#define _XOPEN_SOURCE 700
#include <stdio.h>
#include <time.h>
#include <stdlib.h>
#include <string.h>

static inline unsigned rdtsc()
{
#if defined __i386__ || defined __x86_64__
	unsigned x;
	__asm__ __volatile__ ( "rdtsc" : "=a"(x) : : "rdx" );
//	__asm__ __volatile__ ( "cpuid ; rdtsc" : "=a"(x)
//		: : "rbx", "rcx", "rdx" );
	return x;
#else
	struct timespec ts;
	clock_gettime(CLOCK_PROCESS_CPUTIME_ID, &ts);
	return ts.tv_nsec;
#endif
}

char buf[32768+100];

int main()
{
	unsigned a=0;
	unsigned i, j, t, tmin=-1;
	unsigned long long tmean=0;
	unsigned overhead = -1;
	size_t n;

	for (i=0; i<0+1*4096; i++) {
		t = rdtsc();
		__asm__ __volatile__("nop");
		t = rdtsc()-t;
		if (t < overhead) overhead = t;
	}
	//overhead = 0;

	for (n=2; n<32768; n+=(n<64 ? 2 : n<512 ? 32 : n)) {
		tmin = -1;
		tmean = 0;
		for (i=0; i<0+1*4096; i++) {
			__asm__ __volatile__ ("" : : : "memory");
			t = rdtsc();
			for (j=0; j<64; j++) {
				memset(buf, 0, n);
				__asm__ __volatile__ ("" : : : "memory");
			}
			t = rdtsc()-t;
			__asm__ __volatile__ ("" : : : "memory");
			if (t < tmin) tmin = t;
			tmean += t;
		}
		tmin -= overhead;
		tmean -= 4096*overhead;
		tmin /= 64;
		tmean /= 64;
		tmean /= 4096;
		printf("size %zu: min=%u, avg=%llu\n", n, tmin, tmean);
	}
}