Skip to content

LU_SGS Preconditioner GPU Port #2539

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

Open
areenraj wants to merge 22 commits into
base: develop
Choose a base branch
from
Open

LU_SGS Preconditioner GPU Port #2539

Changes from 1 commit
Commits
Show all changes
22 commits
Select commit Hold shift + click to select a range
79c9e52
updating branch
areenraj Jun 10, 2025
6686171
updating branch
areenraj Jun 10, 2025
b7591f4
Major commit: graph partitioning algorithms, level scheduling method,…
areenraj Jun 25, 2025
6f51f45
Major commit: graph partitioning algorithms, level scheduling method,…
areenraj Jun 25, 2025
cdf0225
resolving conflicts
areenraj Jun 25, 2025
9dd3028
resolving conflicts
areenraj Jun 25, 2025
2495edd
resolving some more conflicts
areenraj Jun 25, 2025
f68358e
cleaning up
areenraj Jun 25, 2025
bf561b6
apologies for repeated commits, just cleaning
areenraj Jun 25, 2025
9121e25
coalesced memory access for MVP, shared memory addition and lamda fun…
areenraj Jun 29, 2025
991e29f
bug fixes
areenraj Jul 1, 2025
9bfeff9
Merge remote-tracking branch 'upstream/master'
areenraj Jul 3, 2025
0372099
Working GPU LU_SGS Preconditioner Port
areenraj Jul 15, 2025
52b90b6
Fixed the issue with the visibility of the rowsPerBlock variable. Als…
areenraj Jul 17, 2025
d367627
Working LU_SGS Preconditioner with graph partitioned algorithms, upda…
areenraj Jul 17, 2025
661c9b8
LU_SGS Preconditioner Port
areenraj Jul 17, 2025
b5cf7dd
Merge branch 'master' of https://github.com/areenraj/SU2_GSoC_GPU
areenraj Jul 17, 2025
c4dbe5c
Fixing warnings
areenraj Jul 17, 2025
b3d2fbf
Merge branch 'develop' of https://github.com/su2code/SU2
areenraj Jul 17, 2025
1be1e2f
Syncing repo to develop
areenraj Jul 17, 2025
7472bd1
updating submodule versions
areenraj Jul 17, 2025
352e148
Fixing some more warnings
areenraj Jul 17, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
bug fixes
  • Loading branch information
@areenraj
areenraj committed Jul 1, 2025
commit 991e29f0b61f5551351617a5ba1d6e9b499cbed3
2 changes: 1 addition & 1 deletion Common/src/linear_algebra/CSysMatrixGPU.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,7 +76,7 @@ __global__ void FirstSymmetricIterationKernel(matrixType* matrix, vectorType* ve
};
Comment on lines +95 to +97
Copy link
Copy Markdown
Member

@pcarruscag pcarruscag Jul 18, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I was thinking more that these could be part of the matrix type that you pass to the kernel.
You'd make a struct that would have the pointers and operator(I, j, ...) to access the elements and in that operator you encapsulate this indexing logic.
This would make the code a little shorter.


auto matrixDiagonalIndex = [=](unsigned long row, unsigned short threadNo){
return (d_row_ptr[row] * matrixParam.blockSize + threadNo);
return (d_dia_ptr[row] * matrixParam.blockSize + threadNo);
};

auto vectorIndex = [=](unsigned long row, unsigned short elemNo){
Expand Down