Subject: Re: [OMPI users] Did you break MPI_Abort recently?
From: Mostyn Lewis (Mostyn.Lewis_at_[hidden])
Date: 2009-06-25 16:54:09
Something like:
#!/bin/ksh
set -x
PREFIX=$OPENMPI_GCC_SVN
export PATH=$OPENMPI_GCC_SVN/bin:$PATH
MCA="--mca btl tcp,self"
mpicc -g -O6 mpiabort.c
NPROCS=4
mpirun --prefix $PREFIX -x LD_LIBRARY_PATH $MCA -np $NPROCS -machinefile fred ./a.out
DM
On Thu, 25 Jun 2009, Ralph Castain wrote:
> Using what launch environment?
>
> On Jun 25, 2009, at 2:29 PM, Mostyn Lewis wrote:
>
>> While using the BLACS test programs, I've seen that with recent SVN
>> checkouts
>> (including todays) the MPI_Abort test left procs running. The last SVN I
>> have where it worked was 1.4a1r20936. By 1.4a1r21246 it fails.
>>
>> Works O.K. in the standard 1.3.2 release.
>>
>> A test program is below. GCC was used.
>>
>> DM
>>
>> #include <stdio.h>
>> #include <sys/types.h>
>> #include <unistd.h>
>> #include <math.h>
>> #include <mpi.h>
>>
>> #define NUM_ITERS 100000
>>
>> /* Prototype the function that we'll use below. */
>>
>> static double f(double);
>>
>> int
>> main(int argc, char *argv[])
>> {
>> int iter, rank, size, i;
>> int foo;
>> double PI25DT = 3.141592653589793238462643;
>> double mypi, pi, h, sum, x;
>> double startwtime = 0.0, endwtime;
>> int namelen;
>> char processor_name[MPI_MAX_PROCESSOR_NAME];
>>
>> /* Normal MPI startup */
>>
>> MPI_Init(&argc, &argv);
>> MPI_Comm_size(MPI_COMM_WORLD, &size);
>> MPI_Comm_rank(MPI_COMM_WORLD, &rank);
>> MPI_Get_processor_name(processor_name, &namelen);
>>
>> printf("Process %d of %d on %s\n", rank, size, processor_name);
>>
>> /* Do approximations for 1 to 100 points */
>>
>> /* sleep(5); */
>> for (iter = 2; iter < NUM_ITERS; ++iter) {
>> h = 1.0 / (double) iter;
>> sum = 0.0;
>>
>> /* A slightly better approach starts from large i and works back */
>>
>> if (rank == 0)
>> startwtime = MPI_Wtime();
>>
>> for (i = rank + 1; i <= iter; i += size) {
>> x = h * ((double) i - 0.5);
>> sum += f(x);
>> }
>> mypi = h * sum;
>>
>> if(iter == (NUM_ITERS - 1000)){
>> MPI_Barrier(MPI_COMM_WORLD);
>> if(rank == 2){
>> MPI_Abort(MPI_COMM_WORLD, -1);
>> } else {
>> /* Just loop */
>> foo = 1;
>> while(foo == 1){
>> foo = foo + 3;
>> foo = foo - 2;
>> foo = foo - 1;
>> }
>> }
>> }
>> MPI_Reduce(&mypi, &pi, 1, MPI_DOUBLE, MPI_SUM, 0, MPI_COMM_WORLD);
>> }
>>
>> /* All done */
>>
>> if (rank == 0) {
>> printf("%d points: pi is approximately %.16f, error = %.16f\n",
>> iter, pi, fabs(pi - PI25DT));
>> endwtime = MPI_Wtime();
>> printf("wall clock time = %f\n", endwtime - startwtime);
>> fflush(stdout);
>> }
>>
>> MPI_Finalize();
>> return 0;
>> }
>>
>> static double
>> f(double a)
>> {
>> return (4.0 / (1.0 + a * a));
>> }
>>
>>
>>
>> _______________________________________________
>> users mailing list
>> users_at_[hidden]
>> http://www.open-mpi.org/mailman/listinfo.cgi/users
>
> _______________________________________________
> users mailing list
> users_at_[hidden]
> http://www.open-mpi.org/mailman/listinfo.cgi/users