leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 27 Packages Projects Releases Wiki Activity

CUTLASS 2.6 (#298)

Browse Source 
CUTLASS 2.6
This commit is contained in:
Manish Gupta
2021-07-23 00:40:53 -04:00
committed by GitHub
parent 6c29fe20ba
commit e5d51840e8
308 changed files with 32408 additions and 4722 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/profiler/src/conv3d_operation_profiler.h
+3 -3
View File
@@ -268,7 +268,7 @@ public:
A(nullptr), B(nullptr), C(nullptr), Computed(nullptr), Reference(nullptr) { }
// Returns stride vector for tensor A
std::vector<int> stride_a(library::ConvKind const &conv_kind) {
std::vector<int64_t> stride_a(library::ConvKind const &conv_kind) {
return {
configuration.layout_a(conv_kind).stride()[0],
configuration.layout_a(conv_kind).stride()[1],
@@ -278,7 +278,7 @@ public:
}
// Returns stride vector for tensor B
std::vector<int> stride_b(library::ConvKind const &conv_kind) {
std::vector<int64_t> stride_b(library::ConvKind const &conv_kind) {
return {
configuration.layout_b(conv_kind).stride()[0],
@@ -289,7 +289,7 @@ public:
}
// Returns stride vector for tensor C
std::vector<int> stride_c(library::ConvKind const &conv_kind) {
std::vector<int64_t> stride_c(library::ConvKind const &conv_kind) {
return {
configuration.layout_c(conv_kind).stride()[0],