I don’t understand the reason, but I think I figured out a solution by trial
and error. Basically, I just copied the configure line from “configure.log”
file to terminal, deleted the “--with-cc=mpicc --with-cxx=mpicxx
--with-fc=mpif90” arguments, and added the “--with-mpi-dir=”xxx”” argument,
Thanks Barry! I am still getting the same error message. Any more suggestions?
I can see that library from the login node:
lrwxrwxrwx 1 sauesw ccsstaff 29 Jan 16 16:39
error while loading shared libraries: libmpi_ibm_usempif08.so: cannot open
shared object file: No such file or directory
So using the mpif90 does not work because it links a shared library that
cannot be found at run time.
Perhaps that library is only visible on the bach nodes. You can
Dear PETSc developers,
I am trying to compile PETSc on Summit with gcc 12.1.0 and spectrum-mpi
10.4.0.6, but encountered the following configuration issues:
=
Configuring PETSc to
The bug fix for 2 is availabel in
https://gitlab.com/petsc/petsc/-/merge_requests/7279
> On Feb 9, 2024, at 10:50 AM, Barry Smith wrote:
>
>
> 1. Code going through line 692 looses the near nullspace of the matrices
> attached to the sub-KSPs
> 2. The call to MatZeroRowsColumns()
1. Code going through line 692 looses the near nullspace of the matrices
attached to the sub-KSPs
2. The call to MatZeroRowsColumns() changes then non-zero structure for MPIAIJ
but not for SEQAIJ
(unless MAT_KEEP_NONZERO_PATTERN is used)
MatZeroRowsColumns() manual page states:
Unlike
> > Because of a combination of settings, our code passes through this line:
> >
> > https://gitlab.com/petsc/petsc/-/blob/main/src/ksp/pc/impls/fieldsplit/fieldsplit.c?ref_type=heads#L692
> >
> > i.e. the matrices associated with each of the sub-KSPs of a fieldsplit are
> > destroyed and then
On Fri, Feb 9, 2024 at 7:04 AM Jeremy Theler (External) <
jeremy.theler-...@ansys.com> wrote:
> Hi all
>
> Because of a combination of settings, our code passes through this line:
>
>
> https://gitlab.com/petsc/petsc/-/blob/main/src/ksp/pc/impls/fieldsplit/fieldsplit.c?ref_type=heads#L692
>
>
Hi all
Because of a combination of settings, our code passes through this line:
https://gitlab.com/petsc/petsc/-/blob/main/src/ksp/pc/impls/fieldsplit/fieldsplit.c?ref_type=heads#L692
i.e. the matrices associated with each of the sub-KSPs of a fieldsplit are
destroyed and then re-created
