From: Jeremy Fitzhardinge <jeremy@goop.org>
To: Herbert Xu <herbert@gondor.apana.org.au>
Cc: dada1@cosmosbay.com, mingo@elte.hu, htejun@gmail.com,
linux-kernel@vger.kernel.org, netdev@vger.kernel.org,
joe@perches.com, rusty@rustcorp.com.au
Subject: Re: [PATCH] x86: percpu_to_op() misses memory and flags clobbers
Date: Thu, 02 Apr 2009 07:12:30 -0700 [thread overview]
Message-ID: <49D4C7CE.3060005@goop.org> (raw)
In-Reply-To: <20090402095217.GA30759@gondor.apana.org.au>
Herbert Xu wrote:
> Jeremy Fitzhardinge <jeremy@goop.org> wrote:
>
>> There's probably not a lot of value in this. The Intel and AMD
>> optimisation guides tend to deprecate inc/dec in favour of using
>> add/sub, because the former can cause pipeline stalls due to its partial
>> flags update.
>>
>
> Is this still the case on the latest Intel CPUs?
>
Yes:
Assembly/Compiler Coding Rule 32. (M impact, H generality) INC and DEC
instructions should be replaced with ADD or SUB instructions,
because ADD and
SUB overwrite all flags, whereas INC and DEC do not, therefore
creating false
dependencies on earlier instructions that set the flags.
J
next prev parent reply other threads:[~2009-04-02 14:12 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-04-01 8:13 [PATCH] x86: percpu_to_op() misses memory and flags clobbers Eric Dumazet
2009-04-01 9:02 ` Jeremy Fitzhardinge
2009-04-01 10:14 ` Eric Dumazet
2009-04-01 16:12 ` Ingo Molnar
2009-04-01 16:41 ` Jeremy Fitzhardinge
2009-04-01 16:44 ` Ingo Molnar
2009-04-01 17:13 ` Eric Dumazet
2009-04-01 18:07 ` Jeremy Fitzhardinge
2009-04-01 18:47 ` Eric Dumazet
2009-04-02 9:52 ` Herbert Xu
2009-04-02 14:12 ` Jeremy Fitzhardinge [this message]
2009-04-01 18:44 ` [RFC] percpu: convert SNMP mibs to new infra Eric Dumazet
2009-04-02 0:13 ` Tejun Heo
2009-04-02 4:05 ` Ingo Molnar
2009-04-02 8:07 ` [PATCH] " Eric Dumazet
2009-04-03 0:39 ` Tejun Heo
2009-04-03 17:10 ` Ingo Molnar
2009-04-02 5:04 ` [RFC] " Rusty Russell
2009-04-02 5:19 ` Eric Dumazet
2009-04-02 11:46 ` Rusty Russell
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=49D4C7CE.3060005@goop.org \
--to=jeremy@goop.org \
--cc=dada1@cosmosbay.com \
--cc=herbert@gondor.apana.org.au \
--cc=htejun@gmail.com \
--cc=joe@perches.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=netdev@vger.kernel.org \
--cc=rusty@rustcorp.com.au \
/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).