Changes in ex5_55.out

dd874c20e1b8bb56639592ba136e1f877322cbbd - Merge branch 'hongzh/sell-cuda' into 'main'

Mon, 10 Apr 2023 23:51:00 +0000

Merge branch 'hongzh/sell-cuda' into 'main'SELL-based SpMVSee merge request petsc/petsc!3428 List of files: /petsc/src/mat/tests/output/ex5_55.out

5f9962eec1b191700dd210fc035aa56572a01623 - Add more tests

Sat, 08 Apr 2023 04:59:57 +0000

Add more tests List of files: /petsc/src/mat/tests/output/ex5_55.out

90d2215b4f5b865a0e7953289703ce9072a42621 - Add the load-balancing kernel for MatMultAdd_SeqSELL and fine tune the heuristic

Tue, 12 Jan 2021 02:45:55 +0000

Add the load-balancing kernel for MatMultAdd_SeqSELL and fine tune the heuristicKernel7 is significantly slower than kernel9x for the following two cases:- nrows is too small. Kernel7 uses 2 threads per row (assuming sliceheight=16), it does not fully utilize the GPU if nrows < 100K.- maxslicewidth is too big.Thanks-to: Peng Wang List of files: /petsc/src/mat/tests/output/ex5_55.out