From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([208.118.235.92]:56245)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <aurelien@aurel32.net>) id 1T9yBL-0005jl-G9
	for qemu-devel@nongnu.org; Fri, 07 Sep 2012 09:01:20 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <aurelien@aurel32.net>) id 1T9yBB-0003xb-Do
	for qemu-devel@nongnu.org; Fri, 07 Sep 2012 09:01:11 -0400
Received: from hall.aurel32.net ([88.191.126.93]:53463)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <aurelien@aurel32.net>) id 1T9yBB-0003xR-7n
	for qemu-devel@nongnu.org; Fri, 07 Sep 2012 09:01:01 -0400
Date: Fri, 7 Sep 2012 15:00:53 +0200
From: Aurelien Jarno <aurelien@aurel32.net>
Message-ID: <20120907130053.GC6024@ohm.aurel32.net>
References: <1346943657-17256-1-git-send-email-aurelien@aurel32.net>
	<CAFEAcA9Fr-tAtZ=ZJQS82Q-cdJ+Qy2t9cqiGYSFCCOhmQ1TB6w@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=iso-8859-15
Content-Disposition: inline
In-Reply-To: <CAFEAcA9Fr-tAtZ=ZJQS82Q-cdJ+Qy2t9cqiGYSFCCOhmQ1TB6w@mail.gmail.com>
Subject: Re: [Qemu-devel] [PATCH 0/8] Improve TCG optimizer
List-Id: <qemu-devel.nongnu.org>
List-Unsubscribe: <https://lists.nongnu.org/mailman/options/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>
List-Archive: <http://lists.nongnu.org/archive/html/qemu-devel>
List-Post: <mailto:qemu-devel@nongnu.org>
List-Help: <mailto:qemu-devel-request@nongnu.org?subject=help>
List-Subscribe: <https://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: Peter Maydell <peter.maydell@linaro.org>
Cc: qemu-devel@nongnu.org

On Fri, Sep 07, 2012 at 01:34:10PM +0100, Peter Maydell wrote:
> On 6 September 2012 16:00, Aurelien Jarno <aurelien@aurel32.net> wrote:
> > This patch series improves the TCG optimizer, based on patterns found
> > while executing various guest. The brcond ad setcond constant folding
> > are useful especially useful when they are used to avoid some argument
> > values (e.g. division by 0), and thus can be optimized when this argument
> > is a constant.
> >
> > This bring around 0.5% improvement on openssl like benchmarks.
> 
> This didn't overall seem to make much difference on my popular
> embedded benchmark setup. However I am rapidly losing confidence
> in the benchmark since from run to run individual tests can have
> results which vary by a factor of two, which is such high
> variation it's almost impossible to say whether a change has
> had an overall +1% or -1% effect. Hohum.
> 

I am usually doing the tests by setting the CPU performance to
performance and by pinning QEMU to a given CPU, on a machine without or
with very few other tasks. This improve the stability of the results.

Unfortunately it's not easy to do that on a laptop, especially when
running on battery.

-- 
Aurelien Jarno                          GPG: 1024D/F1BCDB73
aurelien@aurel32.net                 http://www.aurel32.net