From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: Andi Kleen <andi@firstfloor.org>
Cc: x86@kernel.org, linux-kernel@vger.kernel.org,
Andi Kleen <ak@linux.intel.com>
Subject: Re: [PATCH 2/5] perf, x86: Enable PDIR precise instruction profiling on IvyBridge
Date: Mon, 02 Jul 2012 21:18:53 +0200 [thread overview]
Message-ID: <1341256733.23484.11.camel@twins> (raw)
In-Reply-To: <1341254598-1379-3-git-send-email-andi@firstfloor.org>
On Mon, 2012-07-02 at 11:43 -0700, Andi Kleen wrote:
> From: Andi Kleen <ak@linux.intel.com>
>
> Even with precise profiling Intel CPUs have a "skid". The sample
> triggers a few cycles later than the instruction, so in some
> cases there can be systematic errors where expensive instructions never
> show up in the profile log.
>
> Sandy Bridge added a new PDIR instruction retired event that randomizes
> the sampling slightly. This corrects for systematic errors, so that
> you should in most cases see the correct instruction getting profile hits.
>
> Unfortunately the SandyBridge version could only work with a otherwise
> quiescent CPU and was difficult to use. But now on IvyBridge this
> restriction is gone and can be more widely used.
>
> This only works for retired instructions.
>
> I enabled it -- somewhat arbitarily -- for two 'p's or more.
>
> To use it
>
> perf record -e instructions:pp ...
>
> This provides a more precise alternative to the usual cycles:pp,
> however it will not account for expensive instructions.
Already told you no.
next prev parent reply other threads:[~2012-07-02 19:19 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-07-02 18:43 Updated and combined Sandy Bridge/Ivy Bridge perf patchkits Andi Kleen
2012-07-02 18:43 ` [PATCH 1/5] perf, x86: Improve basic Ivy Bridge support v3 Andi Kleen
2012-07-02 19:26 ` Peter Zijlstra
2012-07-02 19:58 ` Andi Kleen
2012-07-02 20:18 ` Peter Zijlstra
2012-07-02 18:43 ` [PATCH 2/5] perf, x86: Enable PDIR precise instruction profiling on IvyBridge Andi Kleen
2012-07-02 19:18 ` Peter Zijlstra [this message]
2012-07-02 19:57 ` Andi Kleen
2012-07-02 20:22 ` Peter Zijlstra
2012-07-02 21:00 ` Andi Kleen
2012-07-02 21:36 ` Peter Zijlstra
2012-07-02 21:57 ` Andi Kleen
2012-07-02 23:13 ` Stephane Eranian
2012-07-03 4:04 ` Andi Kleen
2012-07-05 15:45 ` Stephane Eranian
2012-07-05 17:26 ` Andi Kleen
2012-07-06 1:04 ` Stephane Eranian
2012-07-02 18:43 ` [PATCH 3/5] x86: Do microcode updates at CPU_STARTING, not CPU_ONLINE v2 Andi Kleen
2012-07-02 18:43 ` [PATCH 4/5] perf, x86: check ucode before disabling PEBS on SandyBridge v4 Andi Kleen
2012-07-02 18:43 ` [PATCH 5/5] perf, x86: Spell Romley correctly Andi Kleen
-- strict thread matches above, loose matches on Subject: below --
2012-07-02 20:40 Another IvyBridge/SandyBridge patchkit Andi Kleen
2012-07-02 20:40 ` [PATCH 2/5] perf, x86: Enable PDIR precise instruction profiling on IvyBridge Andi Kleen
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=1341256733.23484.11.camel@twins \
--to=a.p.zijlstra@chello.nl \
--cc=ak@linux.intel.com \
--cc=andi@firstfloor.org \
--cc=linux-kernel@vger.kernel.org \
--cc=x86@kernel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.