Hi Miroslav
I tested following C Code by TSM320C55x
it spend time about 45 second
so i guess the AM335X is better :)
void NeonTest(float * a, float * b, float * z)
{
int i;
for(i=0;i<200;i++) {
z[i] = a[i] * b[i];
}
}
for(j=0;j<500000;j++)
{
NeonTest(&a,&b,&z);
}
===============================================================
Running on OMAP3EVM under Linux with a Cortex-A8 clock speed of 600MHz
VFP | 7.36 seconds |
Neon | 0.94 seconds |