leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 29 Packages Projects Releases Wiki Activity

Updated mma_sm80.h to avoid perf penalty due to reinterpret_cast<>. (#100)

Browse Source 
- Updated mma_sm80.h to avoid perf penalty due to reinterpret_cast<>.
- Enhancement to CUTLASS Utility Library's HostTensorPlanarComplex template to support copy-in and copy-out
- Added test_examples target to build and test all CUTLASS examples
- Minor edits to documentation to point to GTC 2020 webinar
This commit is contained in:
Andrew Kerr
2020-06-15 10:47:01 -07:00
committed by GitHub
parent 86931fef85
commit 1ab1027954
11 changed files with 213 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/cutlass/arch/mma.h
+1
View File
@@ -164,4 +164,5 @@ struct Mma<gemm::GemmShape<1, 1, 1>, 1, ElementA, LayoutA, ElementB, LayoutB, El
#include "cutlass/arch/mma_sm61.h"
#include "cutlass/arch/mma_sm70.h"
#include "cutlass/arch/mma_sm75.h"
#include "cutlass/arch/mma_sm80.h"
/////////////////////////////////////////////////////////////////////////////////////////////////