------- Comment #3 from jb at gcc dot gnu dot org 2006-11-04 21:24 -------
Well, redoing the C benchmark above to use 1d arrays and manual index
calculations, the results are now essentially the same as for the Fortran
version. And a commercial compiler produces about the same results for the
Fortran version as gfortran, which means the reason for our poor complex matmul
performance lies elsewhere.
#include <stdio.h>
#include <stdlib.h>
#include <complex.h>
#include <sys/time.h>
#include <time.h>
int main(void)
{
int n = 300;
complex float *a, *b, *c;
int i, j, k, tc;
a = malloc (n*n * sizeof (*a));
b = malloc (n*n * sizeof (*b));
c = malloc (n*n * sizeof (*c));
struct timeval tv, tv2;
float res;
FILE *fp;
tc = 0;
for (i = 0; i < n*n; i++)
{
a[i] = i*10.0 + 100.0*I;
b[i] = 1.0 + 42.0*I;
c[i] = 0.0 + 0.0*I;
}
gettimeofday (&tv, NULL);
for (i = 0; i < n; i++)
{
for (j = 0; j < n; j++)
{
c[i*n + j] = 0.0 + 0.0*I;
for (k = 0; k < n; k++)
{
c[i*n + j] = c[i*n + j] + a[i*n + k] * b[k*n + j];
tc++;
}
}
}
gettimeofday (&tv2, NULL);
res = tv2.tv_sec - tv.tv_sec + (tv2.tv_usec - tv.tv_usec) / 1000000.0;
printf ("gemm time: %f\n", res);
fp = fopen ("c-matrix", "w");
for (i = 0; i < n; i++)
{
for (j = 0; j<n; j++)
{
fprintf (fp, "%f ", c[i*n + j]);
}
fprintf (fp, "\n");
}
fclose (fp);
printf ("trip count: %i\n", tc);
}
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=29549
