LAM/MPI General User's Mailing List Archives

From: sean dettrick (sdettrick_at_[hidden])
Date: 2006-01-24 01:00:16

• Next message: Adams Samuel D Contr AFRL/HEDR: "LAM: STDERR and MPI"
• Previous message: sean dettrick: "LAM: LAM linking troubles on OSX10.4 with PETSc 2.3.0"
• In reply to: sean dettrick: "LAM: LAM linking troubles on OSX10.4 with PETSc 2.3.0"

Looks like I posted to this list too soon. I got some good feedback from
one of the PETSc people on this, and the result works nicely. Satish Balay
writes:

We don't have fix for this problem yet. The current workarround is to
change the following in python/PETSc/packages/MPI.py from:

    self.functions = ['MPI_Init', 'MPI_Comm_create', 'MPI_Allreduce']

to
    self.functions = ['MPI_Init', 'MPI_Comm_create']

and rerun configure.

• Next message: Adams Samuel D Contr AFRL/HEDR: "LAM: STDERR and MPI"
• Previous message: sean dettrick: "LAM: LAM linking troubles on OSX10.4 with PETSc 2.3.0"
• In reply to: sean dettrick: "LAM: LAM linking troubles on OSX10.4 with PETSc 2.3.0"