On Thu, 23 Aug 2007 21:29:41 +0200, Segher Boessenkool said:
> int f(atomic_t *x)
> {
> return atomic_read(x) + atomic_read(x);
> }
> ld r0,@r0
> slli r0,#1
> jmp lr
Looks like peephole optimization at work.
Attachment:
pgp3JI5wgyWMo.pgp
Description: PGP signature
- References:
- [PATCH 0/23] make atomic_read() and atomic_set() behavior consistent across all architectures
- From: Chris Snook <csnook@redhat.com>
- [PATCH 11/23] make atomic_read() and atomic_set() behavior consistent on m32r
- From: Chris Snook <csnook@redhat.com>
- Re: [PATCH 11/23] make atomic_read() and atomic_set() behavior consistent on m32r
- From: Hirokazu Takata <takata@linux-m32r.org>
- Re: [PATCH 11/23] make atomic_read() and atomic_set() behavior consistent on m32r
- From: Hirokazu Takata <takata@linux-m32r.org>
- Re: [PATCH 11/23] make atomic_read() and atomic_set() behavior consistent on m32r
- From: Chris Snook <csnook@redhat.com>
- Re: [PATCH 11/23] make atomic_read() and atomic_set() behavior consistent on m32r
- From: Segher Boessenkool <segher@kernel.crashing.org>
- Re: [PATCH 11/23] make atomic_read() and atomic_set() behavior consistent on m32r
- From: Linus Torvalds <torvalds@linux-foundation.org>
- Re: [PATCH 11/23] make atomic_read() and atomic_set() behavior consistent on m32r
- From: Segher Boessenkool <segher@kernel.crashing.org>
- [PATCH 0/23] make atomic_read() and atomic_set() behavior consistent across all architectures
- Prev by Date: RE: "double" hpet clocksource && hard freeze [bisected]
- Next by Date: Re: x86_64-dynticks-disable-hpet_id_legsup-hpets.patch hangs the system
- Previous by thread: RE: [PATCH 11/23] make atomic_read() and atomic_set() behavior consistent on m32r
- Next by thread: Re: [PATCH 11/23] make atomic_read() and atomic_set() behavior consistent on m32r
- Index(es):
 |