public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Ingo Molnar <mingo@elte.hu>
To: Steven Rostedt <rostedt@goodmis.org>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	linux-kernel@vger.kernel.org, tglx@linutronix.de,
	peterz@infradead.org, tytso@mit.edu, arjan@infradead.org,
	srostedt@redhat.com
Subject: Re: [PATCH 4/4] trace: profile all if conditionals
Date: Sun, 23 Nov 2008 13:37:30 +0100	[thread overview]
Message-ID: <20081123123730.GI29663@elte.hu> (raw)
In-Reply-To: <alpine.DEB.1.10.0811211832460.7797@gandalf.stny.rr.com>


* Steven Rostedt <rostedt@goodmis.org> wrote:

> 
> On Fri, 21 Nov 2008, Andrew Morton wrote:
> > >
> > > +#define if(cond) if (__builtin_constant_p((cond)) ? !!(cond) :		\
> > 
> > wheee...
> > 
> > Now how are you going to profile ?:, while, for(;expr;), etc? ;)

btw., there's hardware driven branch tracing and profiling in the 
works too, which captures all conditionals - including loops. Stay 
tuned :)

> I don't know. Give me a few months, I'll figure out a way ;-)

also loops generally have a more static (hence less interesting) 
prediction pattern - while for branches we frequently have a "should 
this branch be made likely/unlikely in the fastpath" question.

	Ingo

  reply	other threads:[~2008-11-23 12:38 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-11-21  7:12 [PATCH 0/4] trace: profiling branches Steven Rostedt
2008-11-21  7:12 ` [PATCH 1/4] trace: remove extra assign in branch check Steven Rostedt
2008-11-21  7:12 ` [PATCH 2/4] trace: consolidate unlikely and likely profiler Steven Rostedt
2008-11-21  7:12 ` [PATCH 3/4] trace: branch profiling should not print percent without data Steven Rostedt
2008-11-21  7:12 ` [PATCH 4/4] trace: profile all if conditionals Steven Rostedt
2008-11-21 23:20   ` Andrew Morton
2008-11-21 23:33     ` Steven Rostedt
2008-11-23 12:37       ` Ingo Molnar [this message]
2008-11-23 15:48   ` Ingo Molnar
2008-11-23 16:07     ` [PATCH] net/wireless/reg.c: fix Ingo Molnar
2008-11-23 19:43   ` [PATCH 4/4] trace: profile all if conditionals Andi Kleen
2008-11-23 19:56     ` Steven Rostedt
2008-11-23 20:24       ` Andi Kleen
2008-11-23 20:32         ` Steven Rostedt
2008-11-23 20:51           ` Andi Kleen
2008-11-23 21:38       ` Ingo Molnar
2008-11-30 10:58 ` [PATCH 0/4] trace: profiling branches Daniel Walker
2008-11-30 15:19   ` Steven Rostedt

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20081123123730.GI29663@elte.hu \
    --to=mingo@elte.hu \
    --cc=akpm@linux-foundation.org \
    --cc=arjan@infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=srostedt@redhat.com \
    --cc=tglx@linutronix.de \
    --cc=tytso@mit.edu \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox