From: Nick Piggin <nickpiggin@yahoo.com.au>
To: Pekka J Enberg <penberg@cs.Helsinki.FI>
Cc: "Kyle Moffett" <mrmacman_g4@mac.com>,
"Bart Hartgers" <bart@etpmod.phys.tue.nl>,
"Jörn Engel" <joern@wohnheim.fh-wedel.de>,
"Arjan van de Ven" <arjan@infradead.org>,
"Hua Zhong" <hzhong@gmail.com>,
linux-kernel@vger.kernel.org, akpm@osdl.org
Subject: Re: [PATCH] likely cleanup: remove unlikely for kfree(NULL)
Date: Thu, 27 Apr 2006 16:37:36 +1000 [thread overview]
Message-ID: <445066B0.1010104@yahoo.com.au> (raw)
In-Reply-To: <Pine.LNX.4.58.0604270928170.20454@sbz-30.cs.Helsinki.FI>
Pekka J Enberg wrote:
> On Wed, 26 Apr 2006, Kyle Moffett wrote:
>
>>Here's code that I've found works as well as can be expected under both GCC 3
>>and GCC 4. If xp is a known-NULL constant the whole function will be
>>optimized out completely. If xp is known-not-NULL, then it will optimize to a
>>kfree function without the null check. Otherwise it optimizes to call the
>>out-of-line version.
>
>
> Wouldn't it be better to simply remove calls to kfree() with known
> NULL constant?
Yes, but this will optimise away the check for known non-NULL.
At the cost of icache footprint.
I think unmeasurable micro-optimisations that go against historic
CPU trends (eg. size for speed) aren't worth wasting too much
sleep over. If it is a 0.0001% speedup today, it'll be a 0.0001%
slowdown tomorrow :)
--
SUSE Labs, Novell Inc.
Send instant messages to your online friends http://au.messenger.yahoo.com
next prev parent reply other threads:[~2006-04-27 6:47 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-04-25 18:21 Hua Zhong
2006-04-26 7:30 ` Pekka Enberg
2006-04-26 7:53 ` Andreas Mohr
2006-04-26 7:58 ` Arjan van de Ven
2006-04-26 8:16 ` Pekka J Enberg
2006-04-26 8:27 ` Arjan van de Ven
2006-04-26 10:05 ` Adrian Bunk
2006-04-26 10:05 ` Jörn Engel
2006-04-26 10:08 ` Arjan van de Ven
2006-04-26 10:57 ` Pekka J Enberg
2006-04-26 11:03 ` Arjan van de Ven
2006-04-26 11:06 ` Jörn Engel
2006-04-26 11:37 ` Bart Hartgers
2006-04-26 13:04 ` Bart Hartgers
2006-04-26 19:07 ` Kyle Moffett
2006-04-27 6:28 ` Pekka J Enberg
2006-04-27 6:37 ` Nick Piggin [this message]
2006-04-27 8:17 ` Bart Hartgers
2006-04-27 15:23 ` Kyle Moffett
2006-04-26 14:11 ` Pekka J Enberg
2006-04-27 5:54 ` Pekka J Enberg
2006-04-27 6:17 ` Nick Piggin
2006-04-27 6:28 ` Pekka J Enberg
2006-04-27 6:50 ` Arjan van de Ven
2006-04-27 8:31 ` Adrian Bunk
2006-04-27 8:41 ` Arjan van de Ven
2006-04-27 8:56 ` Adrian Bunk
2006-04-27 9:08 ` Arjan van de Ven
2006-04-27 11:41 ` Bart Hartgers
2006-04-27 18:23 ` Adrian Bunk
2006-04-27 18:29 ` Arjan van de Ven
2006-04-26 11:05 ` Nick Piggin
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=445066B0.1010104@yahoo.com.au \
--to=nickpiggin@yahoo.com.au \
--cc=akpm@osdl.org \
--cc=arjan@infradead.org \
--cc=bart@etpmod.phys.tue.nl \
--cc=hzhong@gmail.com \
--cc=joern@wohnheim.fh-wedel.de \
--cc=linux-kernel@vger.kernel.org \
--cc=mrmacman_g4@mac.com \
--cc=penberg@cs.Helsinki.FI \
/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
Powered by JetHome