ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-12 01:10:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

update build

Browse Source
This commit is contained in:
Chao Liu
2019-07-05 16:33:48 -05:00
parent 96d73c2154
commit ce4ec7dcaa
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
composable_kernel/include/tensor_operation/blockwise_gemm.hpp
View File

@@ -131,10 +131,10 @@ struct BlockwiseGemmBlockABlockBThreadCTransANormalBNormalC_v2
// thread A, B for GEMM
constexpr auto a_thread_mtx =
make_ConstantMatrixDescriptor(Number<KPerThreadLoop>{}, Number<MPerThread>{});
make_ConstantMatrixDescriptor_packed(Number<KPerThreadLoop>{}, Number<MPerThread>{});
constexpr auto b_thread_mtx =
make_ConstantMatrixDescriptor(Number<KPerThreadLoop>{}, Number<NPerThread>{});
make_ConstantMatrixDescriptor_packed(Number<KPerThreadLoop>{}, Number<NPerThread>{});
FloatA p_a_thread[a_thread_mtx.GetElementSpace()];
FloatB p_b_thread[b_thread_mtx.GetElementSpace()];