diff options
| author | Robert Maynard <rmaynard@nvidia.com> | 2022-10-11 14:09:42 (GMT) |
|---|---|---|
| committer | Robert Maynard <rmaynard@nvidia.com> | 2022-10-11 14:35:50 (GMT) |
| commit | 01cfd0163d93880ed73fede54fa6bae3064dd58e (patch) | |
| tree | b13e380642802a973eaead300314599359573b1a /Modules | |
| parent | 17250fe2c9ad70610fce9079a50049e53d3b84b9 (diff) | |
| download | CMake-01cfd0163d93880ed73fede54fa6bae3064dd58e.zip CMake-01cfd0163d93880ed73fede54fa6bae3064dd58e.tar.gz CMake-01cfd0163d93880ed73fede54fa6bae3064dd58e.tar.bz2 | |
FindCUDAToolkit: Add support for the nvptx compiler library
Fixes #23892
Diffstat (limited to 'Modules')
| -rw-r--r-- | Modules/FindCUDAToolkit.cmake | 20 |
1 files changed, 20 insertions, 0 deletions
diff --git a/Modules/FindCUDAToolkit.cmake b/Modules/FindCUDAToolkit.cmake index 0e333cc..391b185 100644 --- a/Modules/FindCUDAToolkit.cmake +++ b/Modules/FindCUDAToolkit.cmake @@ -119,6 +119,7 @@ of the following libraries that are part of the CUDAToolkit: - :ref:`nvGRAPH<cuda_toolkit_nvGRAPH>` - :ref:`nvJPEG<cuda_toolkit_nvJPEG>` - :ref:`nvidia-ML<cuda_toolkit_nvML>` +- :ref:`nvPTX Compiler<cuda_toolkit_nvptx>` - :ref:`nvRTC<cuda_toolkit_nvRTC>` - :ref:`nvToolsExt<cuda_toolkit_nvToolsExt>` - :ref:`nvtx3<cuda_toolkit_nvtx3>` @@ -334,6 +335,22 @@ Targets Created: - ``CUDA::nvjpeg`` - ``CUDA::nvjpeg_static`` +.. _`cuda_toolkit_nvPTX`: + +nvPTX Compiler +"""""""""""""" + +.. versionadded:: 3.25 + +The `nvPTX <https://docs.nvidia.com/cuda/ptx-compiler-api/index.html>`_ (PTX Compilation) library. +The PTX Compiler APIs are a set of APIs which can be used to compile a PTX program into GPU assembly code. +Introduced in CUDA 11.1 +This is a static library only. + +Targets Created: + +- ``CUDA::nvptxcompiler`` starting in CUDA 11.1 + .. _`cuda_toolkit_nvRTC`: nvRTC @@ -1015,6 +1032,9 @@ if(CUDAToolkit_FOUND) endif() _CUDAToolkit_find_and_add_import_lib(nvrtc DEPS cuda_driver) + if(CUDAToolkit_VERSION VERSION_GREATER_EQUAL 11.1.0) + _CUDAToolkit_find_and_add_import_lib(nvptxcompiler_static DEPS cuda_driver) + endif() _CUDAToolkit_find_and_add_import_lib(nvml ALT nvidia-ml nvml) |