Re: [LAD] vectorization

Jussi! Could you try this out with your proposed compiler options on your own hardware? Admittedly, the recycled PIII here is very unrepresentative, outdated and old-skool (although it seems to shine when paired up with icc :) --8<----------------------------- // include everything just in case we need it ... #include <unistd.h> #include <stdio.h> #include <sched.h> #include <time.h> #include <stdlib.h> #define N 1024 #include <complex.h> float // complex ffta[N][2] __attribute__ ((aligned(16))), fftb[N][2] __attribute__ ((aligned(16))), data[N][2] __attribute__ ((aligned(16))); _Complex float cxA[N] __attribute__ ((aligned(16))), cxB[N] __attribute__ ((aligned(16))), cxD[N] __attribute__ ((aligned(16))) ; typedef struct { float r[N] __attribute__ ((aligned(16))); float i[N] __attribute__ ((aligned(16))); } cvec_t; cvec_t cA,cB,cD; int main() { int n = 1000000; int i,j; char* s; clock_t clk = clock(); s = "(_Complex)"; for (j = 0; j < n; ++j) for (i = 0;i < N; ++i) cxD[i]+= cxA[i]*cxB[i]; fprintf (stderr,"> clock: %d ms %s\n",(clock()-clk)/1000,s); s = "(cvec_t)"; clk = clock(); for (j = 0; j < n; ++j) for (i = 0;i < N; ++i) { cD.r[i] += cA.r[i] * cB.r[i] - cA.i[i] * cB.i[i]; cD.i[i] += cA.r[i] * cB.i[i] + cA.i[i] * cB.r[i]; } fprintf (stderr,"> clock: %d ms %s\n",(clock()-clk)/1000,s); s = "(original float array[N][2])"; clk = clock(); for (j = 0; j < n ; ++j) for (i = 0; i <N; ++i) { data [i][0] += ffta [i][0] * fftb [i][0] - ffta [i][1] * fftb [i][1]; data [i][1] += ffta [i][0] * fftb [i][1] + ffta [i][1] * fftb [i][0]; } fprintf (stderr,"> clock: %d ms %s\n",(clock()-clk)/1000,s); return 0; } On Mon, 2008-05-05 at 19:15 +0300, Jussi Laako wrote: --