Reverse Engineering challenge #13.

What does this SSE code do?

Optimizing GCC 4.8.2:


f:
	xor	rax, rax
.L4:
	movdqu	xmm0, XMMWORD PTR [rsi+rax]
	movdqu	xmm1, XMMWORD PTR [rdx+rax]
	pmaxub	xmm0, xmm1
	movdqu	XMMWORD PTR [rdi+rax], xmm0
	add	rax, 16
	cmp	rax, 1024
	jne	.L4
	rep ret

More challenges: //challenges.re/; about solutions: //challenges.re/#Solutions.