X86: Optimise fls(), ffs() and fls64()
in [Kernel]
|
Prev: benet: Fix compile warnnings in drivers/net/benet/be_ethtool.c
Next: What are the goals for the architecture of an in-kernel IR system?
From: Avi Kivity on 15 Apr 2010 05:00 On 04/15/2010 11:48 AM, David Howells wrote: > Avi Kivity<avi(a)redhat.com> wrote: > > >> Even if Intel processors behave that way, other processors (real and >> emulated) use those manuals as a specification. Emulated processors are >> unlikely to touch an undefined register, but real processors may. >> >> (qemu tcg appears not to touch the output) >> > Possibly because the AMD64 spec specifies that the destination will be > unchanged if the source was 0. > Likely. But we haven't tested all current and future x86 clones, and they may be based off the Intel documentation instead of the AMD documentation. -- I have a truly marvellous patch that fixes the bug which this signature is too narrow to contain. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Jamie Lokier on 15 Apr 2010 07:50
Avi Kivity wrote: > Likely. But we haven't tested all current and future x86 clones, and > they may be based off the Intel documentation instead of the AMD > documentation. I wonder about that too. I got the impression Transmeta did lots of testing real x86s in all sorts of corner cases, because the manuals don't cover everything that the broad base of software depends on in practice. Clone makers have to do it to a much higher standard than emulators because you can't generally release patches... I think Via (including whatever the CPU line was formerly called) have been bitten a few times by not quite matching software expectations. Even Intel was caught on x86_64 at the beginning by slight differences when they cloned AMD's design :-) -- Jamie -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ |