GPU CUDA variant of ISSM#35
Draft
justinh2002 wants to merge 13 commits into
Draft
Conversation
In +ad builds PVec resolves to adjoint_petsc::ADVec (ADVecImpl*) which is not compatible with VecScatterCreate*/VecGetArrayRead — those APIs only accept plain Vec. +cuda and +ad are mutually exclusive (Spack conflict), so: _HAVE_PETSC_CUDA_ defined -> scatter / VecGetArrayRead (Vec only) _HAVE_PETSC_CUDA_ not set -> original VecGetValues path (handles ADVec) Fixes CI failure in gcc-ad build (PR #35).
The strncmp commit accidentally dropped the preallocation call, closing braces and return statement, leaving only the fold marker. Restore them.
Collaborator
Author
|
!redeploy |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
ISSM — GPU/CUDA support
https://github.com/ACCESS-NRI/ISSM
Four files modified/created:
externalpackages/petsc/install-3.22-gadi-gpu.sh--with-cuda, installs toinstall-gpu/alongside the CPU installsrc/m/classes/gpuoptions.pymd.toolkits.DefaultAnalysis = gpuoptions()that setsvec_type=cuda,mat_type=aijcusparse, GMRES+block-Jacobiconfigure.shgpustep: loads CUDA module, builds GPU PETSc if needed, then configures ISSM against ittoolkits/petsc/patches/NewMat.cppstrcmp(type,"mpiaij")→strncmp(type,"mpiaij",6)so CUDA matrix typempiaijcusparsealso gets preallocatedSpack package —
+cudavariantpackages/issm/package.py updated:
CudaPackagemixin → provides+cudavariant andcuda_archvalues automatically~cuda/+cudapairs sospack install issm +cuda cuda_arch=70propagates+cuda cuda_arch=70down to PETSc+cuda +adis rejected