/* compiled with -msse2, etc*/ //#include /* MMX */ //#include /* SSE */ #include /* SSE2 */ //#include /* SSE3 */ //#include /* SSSE3 */ //#include /* SSE4.2 SSE4.1 */ #include #include #include typedef unsigned long long ticks; static __inline__ ticks getticks(void) { unsigned a, d; asm("cpuid"); asm volatile("rdtsc" : "=a" (a), "=d" (d)); return (((ticks)a) | (((ticks)d) << 32)); } /* plain version x = a*x */ void sapxy(int n, float a, float *x) { int i; for (i=0; i