leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 30 Packages Projects Releases Wiki Activity

CUTLASS 2.4 (Implicit GEMM convolution) (#147)

Browse Source 
CUTLASS 2.4 (Implicit GEMM Convolution)

Co-authored-by: Manish Gupta <manigupta@nvidia.com>, Haicheng Wu <haichengw@nvidia.com>, Dustyn Blasig <dblasig@nvidia.com>, Andrew Kerr <akerr@nvidia.com>
This commit is contained in:
Manish Gupta
2020-11-19 21:25:25 -08:00
committed by GitHub
co-authored by Manish Gupta <manigupta@nvidia.com>, Haicheng Wu <haichengw@nvidia.com>, Dustyn Blasig <dblasig@nvidia.com>, Andrew Kerr <akerr@nvidia.com>
parent c2b80ad4e4
commit 6615010cd0
224 changed files with 43939 additions and 1061 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/unit/epilogue/threadblock/epilogue_simt_sm61.cu
+5 -5
View File
@@ -804,7 +804,7 @@ TEST(SM61_Epilogue_threadblock_epilogue, simt_i8_i32_32x64_32x64x8) {
// Output operator
//
using OutputOp = cutlass::epilogue::thread::LinearCombinationClamp<
using OutputOp = cutlass::epilogue::thread::LinearCombination<
ElementOutput,
kElementsPerAccess,
ElementAccumulator,
@@ -874,7 +874,7 @@ TEST(SM61_Epilogue_threadblock_epilogue, simt_i8_i32_32x128_32x64x8) {
// Output operator
//
using OutputOp = cutlass::epilogue::thread::LinearCombinationClamp<
using OutputOp = cutlass::epilogue::thread::LinearCombination<
ElementOutput,
kElementsPerAccess,
ElementAccumulator,
@@ -944,7 +944,7 @@ TEST(SM61_Epilogue_threadblock_epilogue, simt_i8_i32_64x128_32x64x8) {
// Output operator
//
using OutputOp = cutlass::epilogue::thread::LinearCombinationClamp<
using OutputOp = cutlass::epilogue::thread::LinearCombination<
ElementOutput,
kElementsPerAccess,
ElementAccumulator,
@@ -1014,7 +1014,7 @@ TEST(SM61_Epilogue_threadblock_epilogue, simt_i8_i32_128x128_32x64x8) {
// Output operator
//
using OutputOp = cutlass::epilogue::thread::LinearCombinationClamp<
using OutputOp = cutlass::epilogue::thread::LinearCombination<
ElementOutput,
kElementsPerAccess,
ElementAccumulator,
@@ -1084,7 +1084,7 @@ TEST(SM61_Epilogue_threadblock_epilogue, simt_i8_i32_128x64_32x64x8) {
// Output operator
//
using OutputOp = cutlass::epilogue::thread::LinearCombinationClamp<
using OutputOp = cutlass::epilogue::thread::LinearCombination<
ElementOutput,
kElementsPerAccess,
ElementAccumulator,