leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 24 Packages Projects Releases Wiki Activity

CUTLASS 2.10 updates (#622)

Browse Source 
Co-authored-by: Aniket Shivam <ashivam@nvidia.com>
This commit is contained in:
ANIKET SHIVAM
2022-09-12 21:26:30 -04:00
committed by GitHub
co-authored by Aniket Shivam
parent beae168f90
commit e773429f7e
96 changed files with 8365 additions and 1667 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/36_gather_scatter_fusion/gather_scatter_fusion.cu
+3 -3
View File
@@ -187,8 +187,8 @@ struct Options {
// elements in input matrices.
using ElementAccumulator = float; // <- data type of accumulator
using ElementComputeEpilogue = ElementAccumulator; // <- data type of epilogue operations
using ElementInputA = cutlass::half_t;; // <- data type of elements in input matrix A
using ElementInputB = cutlass::half_t;; // <- data type of elements in input matrix B
using ElementInputA = cutlass::half_t; // <- data type of elements in input matrix A
using ElementInputB = cutlass::half_t; // <- data type of elements in input matrix B
using ElementOutput = float; // <- data type of elements in output matrix D
// The code section below describes matrix layout of input and output matrices.
@@ -252,7 +252,7 @@ using Gemm = cutlass::gemm::device::GemmUniversal<ElementInputA,
SwizzleThreadBlock,
NumStages,
8, /*alignmentA*/
8, /*alignmengB*/
8, /*alignmentB*/
cutlass::arch::OpMultiplyAdd,
cutlass::ComplexTransform::kNone,
cutlass::ComplexTransform::kNone,