#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 i, t, tmin;
	unsigned long long tmean;
	unsigned n;

// I need a million of iterations to get a stable "min" measurement
#define REP (1024*4096)

	for (n=2; n<32768; n+=(n<64 ? 2 : n<512 ? 32 : n)) {
		int repeat = (1024 / (n|1)) ? : 1;

		memset(buf, 0, n);
		tmin = -1;
		tmean = 0;
		for (i=0; i < REP; i++) {
			int j = repeat;
			__asm__ __volatile__ ("" : : : "memory");
			t = rdtsc();
			do {
				memset(buf, 0, n);
				__asm__ __volatile__ ("" : : : "memory");
			} while (--j != 0);
			t = rdtsc() - t;
			__asm__ __volatile__ ("" : : : "memory");
			if (t < tmin) tmin = t;
			tmean += t;
		}
		printf("size %u: min=%.2f, avg=%.2f\n",
			n,
			(double)tmin / repeat,
			(double)tmean / (repeat*REP)
		);
	}
	return 0;
}