zhangyiss/spack
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: mention cuda multi-arch capability (#36321)

Browse Source
This commit is contained in:
Leopold Talirz 2023-03-22 21:52:53 +01:00 committed by GitHub
parent 2393e456ee
commit 311d3be18e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
lib/spack/docs/build_systems/cudapackage.rst
View File

@ -28,12 +28,15 @@ This package provides the following variants:
* **cuda_arch** * **cuda_arch**
This variant supports the optional specification of the architecture. This variant supports the optional specification of one or multiple architectures.
Valid values are maintained in the ``cuda_arch_values`` property and Valid values are maintained in the ``cuda_arch_values`` property and
are the numeric character equivalent of the compute capability version are the numeric character equivalent of the compute capability version
(e.g., '10' for version 1.0). Each provided value affects associated (e.g., '10' for version 1.0). Each provided value affects associated
``CUDA`` dependencies and compiler conflicts. ``CUDA`` dependencies and compiler conflicts.
The variant builds both PTX code for the _virtual_ architecture
(e.g. ``compute_10``) and binary code for the _real_ architecture (e.g. ``sm_10``).
GPUs and their compute capability versions are listed at GPUs and their compute capability versions are listed at
https://developer.nvidia.com/cuda-gpus . https://developer.nvidia.com/cuda-gpus .