#include <stdlib.h>
#include <stdio.h>
#include <time.h>
#include <pthread.h>
#include <unistd.h>
#include <stdlib.h>

#define rdtscll(val) \
     __asm__ __volatile__ ("rdtsc;" : "=A" (val))

#define SECS 3ULL

volatile unsigned int count_array[1000] __attribute__((aligned(256)));
int atomic = 0;
unsigned long long delta = 0;

void *loop(void *arg)
{
	unsigned long long start, now, mhz = 525000000, limit = mhz * SECS,
		min = -1ULL, tmp;
	volatile unsigned int *count, offset = (int)arg;
	int j;

	printf("offset: %u (atomic: %d).\n", offset, atomic);
	count = (void *)count_array + offset;

	if (!arg) {
		for (j = 0; j < 10; j++) {
			limit = mhz/10;
			*count = 0;
			rdtscll(start);
			for (;;) {
				(*count)++;
				rdtscll(now);
				if (now - start > limit)
					break;
			}
			rdtscll(now);
			tmp = (now-start)/(*count);
			if (tmp < min)
				min = tmp;
		}
		printf("delta: %Ld\n", min);
		delta = min;
	} else
		while (!delta)
			usleep(100000);
	limit = mhz*SECS;

repeat:
	*count = 0;
	rdtscll(start);
	if (atomic)
		for (;;) {
			asm ("lock; incl %0" : "=m" (*count) : "m" (*count));
			rdtscll(now);
			if (now - start > limit)
				break;
		}
	else
		for (;;) {
			(*count)++;
			rdtscll(now);
			if (now - start > limit)
				break;
		}
	printf("speed: %Ld loops (%Ld cycles per iteration).\n", (*count)/SECS, (limit/(*count)-delta)); fflush(stdout);
	goto repeat;
}

int main (int argc, char **argv)
{
	unsigned int nr_threads, i, ret, offset = 0;
	pthread_t *t;

	if (argc != 2 && argc != 3 && argc != 4) {
usage:
		printf("usage: loop_print2 <nr threads> [<counter offset>] [<atomic>]\n");
		exit(-1);
	}
	nr_threads = atol(argv[1]);
	if (!nr_threads)
		goto usage;
	t = calloc(nr_threads, sizeof(*t));
	if (argc >= 3)
		offset = atol(argv[2]);
	if (offset < sizeof(unsigned int))
		offset = sizeof(unsigned int);
	atomic = 0;
	if (argc >= 4) {
		atomic = atol(argv[3]);
		printf("a: %d\n", atomic);
	}

	for (i = 1; i < nr_threads; i++) {
		ret = pthread_create (t+i, NULL, loop,
			       	(void *)(i*offset));
		if (ret)
			exit(-1);
	}
	loop((void *)0);

	return 0;
}