ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-12 09:16:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

tidy

Browse Source
This commit is contained in:
Chao Liu
2021-08-09 18:49:59 -05:00
parent d18428901e
commit 76f3131939
6 changed files with 6 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
composable_kernel/include/tensor_operation/gridwise_dynamic_gemm_xdlops_v2r3.hpp
View File

@@ -411,9 +411,6 @@ struct GridwiseDynamicGemm_k0mk1_k0nk1_mn_xdlops_v2r3
constexpr auto a_block_space_size =
math::integer_least_multiple(a_k0_m_k1_block_desc.GetElementSpaceSize(), max_lds_align);
constexpr auto b_block_space_size =
math::integer_least_multiple(b_k0_n_k1_block_desc.GetElementSpaceSize(), max_lds_align);
FloatAB* p_a_block = p_shared_block;
FloatAB* p_b_block = p_shared_block + a_block_space_size;
@@ -574,8 +571,6 @@ struct GridwiseDynamicGemm_k0mk1_k0nk1_mn_xdlops_v2r3
make_dynamic_naive_tensor_descriptor_packed_v2(make_tuple(
I1, I1, I1, I1, Number<M0>{}, Number<1>{}, Number<M2>{}, Number<1>{}));
StaticBuffer<AddressSpaceEnum_t::Vgpr, FloatC, BlkSize> c_blk_buf_;
// calculate origin of thread output tensor on global memory
// blockwise GEMM c matrix starting index
const auto c_thread_mtx_on_block =