#include <stdlib.h>
#include <stdio.h>

#include <sys/io.h>

#define LOOPS 1000

unsigned long cycles[LOOPS];

int main(void)
{
	unsigned long overhead;
	unsigned long total;
	int i;

	if (iopl(3) < 0) {
		perror("iopl");
		return EXIT_FAILURE;
	}

	/* pull it in */
	for (i = 0; i < LOOPS; i++)
		cycles[i] = 0;

	asm volatile ("cli");
	for (i = 0; i < LOOPS; i++)
		asm (
			"xor	%%eax, %%eax	\n\t"
			"cpuid			\n\t"	
			"rdtsc			\n\t"
			"movl	%%eax, %%esi	\n\t"	
			"xor	%%eax, %%eax	\n\t"
			"cpuid			\n\t"
			"rdtsc			\n\t"
			"subl	%%esi, %%eax	\n\t"

			: "=a" (cycles[i]) : : "ecx", "edx", "ebx", "esi");
	asm volatile ("sti");

	overhead = 0;
	for (i = 0; i < LOOPS; i++)
		overhead += cycles[i];

	asm volatile ("cli");
	for (i = 0; i < LOOPS; i++)
		asm (
			"xor	%%eax, %%eax	\n\t"
			"cpuid			\n\t"	
			"rdtsc			\n\t"
			"movl	%%eax, %%esi	\n\t"	
			"outb	%%al, $0x80	\n\t"
			"xor	%%eax, %%eax	\n\t"
			"cpuid			\n\t"
			"rdtsc			\n\t"
			"subl	%%esi, %%eax	\n\t"

			: "=a" (cycles[i]) : : "ecx", "edx", "ebx", "esi");
	asm volatile ("sti");

	total = 0;
	for (i = 0; i < LOOPS; i++)
		total += cycles[i];
	total -= overhead;

	printf("out: %lu\n", total / LOOPS);

	asm volatile ("cli");
	for (i = 0; i < LOOPS; i++)
		asm (
			"xor	%%eax, %%eax	\n\t"
			"cpuid			\n\t"	
			"rdtsc			\n\t"
			"movl	%%eax, %%esi	\n\t"	
			"inb	$0x80, %%al	\n\t"
			"xor	%%eax, %%eax	\n\t"
			"cpuid			\n\t"
			"rdtsc			\n\t"
			"subl	%%esi, %%eax	\n\t"

			: "=a" (cycles[i]) : : "ecx", "edx", "ebx", "esi");
	asm volatile ("sti");

	total = 0;
	for (i = 0; i < LOOPS; i++)
		total += cycles[i];
	total -= overhead;

	printf("in : %lu\n", total / LOOPS);

	return EXIT_SUCCESS;
}