.global memset
.type memset,@function
memset:
	mov 12(%esp),%ecx
	cmp $62,%ecx
	ja 2f

	movzbl 8(%esp),%edx
	mov 4(%esp),%eax
	test %ecx,%ecx
	jz 1f

	mov %dl,%dh

	mov %dl,(%eax)
	mov %dl,-1(%eax,%ecx)
	cmp $2,%ecx
	jbe 1f

	mov %dx,1(%eax)
	mov %dx,(-1-2)(%eax,%ecx)
	cmp $6,%ecx
	jbe 1f

	shl $8,%edx
	mov %dh,%dl
	shl $8,%edx
	mov %dh,%dl

	mov %edx,(1+2)(%eax)
	mov %edx,(-1-2-4)(%eax,%ecx)
	cmp $14,%ecx
	jbe 1f

	mov %edx,(1+2+4)(%eax)
	mov %edx,(1+2+4+4)(%eax)
	mov %edx,(-1-2-4-8)(%eax,%ecx)
	mov %edx,(-1-2-4-4)(%eax,%ecx)
	cmp $30,%ecx
	jbe 1f

	mov %edx,(1+2+4+8)(%eax)
	mov %edx,(1+2+4+8+4)(%eax)
	mov %edx,(1+2+4+8+8)(%eax)
	mov %edx,(1+2+4+8+12)(%eax)
	mov %edx,(-1-2-4-8-16)(%eax,%ecx)
	mov %edx,(-1-2-4-8-12)(%eax,%ecx)
	mov %edx,(-1-2-4-8-8)(%eax,%ecx)
	mov %edx,(-1-2-4-8-4)(%eax,%ecx)

1:	ret 	

2:	mov %edi,12(%esp)
	movzbl 8(%esp),%eax
	mov $0x01010101,%edx
	imul %edx,%eax

	mov %ecx,%edx
	lea -5(%ecx),%ecx
	mov 4(%esp),%edi
	shr $2, %ecx

	mov %eax,(%edi)
	mov %eax,-8(%edi,%edx)
	mov %eax,-4(%edi,%edx)
	add $4,%edi
	and $-4,%edi
	rep
	stosl
	mov 4(%esp),%eax
	ret