Date: Thu, 18 Mar 2010 19:43:57 -0600 From: Scott Long <scottl@samsco.org> To: "M. Warner Losh" <imp@bsdimp.com> Cc: max@love2party.net, rwatson@FreeBSD.org, freebsd-arch@FreeBSD.org Subject: Re: likely and unlikely Message-ID: <15D5A6D4-1594-4667-AE51-0E26950C81DA@samsco.org> In-Reply-To: <20100318.165725.480410072667175878.imp@bsdimp.com> References: <alpine.BSF.2.00.1003131346270.51476@fledge.watson.org> <20100318.161117.658811636873842325.imp@bsdimp.com> <DA31205F-41FA-4AC3-888E-2001210EE623@samsco.org> <20100318.165725.480410072667175878.imp@bsdimp.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Mar 18, 2010, at 4:57 PM, M. Warner Losh wrote: > In message: <DA31205F-41FA-4AC3-888E-2001210EE623@samsco.org> > Scott Long <scottl@samsco.org> writes: > : On Mar 18, 2010, at 4:11 PM, M. Warner Losh wrote: > : > In message: = <alpine.BSF.2.00.1003131346270.51476@fledge.watson.org> > : > Robert Watson <rwatson@FreeBSD.org> writes: > : > :=20 > : > : On Sat, 13 Mar 2010, Bruce Evans wrote: > : > :=20 > : > : >> My point is: Handle with care!!! Trust your compiler/CPU > : > : >> predictors/... - most of the time, they are smarter than you = are ;) > : > : > > : > : > These macros may have useful 15-25 years ago for i386, i486 = and > : > : > Pentium1, since CPU branch predictors were either nonexistent = or not > : > : > so good. After that, CPU branch predictors became quite good. = The > : > : > macros should have been mostly unused 15-25 years ago too, = since they > : > : > optimize for unreadability and unwritability. Fortunately = they are > : > : > rarely used in FreeBSD. They were imported from NetBSD in = 2003 where > : > : > they are used more (306 instances in 2005 NetBSD /sys vs 28 = instances > : > : > in 2004 FreeBSD /sys; there are 2208 instances of likely() in = 2004 > : > : > linux-2.6.10). > : > :=20 > : > : I think it would be reasonable to expect that people deploy = branch > : > : prediction macros (as with prefetch, etc) only where there's = specific > : > : measurements that indicate they are important to have there -- = at the > : > : very least, pmc data, but ideally also benchmarking data. > : >=20 > : > They are more useful on architectures where you have branches that > : > tell the CPU if they are likely or unlikely to be taken... > : >=20 > :=20 > : And that's a very good point, one that Bruce really failed to > : address. Not only is branch prediction useful for MIPS and ARM, I > : suspect that it's also useful for Atom. >=20 > The PMC work will tell us that... >=20 My understanding was that Atom wasn't super-scalar at all and has no = branch prediction or out-of-order logic. It's basically an 80486 with a = modern instruction set. Scott
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?15D5A6D4-1594-4667-AE51-0E26950C81DA>