Dear all,
I have a small test code here trying to test the performance of
MPI_Allgatherv, I was shocked by the waiting time that MPI_Allgatherv
consumed. I'm sure something wrong with my code. Could someone help me
to modify it? Thanks a lot!!!!
+++++++++++++++++++++++++++++++++++++++++++
results
node 0 comutime 0.000001 totaltime 13.694220
node 1 comutime 5.649959 totaltime 95.133599
node 2 comutime 5.464476 totaltime 95.928307
node 3 comutime 5.464566 totaltime 96.483795
node 4 comutime 5.540017 totaltime 97.016238
node 5 comutime 5.466977 totaltime 97.538457
node 6 comutime 5.618389 totaltime 98.086424
node 7 comutime 5.490053 totaltime 98.649446
node 8 comutime 5.541841 totaltime 99.408869
node 9 comutime 5.466705 totaltime 99.961623
node 10 comutime 5.466315 totaltime 100.550240
node 11 comutime 5.515423 totaltime 101.133764
node 12 comutime 5.516169 totaltime 101.655122
node 13 comutime 5.480149 totaltime 101.737988
node 14 comutime 5.386903 totaltime 101.799232
++++++++++++++++++++++++++++++++++++++++++
code:
#include <stdio.h>
#include <mpi.h>
const int Nrows = 20000;
const int Ncolumns = 1000;
int main (int argc, char **argv) {
// int matrix[Nrows][Ncolumns];
int myRank, Nprocessors;
MPI_Status stat;
MPI_Datatype columntype, rowtype;
MPI_Init(&argc, &argv);
MPI_Comm_rank(MPI_COMM_WORLD, &myRank);
MPI_Comm_size(MPI_COMM_WORLD, &Nprocessors);
int counts[Nprocessors];
int displacements[Nprocessors];
int offsets[Nprocessors];
counts[0] = 0;
displacements[0] = 0;
displacements[1] = 0;
int bin = Nrows / (Nprocessors-1);
int bins[Nprocessors];
int *matrix = new int[Nrows*Ncolumns];
for (int i=1; i<Nprocessors; i++) bins[i] = bin;
if( Nrows > (Nprocessors - 1) * bin )
for (int i=1; i<=Nrows-(Nprocessors-1)*bin; i++)
bins[i] ++;
for( int i=1; i<Nprocessors; i++ ) {
displacements[i] = displacements[i - 1] + counts[i-1];
counts[i] = bins[i] * Ncolumns;
}
MPI_Allgather( &counts[myRank], 1, MPI_INT, counts, 1,
MPI_INT, MPI_COMM_WORLD );
int my_offset = displacements[myRank];
MPI_Gather( &my_offset, 1, MPI_INT, offsets, 1, MPI_INT, 0,
MPI_COMM_WORLD );
double start_time = MPI_Wtime();
for (int i=0; i<counts[myRank]; i++) {
matrix[my_offset + i] = myRank*1000 + i;
for (int j=0; j<1000; j++) {}
}
double end_time = MPI_Wtime();
double computation = end_time - start_time;
// MPI_Barrier(MPI_COMM_WORLD);
MPI_Allgatherv ( &matrix[my_offset], counts[myRank], MPI_INT,
matrix, counts, displacements, MPI_INT, MPI_COMM_WORLD);
// MPI_Barrier(MPI_COMM_WORLD);
end_time = MPI_Wtime();
double totaltime = end_time - start_time;
printf("node %d comutime %lf totaltime %lf\n", myRank,
computation, totaltime);
MPI_Finalize();
return(0);
}
Guoli Wang, Ph.D.
Bioinformatics Group
Fox Chase Cancer Center
Phone: (215)-214-4261
|
