leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 25 Packages Projects Releases Wiki Activity

releaase 2.11 (#703)

Browse Source
This commit is contained in:
Aditya Atluri
2022-11-19 09:02:15 -05:00
committed by GitHub
parent 3c90f6aea6
commit c975e2ccbb
329 changed files with 47332 additions and 10607 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/30_wgrad_split_k/30_wgrad_split_k.cu
+3 -3
View File
@@ -531,17 +531,17 @@ Result profile_convolution(Options const &options) {
// Reduction input
{
reinterpret_cast<ElementAccumulator*> (workspace.get()),
ReductionStrideIndex(tensor_c.stride()[ImplicitGemm::ImplicitGemmKernel::kTensorCStrideIdx])
ReductionStrideIndex(tensor_c.stride()[ImplicitGemm::UnderlyingKernel::kTensorCStrideIdx])
},
// Destination
{
tensor_d.device_data(),
ReductionStrideIndex(tensor_d.stride()[ImplicitGemm::ImplicitGemmKernel::kTensorCStrideIdx])
ReductionStrideIndex(tensor_d.stride()[ImplicitGemm::UnderlyingKernel::kTensorCStrideIdx])
},
// Source
{
tensor_c.device_data(),
ReductionStrideIndex(tensor_c.stride()[ImplicitGemm::ImplicitGemmKernel::kTensorCStrideIdx])
ReductionStrideIndex(tensor_c.stride()[ImplicitGemm::UnderlyingKernel::kTensorCStrideIdx])
},
{options.alpha, options.beta}
);