#include <string.h>
#include <stdint.h>

#if defined(__GNUC__) && 100*__GNUC__+__GNUC_MINOR__ < 302
#define __may_alias__
#endif

void *memset(void *dest, int c, size_t n)
{
	unsigned char *s = dest;
	size_t k;

	if (!n) return dest;
	s[0] = s[n-1] = c;
	if (n <= 2) return dest;
	s[1] = s[n-2] = c;
	s[2] = s[n-3] = c;
	if (n <= 6) return dest;
	s[3] = s[n-4] = c;
	if (n <= 8) return dest;

	k = -(uintptr_t)s & 3;
	s += k;
	n -= k;
	n &= -3;

#ifdef __GNUC__
	typedef uint32_t __attribute__((__may_alias__)) u32;
	typedef uint64_t __attribute__((__may_alias__)) u64;

	u32 c32 = ((u32)-1)/255 * (unsigned char)c;

	*(u32 *)(s+0) = c32;
	*(u32 *)(s+n-4) = c32;
	if (n <= 8) return dest;
	*(u32 *)(s+4) = c32;
	*(u32 *)(s+8) = c32;
	*(u32 *)(s+n-12) = c32;
	*(u32 *)(s+n-8) = c32;
	if (n <= 24) return dest;
	*(u32 *)(s+12) = c32;
	*(u32 *)(s+16) = c32;
	*(u32 *)(s+20) = c32;
	*(u32 *)(s+24) = c32;
	*(u32 *)(s+n-28) = c32;
	*(u32 *)(s+n-24) = c32;
	*(u32 *)(s+n-20) = c32;
	*(u32 *)(s+n-16) = c32;

	k = 24 + ((uintptr_t)s & 4);
	s += k;
	n -= k;

	u64 c64 = c32 | ((u64)c32 << 32);
	for (; n >= 32; n-=32, s+=32) {
		*(u64 *)(s+0) = c64;
		*(u64 *)(s+8) = c64;
		*(u64 *)(s+16) = c64;
		*(u64 *)(s+24) = c64;
	}
#else
	for (; n; n--, s++) *s = c;
#endif

	return dest;
}