ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-21 21:39:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

bug fix and tune implicit gemm

Browse Source
This commit is contained in:
Chao Liu
2019-01-16 23:24:49 -06:00
parent caf4d7e6f5
commit 216e3da609
6 changed files with 35 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/include/gridwise_direct_convolution_2.cuh
View File

@@ -174,7 +174,7 @@ __global__ void gridwise_direct_convolution_2(InGlobalDesc,
for(unsigned c_thread_data = 0; c_thread_data < CPerBlock; c_thread_data += CPerThread)
{
// threadwise convolution
#if 1
#if 0
threadwise_direct_convolution_2(
in_thread_block_desc,
p_in_block + in_block_desc.Get1dIndex(n_thread_data_begin,