mirror/CMake
1
0
Fork 0
mirror of https://github.com/Kitware/CMake.git synced 2026-01-02 11:49:55 -06:00
Code Issues Packages Projects Releases Wiki Activity

CUDA/Clang: Update nvcc default architectures with CUDA 13 deprecations

Browse Source 
As outlined in the CUDA 12.9 release notes sm_5X, sm_6X, and sm_70
are being removed in CUDA 13:

> Maxwell, Pascal, and Volta architectures are now feature-complete with
> no further enhancements planned. While CUDA Toolkit 12.x series will
> continue to support building applications for these architectures,
> offline compilation and library support will be removed in the next
> major CUDA Toolkit version release.
This commit is contained in:
Robert Maynard
2025-05-13 08:55:54 -04:00
committed by Brad King
parent 23e8090aa4
commit b62f3257f2
1 changed files with 3 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
Modules/CMakeDetermineCUDACompiler.cmake
View File

@@ -115,6 +115,9 @@ if(NOT CMAKE_CUDA_COMPILER_ID_RUN)
# Clang does not automatically select an architecture supported by the SDK.
# Prefer NVCC's default for each SDK version, and fall back to older archs.
set(archs "")
if(NOT CMAKE_CUDA_COMPILER_TOOLKIT_VERSION VERSION_LESS 13.0)
list(APPEND archs 75)
endif()
if(NOT CMAKE_CUDA_COMPILER_TOOLKIT_VERSION VERSION_LESS 11.0)
list(APPEND archs 52)
endif()