ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-21 13:29:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

more utility code

Browse Source
This commit is contained in:
Chao Liu
2019-09-09 00:29:33 -05:00
parent 625838def0
commit 7a7fe16086
21 changed files with 824 additions and 455 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
driver/include/device_convolution_implicit_gemm_v1_chwn_cyxk_khwn_padded.hpp
View File

@@ -115,8 +115,12 @@ void device_convolution_implicit_gemm_v1_chwn_cyxk_khwn_padded(InDesc,
constexpr index_t OutThreadCopyDataPerAccess_N = 4;
#endif
#if 0 // debug
constexpr index_t GridSize =
(N / NPerBlock) * (K / KPerBlock) * (Ho / HoPerBlock) * (Wo / WoPerBlock);
#else
constexpr index_t GridSize = 1;
#endif
printf("%s: BlockSize %u, GridSize %u \n", __func__, BlockSize, GridSize);