Optimized… in Assembler

OK, now for the fanatics as always: The same thing I just posted, but in assembler:

BitReverse PROC
PUSH r13

MOV rax, rcx
MOV r13, rcx
SHR rax, 1
AND rax, 0x5555555555555555
AND r13, 0x5555555555555555
SHL r13, 1
OR rax, r13

MOV r13, rax
SHR rax, 2
AND rax, 0x3333333333333333
AND r13, 0x3333333333333333
SHL r13, 2
OR rax, r13

MOV r13, rax
SHR rax, 4
AND rax, 0x0F0F0F0F0F0F0F0F
AND r13, 0x0F0F0F0F0F0F0F0F
SHL r13, 4
OR rax, r13

MOV r13, rax
SHR rax, 8
AND rax, 0x00FF00FF00FF00FF
AND r13, 0x00FF00FF00FF00FF
SHL r13, 8
OR rax, r13

MOV r13, rax
SHR rax, 16
AND rax, 0x0000FFFF0000FFFF
AND r13, 0x0000FFFF0000FFFF
SHL r13, 16
OR rax, r13

MOV r13, rax
SHR rax, 32
SHL r13, 32
OR rax, r13

POP r13

ret

BitReverse ENDP