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

void *memcpy(void *restrict dest, const void *restrict src, size_t n)
{
	unsigned char *d = dest;
	const unsigned char *s = src;
	uint32_t w, x;

	for (; (uintptr_t)s % 8 && n; n--) *d++ = *s++;
	if (!n) return dest;

	if (n>=4) switch ((uintptr_t)d % 4) {
	case 0:
		if (!(uintptr_t)d % 8) for (; n>=8; s+=8, d+=8, n-=8)
			*(uint64_t *)d = *(uint64_t *)s;
		else for (; n>=4; s+=4, d+=4, n-=4)
			*(uint32_t *)d = *(uint32_t *)s;
		break;
	case 1:
		if (!(union { int i; char c; }){1}.c) break;
		w = *(uint32_t *)s;
		*d++ = *s++;
		*d++ = *s++;
		*d++ = *s++;
		n -= 3;
		for (; n>=17; s+=16, d+=16, n-=16) {
			x = *(uint32_t *)(s+1);
			*(uint32_t *)(d+0) = (w>>24) | (x<<8);
			w = *(uint32_t *)(s+5);
			*(uint32_t *)(d+4) = (x>>24) | (w<<8);
			x = *(uint32_t *)(s+9);
			*(uint32_t *)(d+8) = (w>>24) | (x<<8);
			w = *(uint32_t *)(s+13);
			*(uint32_t *)(d+12) = (x>>24) | (w<<8);
		}
		break;
	case 2:
		if (!(union { int i; char c; }){1}.c) break;
		w = *(uint32_t *)s;
		*d++ = *s++;
		*d++ = *s++;
		n -= 2;
		for (; n>=18; s+=16, d+=16, n-=16) {
			x = *(uint32_t *)(s+2);
			*(uint32_t *)(d+0) = (w>>16) | (x<<16);
			w = *(uint32_t *)(s+6);
			*(uint32_t *)(d+4) = (x>>16) | (w<<16);
			x = *(uint32_t *)(s+10);
			*(uint32_t *)(d+8) = (w>>16) | (x<<16);
			w = *(uint32_t *)(s+14);
			*(uint32_t *)(d+12) = (x>>16) | (w<<16);
		}
		break;
	case 3:
		if (!(union { int i; char c; }){1}.c) break;
		w = *(uint32_t *)s;
		*d++ = *s++;
		n -= 1;
		for (; n>=19; s+=16, d+=16, n-=16) {
			x = *(uint32_t *)(s+3);
			*(uint32_t *)(d+0) = (w>>8) | (x<<24);
			w = *(uint32_t *)(s+7);
			*(uint32_t *)(d+4) = (x>>8) | (w<<24);
			x = *(uint32_t *)(s+11);
			*(uint32_t *)(d+8) = (w>>8) | (x<<24);
			w = *(uint32_t *)(s+15);
			*(uint32_t *)(d+12) = (x>>8) | (w<<24);
		}
		break;
	}

	for (; n; n--) *d++ = *s++;
	return dest;
}