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

#define unlikely(x)	__builtin_expect(!!(x), 0)

static inline int find_first_bit(const unsigned long *addr, unsigned size)
{
	int d0, d1;
	int res;

	/* This looks at memory. Mark it volatile to tell gcc not to move it around */
	__asm__ __volatile__(
		"xorl %%eax,%%eax\n\t"
		"repe; scasl\n\t"
		"jz 1f\n\t"
		"leal -4(%%edi),%%edi\n\t"
		"bsfl (%%edi),%%eax\n"
		"1:\tsubl %%ebx,%%edi\n\t"
		"shll $3,%%edi\n\t"
		"addl %%edi,%%eax"
		:"=a" (res), "=&c" (d0), "=&D" (d1)
		:"1" ((size + 31) >> 5), "2" (addr), "b" (addr) : "memory");
	return res;
}

static inline unsigned long __ffs(unsigned long word)
{
	__asm__("bsfl %1,%0"
		:"=r" (word)
		:"rm" (word));
	return word;
}

static inline int sched_find_first_bit(const unsigned long *b)
{
	if (unlikely(b[0]))
		return __ffs(b[0]);
	if (unlikely(b[1]))
		return __ffs(b[1]) + 32;
	if (unlikely(b[2]))
		return __ffs(b[2]) + 64;
	if (b[3])
		return __ffs(b[3]) + 96;
	return __ffs(b[4]) + 128;
}

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

#define rdtsc(low,high) \
	     __asm__ __volatile__("rdtsc" : "=a" (low), "=d" (high))

static unsigned long array[5];

#define ITER 1000000 /* 1,000,000 times */

void testit(unsigned long *array, unsigned long long clock)
{
	unsigned long long s1;
	unsigned long long e1;
	unsigned long long s2;
	unsigned long long e2;
	unsigned long long t1;
	unsigned long long t2;
	double f1;
	double f2;
	int i;
	int x;
	
	rdtscll(s1);
	for (i=0; i < ITER; i++) 
		x = find_first_bit(array,140);
	rdtscll(e1);

	rdtscll(s2);
	for (i=0; i < ITER; i++) 
		x = sched_find_first_bit(array);
	rdtscll(e2);
	
	t1 = e1 - s1;
	t2 = e2 - s2;
	f1 = (float)t1 / (float)clock;
	f2 = (float)t2 / (float)clock;

	/*
	 * Since ITER is 1,000,000 the times will be in us.
	 */
	printf("generic ffb: %08lx:%08lx\n",
			(unsigned long)(t1>>32),(unsigned long)t1);
	printf("time: %.09fus\n",f1);
			
	printf("sched ffb: %08lx:%08lx\n",
			(unsigned long)(t2>>32),(unsigned long)t2);
	printf("time: %.09fus\n",f2);
}

int main(int argc, char **argv)
{
	unsigned long long s;
	unsigned long long e;
	unsigned long long t;
	unsigned long long clock;

	/*
	 * Calculate BS time, just to get an 
	 * idea of the tsc speed.
	 */
	rdtscll(s);
	sleep(8);
	rdtscll(e);
	
	t = e - s;
	t >>= 3;
	printf("clock speed = %08lx:%08lx %llu ticks per second\n",
			(unsigned long)(t>>32),(unsigned long)t,
			t);
	clock = t;

	array[4] = 0x80000000;
	printf("last bit set\n");
	testit(array,clock);

	array[0] = 0x00000001;
	printf("\nfirst bit set\n");
	testit(array,clock);
	
	exit(0);
}