NVIDIA/cutlass
1
0
Fork 0
mirror of https://github.com/NVIDIA/cutlass.git synced 2026-05-11 08:50:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUTLASS 3.5.1 (#1623)

Browse Source 
* CUTLASS 3.5.1

* updates, optimizations, fixes
This commit is contained in:
Vijay Thakkar
2024-07-29 08:46:24 -04:00
committed by GitHub
parent 56b46e2d13
commit be60a0b272
312 changed files with 19793 additions and 6775 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
include/cute/algorithm/prefetch.hpp
View File

@@ -32,7 +32,7 @@
#include <cute/config.hpp>
#include <cute/tensor.hpp>
#include <cute/tensor_impl.hpp>
#include <cute/atom/copy_atom.hpp>
@@ -90,12 +90,6 @@ constexpr bool has_prefetch = false;
template <class CopyOp>
constexpr bool has_prefetch<CopyOp, void_t<typename CopyOp::PREFETCH>> = true;
template <class CopyOp, class = void>
constexpr bool is_prefetch = false;
template <class CopyOp>
constexpr bool is_prefetch<CopyOp, void_t<typename CopyOp::PREFETCH>> = is_same_v<CopyOp, typename CopyOp::PREFETCH>;
} // end namespace detail
template <class CopyOp, class... CT_Args, class... CA_Args,