWaves, MPerXDL)),
make_unmerge_transform(make_tuple(NRepeat, NWaves, NPerXDL))), make_unmerge_transform(make_tuple(N / (NWaves * NPerXDL), NWaves, NPerXDL))),
make_tuple(Sequence<0>{}, Sequence<1>{}), make_tuple(Sequence<0>{}, Sequence<1>{}),
make_tuple(Sequence<0, 2, 4>{}, Sequence<1, 3, 5>{})); make_tuple(Sequence<0, 2, 4>{}, Sequence<1, 3, 5>{}));
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment