Skip to content

PETSC with CUDA backend sparse linear solvers #27

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Draft
wants to merge 33 commits into
base: main
Choose a base branch
from
Draft

PETSC with CUDA backend sparse linear solvers #27

wants to merge 33 commits into from

Conversation

@AlexTru96
Copy link

  • Polysolve can use PETSC backend for calling external libraries such as : PARDISO, MUMPS, STRUMPACK, CUSparse, SUPERLU , SUPERLU_dist and PETSC native solver.
  • AMGCL with CUDA backend by @[njsyw1997], fixed bugs, now suitable for PolyFEM
  • CuDENSE solver (could work for small sparse matrices) by @[map9959], fixed bugs, now suitable for PolyFEM

njsyw1997 and others added 30 commits June 14, 2022 13:10
@njsyw1997
Update Hypre Block solver
bc6f295
@njsyw1997
Hypre test
252b87f
@njsyw1997
Merge branch 'polyfem:main' into official
3e4cc13
@njsyw1997
Update the recommend parameters
6b301cf
@njsyw1997
Merge branch 'official' of https://github.com/njsyw1997/polysolve int…
187ab41 
…o official
@njsyw1997
Enable Hypre openmp
09249d7
@njsyw1997
Old json interface
d1df567 
Old json interface and new solver option, only use for local test
@njsyw1997
Old json interface
135bf3b
@njsyw1997
Try to enable parallelism
001e95b
@njsyw1997
Turn Sequential ON(MPI ON),OPENMP off
42ae898 
The same cmake setting as the Hypre official https://github.com/hypre-space/hypre/blob/master/src/CMakeLists.txt
@njsyw1997
Revert "Turn Sequential OFF(MPI ON),OPENMP OFF"
1afecaa 
The same cmake setting as the Hypre official https://github.com/hypre-space/hypre/blob/master/src/CMakeLists.txt
@njsyw1997
Turn Sequential OFF(MPI ON),OPENMP OFF
544225d
@njsyw1997
Upgrade hypre to the newest, turn on Openmp trying for parallel
8ab6e7d
@njsyw1997
Update hypre to 2.25.0, turn on OPENMP
68a68b5
@njsyw1997
Update cuda, cannot resolve unique_ptr
c54adbf
@njsyw1997
Update AMGCL CUDA solver
c215d8c
@njsyw1997
Update AMGCL CUDA solver and Hypre block solver
c05c48b
@njsyw1997
Delete the local nvcc path
2fdfddd
@njsyw1997
Update nvcc path
41adee3
@njsyw1997
Solve the problem of undefined reference
6459409
@njsyw1997
Call cuda solver in cpp file, try it in polyfem
2137b93
@AlexTru96
Hypre OFF and relaxation as preconditioner by default
3456171
@AlexTru96
Merge branch 'main' of https://github.com/polyfem/polysolve into poly…
3c4672a 
…FEM_GPU
@AlexTru96
fixing warnings only for CXX
ceb1c68
@AlexTru96
setting cusparse ilu0 and runtime type for relaxation
3095b34
@AlexTru96
fixing AMGCL_cuda interface, Cusparseilu0 optional
803de42
@AlexTru96
AMG preconditioner as default for AMGCL_CUDA, Setting CUDA and HYPRE …
288b9bd 
…off as default
@AlexTru96
Merge branch 'main' of https://github.com/polyfem/polysolve into PETSC
84ad633
@AlexTru96
added PETSC MUMPS solver
1351f58
@AlexTru96
Adding multiple external sparse solvers with PETSC backend, setting G…
a8beae0 
…PU error check suitable for polyfem
@AlexTru96 AlexTru96 marked this pull request as draft January 29, 2023 21:28
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@AlexTru96 @njsyw1997