Open quantumsteve opened 4 months ago
This may or may not be an easy fix but it raises a question to discuss in the next meeting. Should we continue supporting SCALAPACK
? Given how much more expensive it is to form the Kronecker matrices, even compared to the local kronmult, perhaps we should focus efforts on GMRES+MPI for local kronmult instead.
Let's discuss on the next meeting.
Describe the bug A clear and concise description of what the bug is.
ctest -R time_advance-test-mpi_4 --output-on-failure
To Reproduce Steps to reproduce the behavior:
def3174fd42a1a0010b9286a4f3c1afd308db72b
cmake ../ -DCMAKE_BUILD_TYPE=Release -DCMAKE_CXX_COMPILER=g++ -DASGARD_USE_MPI=1 -DASGARD_USE_SCALAPACK=1 -DASGARD_RECOMMENDED_DEFAULTS=1
ctest -R time_advance-test-mpi_4 --output-on-failure
Expected behavior A clear and concise description of what you expected to happen.
System:
AWS CodeBuild - asgard-unit-mpi-gxx-scalapack
module list
]none
other systems where this is reproducible [e.g. "my laptop", "none"]
my laptop
Additional context Add any other context about the problem here.
Found in #685. Tests disabled here