Linux ARM-MSM sub-architecture
 help / color / mirror / Atom feed
From: "Måns Rullgård" <mans@mansr.com>
To: Russell King - ARM Linux <linux@arm.linux.org.uk>
Cc: Nicolas Pitre <nico@fluxnic.net>,
	Stephen Boyd <sboyd@codeaurora.org>,
	linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org, linux-arm-msm@vger.kernel.org,
	Michal Marek <mmarek@suse.com>,
	linux-kbuild@vger.kernel.org, Arnd Bergmann <arnd@arndb.de>,
	Steven Rostedt <rostedt@goodmis.org>,
	Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Subject: Re: [PATCH v2 2/2] ARM: Replace calls to __aeabi_{u}idiv with udiv/sdiv instructions
Date: Thu, 26 Nov 2015 02:19:48 +0000	[thread overview]
Message-ID: <yw1xziy1o62j.fsf@unicorn.mansr.com> (raw)
In-Reply-To: <20151126012859.GX8644@n2100.arm.linux.org.uk> (Russell King's message of "Thu, 26 Nov 2015 01:28:59 +0000")

Russell King - ARM Linux <linux@arm.linux.org.uk> writes:

> On Thu, Nov 26, 2015 at 12:50:08AM +0000, Måns Rullgård wrote:
>> If not calling the function saves an I-cache miss, the benefit can be
>> substantial.  No, I have no proof of this being a problem, but it's
>> something that could happen.
>
> That's a simplistic view of modern CPUs.
>
> As I've already said, modern CPUs which have branch prediction, but
> they also have speculative instruction fetching and speculative data
> prefetching - which the CPUs which have idiv support will have.
>
> With such features, the branch predictor is able to learn that the
> branch will be taken, and because of the speculative instruction
> fetching, it can bring the cache line in so that it has the
> instructions it needs with minimal or, if working correctly,
> without stalling the CPU pipeline.

It doesn't matter how many fancy features the CPU has.  Executing more
branches and using more cache lines puts additional pressure on those
resources, reducing overall performance.  Besides, the performance
counters readily show that the prediction is nothing near as perfect as
you seem to believe.

-- 
Måns Rullgård
mans@mansr.com
--
To unsubscribe from this list: send the line "unsubscribe linux-kbuild" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

  reply	other threads:[~2015-11-26  2:19 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-11-25 21:51 [PATCH v2 0/2] ARM: Use udiv/sdiv for __aeabi_{u}idiv library functions Stephen Boyd
2015-11-25 21:51 ` [PATCH v2 1/2] scripts: Add a recorduidiv program Stephen Boyd
2015-11-25 23:47   ` Russell King - ARM Linux
2015-11-30 15:11     ` Michal Marek
2015-11-30 15:32       ` Russell King - ARM Linux
2015-11-30 15:40         ` Michal Marek
2015-12-01 16:07           ` Michal Marek
2015-12-01 16:19             ` Russell King - ARM Linux
2015-12-01 16:43               ` Michal Marek
2015-12-01 16:49               ` Steven Rostedt
2015-12-01 17:10                 ` Russell King - ARM Linux
2015-12-01 17:22                   ` Steven Rostedt
2015-12-01 18:16                     ` Russell King - ARM Linux
2015-12-01 21:39                       ` Michal Marek
2015-12-02 10:23                       ` Russell King - ARM Linux
2015-12-02 14:05                         ` Steven Rostedt
2015-12-11 12:09                           ` [PATCH] scripts: recordmcount: break hardlinks Russell King
2015-12-11 14:31                             ` Steven Rostedt
2015-12-11 14:45                               ` Russell King - ARM Linux
2015-12-11 15:08                                 ` Steven Rostedt
2015-12-11 18:10                                 ` Steven Rostedt
2015-12-11 18:33                                   ` Russell King - ARM Linux
2015-12-11 18:51                                     ` Steven Rostedt
2015-12-11 18:58                                       ` Russell King - ARM Linux
2015-12-11 19:28                                         ` Steven Rostedt
2015-11-25 21:51 ` [PATCH v2 2/2] ARM: Replace calls to __aeabi_{u}idiv with udiv/sdiv instructions Stephen Boyd
2015-11-25 23:09   ` Nicolas Pitre
2015-11-26  0:05     ` Russell King - ARM Linux
2015-11-26  0:07     ` Måns Rullgård
2015-11-26  0:44       ` Nicolas Pitre
2015-11-26  0:50         ` Måns Rullgård
2015-11-26  1:28           ` Russell King - ARM Linux
2015-11-26  2:19             ` Måns Rullgård [this message]
2015-11-26  5:32               ` Nicolas Pitre
2015-11-26 12:41                 ` Måns Rullgård
2015-11-26  0:08   ` Russell King - ARM Linux

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=yw1xziy1o62j.fsf@unicorn.mansr.com \
    --to=mans@mansr.com \
    --cc=arnd@arndb.de \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-arm-msm@vger.kernel.org \
    --cc=linux-kbuild@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux@arm.linux.org.uk \
    --cc=mmarek@suse.com \
    --cc=nico@fluxnic.net \
    --cc=rostedt@goodmis.org \
    --cc=sboyd@codeaurora.org \
    --cc=thomas.petazzoni@free-electrons.com \
    /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