memcpy asm for i386 and x86_64

src/string/i386/memcpy.s

+.global memcpy
+.type memcpy,@function
+memcpy:
+	push %esi
+	push %edi
+	mov 12(%esp),%edi
+	mov 16(%esp),%esi
+	mov 20(%esp),%ecx
+	mov %edi,%eax
+	cmp $4,%ecx
+	jc 1f
+	test $3,%edi
+	jz 1f
+2:	movsb
+	dec %ecx
+	test $3,%edi
+	jnz 2b
+1:	mov %ecx,%edx
+	shr $2,%ecx
+	rep
+	movsl
+	and $3,%edx
+	jz 1f
+2:	movsb
+	dec %edx
+	jnz 2b
+1:	pop %edi
+	pop %esi
+	ret

src/string/x86_64/memcpy.s

+.global memcpy
+.type memcpy,@function
+memcpy:
+	mov %rdi,%rax
+	cmp $8,%rdx
+	jc 1f
+	test $7,%edi
+	jz 1f
+2:	movsb
+	dec %rdx
+	test $7,%edi
+	jnz 2b
+1:	mov %rdx,%rcx
+	shr $3,%rcx
+	rep
+	movsq
+	and $7,%edx
+	jz 1f
+2:	movsb
+	dec %edx
+	jnz 2b
+1:	ret