/*
 * $ taskset -c 3 ./nops
 * Running 600 times, 10000000 loops per run.
 * nop_0x90 average: 439.805220
 * nop_3_byte average: 442.412915
 *
 * How to run:
 *
 * taskset -c <cpunum> argv0
 */
#include <stdio.h>
#include <sys/syscall.h>
#include <stdlib.h>
#include <unistd.h>

typedef unsigned long long u64;

#define TWO(a) a; a;
#define FOUR(a) TWO(TWO(a))
#define SIXTEEN(a) FOUR(FOUR(a))
#define TWOFIVESIX(a) SIXTEEN(SIXTEEN(a))

#define DECLARE_ARGS(val, low, high)    unsigned low, high
#define EAX_EDX_VAL(val, low, high)     ((low) | ((u64)(high) << 32))
#define EAX_EDX_ARGS(val, low, high)    "a" (low), "d" (high)
#define EAX_EDX_RET(val, low, high)     "=a" (low), "=d" (high)

static __always_inline unsigned long long rdtsc(void)
{
        DECLARE_ARGS(val, low, high);

        asm volatile("rdtsc" : EAX_EDX_RET(val, low, high));

        return EAX_EDX_VAL(val, low, high);
}

static inline u64 read_tsc(void)
{
	u64 ret;

	asm volatile("mfence");
	ret = rdtsc();
	asm volatile("mfence");

	return ret;
}

static void nop_0x90(void)
{
	TWOFIVESIX(asm volatile(".byte 0x66, 0x66, 0x90"))
}

static void nop_3_byte(void)
{
	TWOFIVESIX(asm volatile(".byte 0x0f, 0x1f, 0x00"))
}

int main()
{
	int i, j;
	u64 p1, p2;
	u64 r, min;

#define TIMES 60
#define LOOPS 1000000ULL

	printf("Running %d times, %lld loops per run.\n", TIMES, LOOPS);

	min = 100000000;

	for (r = 0, j = 0; j < TIMES; j++) {
		p1 = read_tsc();
		for (i = 0; i < LOOPS; i++) {
			nop_0x90();

		}
		p2 = read_tsc();
		r = (p2 - p1);

		if (r < min)
			min = r;
	}

	printf("nop_0x90 average: %f\n", min / (double) LOOPS / 256);

	min = 100000000;

	for (r = 0, j = 0; j < TIMES; j++) {
		p1 = read_tsc();
		for (i = 0; i < LOOPS; i++) {
			nop_3_byte();
		}
		p2 = read_tsc();

		r = (p2 - p1);
		if (r < min)
			min = r;
	}

	printf("nop_3_byte average: %f\n", min / (double) LOOPS / 256);

	return 0;
}