SuperLU Distributed 8.2.1
Distributed memory sparse direct solver
|
This example illustrates how to divide up the processes into subgroups. More...
#include <math.h>
#include "superlu_ddefs.h"
Functions | |
int | main (int argc, char *argv[]) |
This example illustrates how to divide up the processes into subgroups.
Copyright (c) 2003, The Regents of the University of California, through Lawrence Berkeley National Laboratory (subject to receipt of any required approvals from U.S. Dept. of Energy)
All rights reserved.
The source code is distributed under BSD license, see the file License.txt at the top-level directory.
-- Distributed SuperLU routine (version 6.1) -- Lawrence Berkeley National Lab, Univ. of California Berkeley. March 15, 2003 April 5, 2015
int main | ( | int | argc, |
char * | argv[] | ||
) |
Purpose ======= The driver program PDDRIVE4. This example illustrates how to divide up the processes into subgroups (multiple grids) such that each subgroup solves a linear system independently from the other. In this example, there are 2 subgroups: 1. subgroup 1 consists of processes 0 to 5 arranged as a 2-by-3 process grid. 2. subgroup 2 consists of processes 6 to 9 arranged as a 2-by-2 process grid. With MPICH, program may be run by typing: mpiexec -n 10 pddrive4 big.rua