From: Jamie Lokier <jamie@shareable.org>
To: Willy Tarreau <willy@w.ods.org>
Cc: Albert Cahalan <albert@users.sourceforge.net>,
linux-kernel mailing list <linux-kernel@vger.kernel.org>,
davem@redhat.com, chip@pobox.com
Subject: Re: [PATCH] 2.4.22pre10: {,un}likely_p() macros for pointers
Date: Mon, 11 Aug 2003 05:55:31 +0100 [thread overview]
Message-ID: <20030811045531.GH10446@mail.jlokier.co.uk> (raw)
In-Reply-To: <20030810072945.GA14038@alpha.home.local>
Willy Tarreau wrote:
> > I looked at the assembly (ppc, gcc 3.2.3) and didn't
> > see any overhead.
>
> same here on x86, gcc-2.95.3 and gcc-3.3.1. The compiler is smart enough not
> to add several intermediate tests for !!(x).
What I recall is no additional tests, but the different forms affected
the compilers choice of instructions on x86, making one form better
than another. Unfortunately I don't recall what that was, or what
test it showed up in :(
> I agree (I didn't think about pointers, BTW). But what I meant is that we
> don't need the result to be precisely 1, but we need it to be something the
> compiler interpretes as different from zero, to match the condition. So it
> should be cleaner to always check against 0 which is also OK for pointers,
> whatever their type (according to Chip's link) :
>
> likely => __builtin_expect(!(x), 0)
This will break "if (likely(p)) { ... }"
> unlikely => __builtin_expect((x), 0)
This will give a warning with "if (unlikely(p)) { ... }"
-- Jamie
next prev parent reply other threads:[~2003-08-11 4:55 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-08-10 4:03 [PATCH] 2.4.22pre10: {,un}likely_p() macros for pointers Albert Cahalan
2003-08-10 7:29 ` Willy Tarreau
2003-08-10 8:02 ` Willy Tarreau
2003-08-11 1:23 ` Chip Salzenberg
2003-08-11 2:09 ` Jamie Lokier
2003-08-11 2:39 ` Chip Salzenberg
2003-08-11 4:02 ` Albert Cahalan
2003-08-11 4:30 ` Jamie Lokier
2003-08-11 5:30 ` Willy Tarreau
2003-08-11 5:42 ` Jamie Lokier
2003-08-11 13:09 ` Albert Cahalan
2003-08-11 18:55 ` Andrew Morton
2003-08-11 23:13 ` Albert Cahalan
2003-08-13 19:42 ` Jamie Lokier
2003-08-11 4:55 ` Jamie Lokier [this message]
2003-08-11 5:26 ` Willy Tarreau
2003-08-11 5:38 ` Jamie Lokier
-- strict thread matches above, loose matches on Subject: below --
2003-08-05 12:44 Albert Cahalan
2003-08-09 0:21 ` Jamie Lokier
2003-08-09 8:13 ` Willy Tarreau
2003-08-09 8:51 ` David S. Miller
2003-08-09 9:36 ` Jamie Lokier
2003-08-09 10:10 ` Herbert Xu
2003-08-09 10:42 ` Alan Cox
2003-08-09 16:23 ` Jamie Lokier
2003-08-04 17:06 Chip Salzenberg
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=20030811045531.GH10446@mail.jlokier.co.uk \
--to=jamie@shareable.org \
--cc=albert@users.sourceforge.net \
--cc=chip@pobox.com \
--cc=davem@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=willy@w.ods.org \
/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;
as well as URLs for NNTP newsgroup(s).