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

refactor

Browse Source
This commit is contained in:
Chao Liu
2019-02-04 15:40:34 -06:00
parent 3439e4b5b7
commit 9bbe9073ab
6 changed files with 138 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/include/gridwise_implicit_gemm_convolution_2_cnhw_srck_knhw.cuh
View File

@@ -7,7 +7,7 @@
#include "threadwise_2d_tensor_op.cuh"
#include "gemm.cuh"
// define B = N*Hi*Wi
// define B = flatten(N, Hi, Wi)
template <unsigned GridSize,
unsigned BlockSize,
class Float,

2
src/include/gridwise_implicit_gemm_convolution_3_cnhw_srck_knhw.cuh
View File

@@ -115,7 +115,7 @@ gridwise_implicit_gemm_convolution_3_cnhw_srck_knhw(InGlobalDesc,
decltype(in_cb_global_desc),
decltype(in_cb_block_desc),
decltype(in_cb_block_desc.GetLengths())>{};
#elif 0
#elif 1
const auto blockwise_in_copy =
blockwise_2d_tensor_copy_2<BlockSize,
Float,