Mark Gates
Mark Gates
@sknepper Discussion of interest.
I would vote for either * `geherk` — generalized version of `herk` * `hegemm` — Hermitian version of `gemm` (and the `sy` symmetric versions of these.) One item for consideration...
The `test_norm` unit test didn't see the GPU devices due to a minor issue in the `run_tests.py` script, which was setting `(CUDA|ROCR)_VISIBLE_DEVICES=''` for `test_lq`. It's safe to ignore. I'll submit...
The issue with test_norm `skipped: requires num_devices > 0` should be now resolved by #187. See the 2 `unit_test` commits; sorry those are unrelated to the shared library version which...
Thanks for the detailed bug report. We will need to investigate.
Commit [3c4cdcc](https://github.com/icl-utk-edu/slate/pull/48/commits/3c4cdcc0f4651227849c70e67f9e57c240272581) has [3 failures](https://github.com/icl-utk-edu/slate/actions/runs/5412295676/jobs/9836199058?pr=48) CUDA has 2 failures, one in Cholesky QR, one in SVD: ``` mpirun -np 4 ./gpu_bind.sh ./tester --origin d --target d --ref n --nb 8...
I can't reproduce the AMD error on histamine inside Docker. Bewildering. Unfortunately, I can't run Docker on dopamine right now.
2 routines FAILED: hegv, gesvd Both have segfaults. SVD may be fixed with SVD PR.
On CUDA, `hegv` and `svd` have segfaults, which appear to be inside Open MPI in ScaLAPACK BLACS: ``` mpirun -np 4 ./gpu_bind.sh ./tester --origin d --target d --ref n --nb...
Current failures: ``` ** Tests ** > mpirun -np 4 ./gpu_bind.sh ./tester --origin s --target h --ref n --nb 8 --type s,d,c,z --lookahead 1 --dim 100 potri terminate called after...