// Build a-la
// gcc -m32 -static -O2 -Wall memset_bench.c memset.s

#define _GNU_SOURCE
#include <sys/types.h>
#include <sys/time.h>
#include <sys/syscall.h>
#include <time.h>
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <string.h>

#define FILL 0

/* libc has incredibly messy way of doing this,
 * typically requiring -lrt. We just skip all this mess */
#ifndef CLOCK_MONOTONIC
#define CLOCK_MONOTONIC 1
#endif
static void get_mono(struct timespec *ts)
{
        syscall(__NR_clock_gettime, CLOCK_MONOTONIC, ts);
}

unsigned gett()
{
#if 0
	struct timeval tv;
	gettimeofday(&tv, NULL);
	return tv.tv_usec;
#else
	struct timespec ts;
	get_mono(&ts);
	return ts.tv_nsec;
#endif
}

unsigned difft(unsigned t2, unsigned t1)
{
	t2 -= t1;
	if ((int)t2 < 0)
		t2 += 1000000000;
	return t2;
}

void measure(unsigned sz, void *buf, void* (*m)(void *ptr, int c, size_t cnt))
{
	unsigned t1, t2, cnt;
	unsigned repeat = 1;

	/* For small sizes, call m() many times before measuring time diff */
	repeat = ((256*1024) / (sz|1)) ? : 1;

	m(buf, FILL, sz); /* warm up caches */
	m(buf, FILL, sz); /* warm up caches */

	t2 = -1U;
	cnt = 1000;
	while (--cnt) {
		unsigned rep = repeat;

		t1 = gett();
		do {
			m(buf, FILL, sz);
		} while (--rep);
		t1 = difft(gett(), t1);
		if (t2 > t1)
			t2 = t1;
	}
	printf("%u byte block: %.2f bytes/ns\n", sz, (double)(sz) * repeat / t2);
}

int main(int argc, char **argv)
{
	int sz;
	char *buf;

	sz = argv[1] ? atoi(argv[1]) : 1024;
	buf = malloc(sz + 4096);
	buf += 0x100;
	buf = (char*)((long)buf & ~0xffL);

	setlinebuf(stdout);
	printf("size:%u (%uk) buf:%p\n", sz, sz/1024, buf);

	do {
		measure(sz, buf, memset);
	} while (--sz > 0);

	return 0;
}