When using -O>=1, gcc uses the wrong register for the inline assembly below. In my actual usecase, it even does
	bswap %eax
	xorl %eax, %eax
so it instantly threw away the value. When using -m32, it seems to generate correct code. 

== CODE FILES ==
asgard:/tmp$ cat x.c
#include <stdint.h>

uint32_t
x()
{
	return 0x11223344;
}
asgard:/tmp$ cat test.c
#include <stdint.h>
#include <stdio.h>

extern uint32_t x();

static inline __attribute__((always_inline))
bswap32(uint32_t i)
{
	asm("bswap %0" : "=q"(i) : "q"(i));
	return i;
}

int
main()
{
	printf("%08X\n", bswap32(x()));
	return 0;
}

== OUTPUT ==
asgard:/tmp$ gcc test.c x.c
asgard:/tmp$ ./a.out 
44332211
asgard:/tmp$ gcc -O1 test.c x.c
asgard:/tmp$ ./a.out 
381E625D

== ASSEMBLY OUTPUT (only important parts) ==
asgard:/tmp$ gcc -S test.c
asgard:/tmp$ cat test.s
[…]
	movl	$0, %eax
	call	x
	movl	%eax, -4(%rbp)
	movl	-4(%rbp), %eax
#APP
# 9 "test.c" 1
	bswap %eax
# 0 "" 2
#NO_APP
	movl	%eax, -4(%rbp)
	movl	-4(%rbp), %eax
	movl	%eax, %edx
	movl	$.LC0, %eax
	movl	%edx, %esi
	movq	%rax, %rdi
	movl	$0, %eax
	call	printf
[…]
asgard:/tmp$ gcc -S -O1 test.c
asgard:/tmp$ cat test.s       
[…]
	movl	$0, %eax
	call	x
#APP
# 9 "test.c" 1
	bswap %edx
# 0 "" 2
#NO_APP
	movl	$.LC0, %esi
	movl	$1, %edi
	movl	$0, %eax
	call	__printf_chk
[…]