leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 28 Packages Projects Releases Wiki Activity

3.6.0 update (#2005)

Browse Source 
* 3.6.0 update

* doc and swap stuff

---------

Co-authored-by: yuzhai <yuzhai@nvidia.com>
Co-authored-by: Haicheng Wu <haichengw@nvidia.com>
This commit is contained in:
Yujia Zhai
2024-12-25 01:34:40 -05:00
committed by GitHub
co-authored by yuzhai Haicheng Wu
parent e1cd8c7866
commit 3d261a5974
258 changed files with 10863 additions and 3883 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/cutlass/cuda_host_adapter.hpp
+7 -2
View File
@@ -85,7 +85,11 @@ namespace cutlass {
#if !defined(__CUDACC_RTC__)
#if ((__CUDACC_VER_MAJOR__ >= 12) || \
((__CUDACC_VER_MAJOR__ == 11) && (__CUDACC_VER_MINOR__ >= 8)))
#include <cudaTypedefs.h>
#endif // (__CUDACC_VERSION__ >= 11.8)
#include <driver_types.h>
#define CUTLASS_CUDA_DRIVER_STRINGIFY(tok) #tok
@@ -100,7 +104,8 @@ namespace cutlass {
#else // defined(CUTLASS_ENABLE_DIRECT_CUDA_DRIVER_CALL)
#if (__CUDACC_VER_MAJOR__ >= 12 && __CUDACC_VER_MINOR__ >= 5)
#if ((__CUDACC_VER_MAJOR__ >= 13) || \
((__CUDACC_VER_MAJOR__ == 12) && (__CUDACC_VER_MINOR__ >= 5))) \
#define CUTLASS_CUDA_DRIVER_WRAPPER_DECL(func, ver) \
template <typename... Args> \
@@ -138,7 +143,7 @@ namespace cutlass {
return reinterpret_cast<PFN_##func>(pfn)(args...); \
}
#endif // (__CUDACC_VER_MAJOR__ >= 12 && __CUDACC_VER_MINOR__ >= 5)
#endif // (__CUDACC_VERSION__ >= 12.5)
#endif // defined(CUTLASS_ENABLE_DIRECT_CUDA_DRIVER_CALL)