Hi,
I have a problem with derived data types and MPI_Scatter/MPI_Gather in C
(Solaris 10 sparc, openmpi-1.2.4).
I want to distribute the columns of a matrix with MPI_Scatter/MPI_Gather.
Unfortunately my program didn't work with my derived data type, so I used
a 2x2 matrix to figure out what's wrong and added a printf statement after
MPI_Scatter to print the contents of the column vector of each process. The
process with rank 1 didn't get the values "2" and "4" (see below), but more
or less 0. Now I used a 4x2 matrix and still a 2-element column vector (so
I should see the upper 2x2 "matrix" in my columns) to get an idea which
values are used for process 1. As you can see below it got "5" and "7", i.e.
the values of the first column of the lower 2x2 matrix and not the values of
the block which starts after the first element of the first block (a[2][0]
instead of a[0][1]).
Since I wasn't sure if I could use MPI_Type_struct I rewrote the program
with MPI_Type_vector. This time the result was better but still not
satisfying. Process 1 got values from the second column but one value too
late (starting with a[1][1] instead of a[1][0]).
I run into the same problem with MPICH, MPICH2, and LAM-MPI, so that I have
probably misunderstood something or have a programming error. Since I dont't
know how to proceed, I would be very grateful if someone could tell me if I
can't use a strided vector with MPI_Scatter or if it is eventually a bug in
the implementations of the MPI libraries (how unlikely it is). Mainly I've
implemented this part in the following way (the full program code is appended).
int blockcounts[2] = {1, 1};
MPI_Datatype types[2] = {MPI_DOUBLE, MPI_UB};
MPI_Aint offsets[2] = {0, Q * sizeof (double)};
MPI_Datatype coltype;
MPI_Type_struct (2, blockcounts, offsets, types, &coltype);
MPI_Type_commit (&coltype);
MPI_Scatter (matrix, P, coltype, column, P, MPI_DOUBLE, 0,
MPI_COMM_WORLD);
MPI_Type_struct
===============
tyr e5 158 mpiexec -mca btl ^udapl -np 2 e5_1a
original matrix:
1 2
3 4
rank: 0 c0: 1 c1: 3
rank: 1 c0: 5.51719e-313 c1: 4.24399e-314
tyr e5 160 mpiexec -mca btl ^udapl -np 2 e5_1a
original matrix:
1 2
3 4
5 6
7 8
rank: 0 c0: 1 c1: 3
rank: 1 c0: 5 c1: 7
MPI_Type_vector
===============
tyr e5 119 mpiexec -mca btl ^udapl -np 2 e5_1b
original matrix:
1 2
3 4
5 6
7 8
rank: 0 c0: 1 c1: 3
rank: 1 c0: 4 c1: 6
Thank you very much for any help or suggestions in advance.
Kind regards
Siegmar
#include <stdio.h>
#include <stdlib.h>
#include "mpi.h"
#define P 4 /* # of rows */
#define Q 2 /* # of columns */
#define FAKTOR 2 /* multiplicator for col. elem. */
static void print_matrix (int p, int q, double **mat);
int main (int argc, char *argv[])
{
int ntasks, /* number of parallel tasks */
mytid, /* my task id */
namelen, /* length of processor name */
i, j, /* loop variables */
tmp; /* temporary value */
double matrix[P][Q],
column[2];
/* column[P];*/
int blockcounts[2] = {1, 1};
MPI_Datatype types[2] = {MPI_DOUBLE, MPI_UB};
MPI_Aint offsets[2] = {0, Q * sizeof (double)};
MPI_Datatype coltype;
MPI_Init (&argc, &argv);
MPI_Comm_rank (MPI_COMM_WORLD, &mytid);
MPI_Comm_size (MPI_COMM_WORLD, &ntasks);
/* check that we have the correct number of processes in our universe */
if (mytid == 0)
{
if (ntasks != Q)
{
printf ("\n\nWe need exactly %d processes.\n"
"Usage: mpirun -w -np %d N %s\n\n\n",
Q, Q, argv[0]);
}
}
if (ntasks != Q)
{
MPI_Finalize ();
exit (EXIT_FAILURE);
}
/* build the new type for a strided vector */
MPI_Type_struct (2, blockcounts, offsets, types, &coltype);
MPI_Type_commit (&coltype);
if (mytid == 0)
{
tmp = 1;
for (i = 0; i < P; ++i) /* initialize matrix */
{
for (j = 0; j < Q; ++j)
{
matrix[i][j] = tmp++;
}
}
printf ("\n\noriginal matrix:\n\n");
print_matrix (P, Q, (double **) matrix);
}
/* distribute columns */
MPI_Scatter (matrix, 2, coltype, column, 2, MPI_DOUBLE, 0,
/* MPI_Scatter (matrix, P, coltype, column, P, MPI_DOUBLE, 0,*/
MPI_COMM_WORLD);
printf ("rank: %d c0: %g c1: %g\n", mytid, column[0], column[1]);
for (i = 0; i < 2; ++i)
/* for (i = 0; i < P; ++i)*/
{
if ((mytid % 2) == 0)
{
column[i] = column[i] * column[i];
}
else
{
column[i] = column[i] * FAKTOR;
}
}
/* wait for result vectors */
MPI_Gather (column, 2, MPI_DOUBLE, matrix, 2, coltype, 0,
/* MPI_Gather (column, P, MPI_DOUBLE, matrix, P, coltype, 0,*/
MPI_COMM_WORLD);
if (mytid == 0)
{
printf ("\n\nresult matrix:\n"
"(odd columns: elements squared; even columns: elements "
"multiplied with %d)\n\n", FAKTOR);
print_matrix (P, Q, (double **) matrix);
}
MPI_Type_free (&coltype);
MPI_Finalize ();
return EXIT_SUCCESS;
}
/* print the values of a matrix
*
* input parameters: p number of rows
* q number of columns
* mat 2D-matrix of "double" values
* output parameters: none
* return value: none
* side effects: none
*
*/
void print_matrix (int p, int q, double **mat)
{
int i, j; /* loop variables */
for (i = 0; i < p; ++i)
{
for (j = 0; j < q; ++j)
{
printf ("%6g", *((double *) mat + i * q + j));
}
printf ("\n");
}
printf ("\n");
}
#include <stdio.h>
#include <stdlib.h>
#include "mpi.h"
#define P 4 /* # of rows */
#define Q 2 /* # of columns */
#define FAKTOR 2 /* multiplicator for col. elem. */
static void print_matrix (int p, int q, double **mat);
int main (int argc, char *argv[])
{
int ntasks, /* number of parallel tasks */
mytid, /* my task id */
namelen, /* length of processor name */
i, j, /* loop variables */
tmp; /* temporary value */
double matrix[P][Q],
column[2];
MPI_Datatype coltype;
MPI_Init (&argc, &argv);
MPI_Comm_rank (MPI_COMM_WORLD, &mytid);
MPI_Comm_size (MPI_COMM_WORLD, &ntasks);
/* check that we have the correct number of processes in our universe */
if (mytid == 0)
{
if (ntasks != Q)
{
printf ("\n\nWe need exactly %d processes.\n"
"Usage: mpirun -w -np %d N %s\n\n\n",
Q, Q, argv[0]);
}
}
if (ntasks != Q)
{
MPI_Finalize ();
exit (EXIT_FAILURE);
}
/* build the new type for a strided vector */
MPI_Type_vector (2, 1, Q, MPI_DOUBLE, &coltype);
MPI_Type_commit (&coltype);
if (mytid == 0)
{
tmp = 1;
for (i = 0; i < P; ++i) /* initialize matrix */
{
for (j = 0; j < Q; ++j)
{
matrix[i][j] = tmp++;
}
}
printf ("\n\noriginal matrix:\n\n");
print_matrix (P, Q, (double **) matrix);
}
/* distribute columns */
MPI_Scatter (matrix, 1, coltype, column, 2, MPI_DOUBLE, 0,
MPI_COMM_WORLD);
printf ("rank: %d c0: %g c1: %g\n", mytid, column[0], column[1]);
for (i = 0; i < 2; ++i)
{
if ((mytid % 2) == 0)
{
column[i] = column[i] * column[i];
}
else
{
column[i] = column[i] * FAKTOR;
}
}
/* wait for result vectors */
MPI_Gather (column, 2, MPI_DOUBLE, matrix, 1, coltype, 0,
MPI_COMM_WORLD);
if (mytid == 0)
{
printf ("\n\nresult matrix:\n"
"(odd columns: elements squared; even columns: elements "
"multiplied with %d)\n\n", FAKTOR);
print_matrix (P, Q, (double **) matrix);
}
MPI_Type_free (&coltype);
MPI_Finalize ();
return EXIT_SUCCESS;
}
/* print the values of a matrix
*
* input parameters: p number of rows
* q number of columns
* mat 2D-matrix of "double" values
* output parameters: none
* return value: none
* side effects: none
*
*/
void print_matrix (int p, int q, double **mat)
{
int i, j; /* loop variables */
for (i = 0; i < p; ++i)
{
for (j = 0; j < q; ++j)
{
printf ("%6g", *((double *) mat + i * q + j));
}
printf ("\n");
}
printf ("\n");
}
