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


//
//  Inline ix86 memcpy() that contains no jumps. Not copied from
//  anybody.	Contributed by rjohnson@analogic.com
//

static __inline__ void *memcpy(void *dst, void *src, size_t len) {
        void *ret = dst;
        __asm__ __volatile__(	\
	"cld\n"			\
	"shr $1, %%ecx\n"	\
	"pushf\n"		\
	"shr $1, %%ecx\n"	\
	"pushf\n"		\
	"rep\n"			\
	"movsl\n"		\
	"popf\n"		\
	"adcl %%ecx, %%ecx\n"	\
	"rep\n"			\
	"movsw\n"		\
	"popf\n"		\
	"adcl %%ecx, %%ecx\n"	\
	"rep\n"			\
	"movsb\n"		\
	: "=D" (dst), "=S" (src), "=c"(len)
	: "0"  (dst), "1"  (src), "2" (len)
	: "memory" );
    return ret;
}


const char tester[]=	"0123456789"
			"0123456789"
			"0123456789"
			"0123456789"
			"0123456789"
			"0123456789"
			"0123456789"
			"0123456789";
char allocated[0x1000];

int main()
{
    size_t i;
    char buf[0x1000];

    memset(buf, 0x00, sizeof(buf));
    for(i=0; i< sizeof(buf); i++)
        puts(memcpy(buf, (char *)tester, i));
    memset(buf, 0x00, sizeof(buf));
    for(i=0; i< sizeof(buf)-1; i++)
        puts(memcpy(&buf[1], (char *)tester, i));
    memset(buf, 0x00, sizeof(buf));
    for(i=0; i< sizeof(buf)-2; i++)
        puts(memcpy(&buf[2], (char *)tester, i));
    memset(buf, 0x00, sizeof(buf));
    for(i=0; i< sizeof(buf)-3; i++)
        puts(memcpy(&buf[3], (char *)tester, i));
    return 0;
}