[petsc-dev] segv on Cray with 64K processes

[Mark F. Adams]

I've got a consistent segv on the Cray at NERSC with 64K cores.  No problems with smaller jobs.

It seems to happen in here:

  /* Done after init due to a bug in MPICH-GM? */
  ierr = PetscErrorPrintfInitialize();CHKERRQ(ierr);

I can keep diving in, but anyone have any ideas on this?

Mark