[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20070604222010.GA1169@Krystal>
Date: Mon, 4 Jun 2007 18:20:10 -0400
From: Mathieu Desnoyers <mathieu.desnoyers@...ymtl.ca>
To: Andi Kleen <andi@...stfloor.org>,
Nicholas Mc Guire <mcguire@....edu.cn>
Cc: akpm@...ux-foundation.org, linux-kernel@...r.kernel.org
Subject: Re: [patch 9/9] Scheduler profiling - Use conditional calls
* Andi Kleen (andi@...stfloor.org) wrote:
> > I see your point, but there is a level of control on the branch I would
> > lack by doing so: the ability to put the call in either the if or else
> > branch. It is an optimization on i386.
>
> What does it optimize exactly?
>
Nicholas McGuire told me that the non common cases should be put in
else branches of if statements for i386. At the time, I did a quick test
that correlated what he said, but I seem to be unable to reproduce this
behavior now (maybe my code snippet is too simple?): I will then assume
that the likely/unlikely (builtin expects) tells everything that is
needed to gcc until further notice. Therefore, we can use the form :
if (cond_call(var)), as you proposed.
> > Also, I live in the expectation that, someday, the gcc guys will be nice
> > enough to add some kind of support for a nop-based jump that would
> > require code patching to put a jump instead. If it ever happens, my
> > macro could evolve into this for newer compiler versions, which I could
> > not do with the if() statement you are proposing.
>
> If that ever happens we couldn't use it anyways because Linux still
> has to support old compilers for a long time. And when those are dropped the
> code could be updated.
>
Agreed.
--
Mathieu Desnoyers
Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists