Newsgroups: php.internals
Path: news.php.net
Xref: news.php.net php.internals:89844
Mailing-List: contact internals-help@lists.php.net; run by ezmlm
Received-SPF: pass (pb1.pair.com: domain intel.com designates 134.134.136.20 as permitted sender)
To: "internals@lists.php.net" <internals@lists.php.net>,
	"'laruence@gmail.com'" <laruence@gmail.com>
Thread-Topic: Benchmark Results for PHP Master 2015-12-18
Thread-Index: AQHROZdeHMZ8qFCBfk2l2K9qg7rmg57QxWLQ
Date: Fri, 18 Dec 2015 14:14:37 +0000
Message-ID: <0ABC26E371A76440A370CFC5EB1056CC40EB79BA@IRSMSX106.ger.corp.intel.com>
References: <ab3fdebe-c54e-43d3-bcf6-3daa1ea252c7@irsmsx153.ger.corp.intel.com>
In-Reply-To: <ab3fdebe-c54e-43d3-bcf6-3daa1ea252c7@irsmsx153.ger.corp.intel.com>
Accept-Language: en-US
Content-Language: en-US
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
Subject: RE: Benchmark Results for PHP Master 2015-12-18
From: bogdan.andone@intel.com ("Andone, Bogdan")

Hi Guys,

A small and unexpected help for supporting our daily performance benchmark =
tick :)

We just observed a consistent performance drop in the last 24 hours with hi=
ghest presence on Mandelbrot (-13%).
After a binary iteration on the concerned set of commits we identified the =
following:
- commit 940c68b has x2.25 bigger execution time on Mandelbrot compared wit=
h the previous one (7a01ff5)
- commit 9374977d215be414d6e2e98b041a2b8f9b9a1e8d brought Mandelbrot speed =
back but still 13% below the previous values

@laruence: could you have a double check on these commits?

Kind Regards,
Bogdan

> -----Original Message-----
> From: lp_benchmark_robot
> Sent: Friday, December 18, 2015 3:24 PM
> To: internals@lists.php.net; langperf@lists.01.org
> Subject: Benchmark Results for PHP Master 2015-12-18
>=20
> Results for project PHP master, build date 2015-12-18 06:30:04+02:00
> commit:		1abbdcd9a455ce2638848c13f382cf3f92333d5d
> revision date:	2015-12-17 23:36:20+00:00
> environment:	Haswell-EP
> 	cpu:	Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz 2x18 cores,
> stepping 2, LLC 45 MB
> 	mem:	128 GB
> 	os:	CentOS 7.1
> 	kernel:	Linux 3.10.0-229.4.2.el7.x86_64
>=20
> Baseline results were generated using release php-7.0.0, with hash
> 60fffd296abce5fc071f3c173c25a2696cf683c6 from 2015-12-01 04:16:47+00:00
>=20
> ------------------------------------------------------------------------
> -------------------
>                         benchmark   relative   change since   change
> since  current rev run
>                                     std_dev*       last run
> baseline         with PGO
> ------------------------------------------------------------------------
> -------------------
> :-|   Wordpress 4.2.2 cgi -T10000      0.11%         -0.18%
> 0.19%            7.32%
> :-|       Drupal 7.36 cgi -T10000      0.20%         -0.66%         -
> 0.43%            5.06%
> :-|   MediaWiki 1.23.9 cgi -T5000      0.22%         -0.97%
> 0.51%            2.82%
> :-|           bench.php cgi -T100      0.02%         -0.97%
> 0.07%            6.25%
> :-(      micro_bench.php cgi -T10      0.05%         -1.06%         -
> 0.03%            4.22%
> :-(      mandelbrot.php cgi -T100      0.01%        -13.58%        -
> 11.39%            0.74%
> ------------------------------------------------------------------------
> -------------------
> Note: Benchmark results for Wordpress, Drupal, MediaWiki are measured in
> fetches/second while all others are measured in seconds.
> More details on measurements methodology at:
> https://01.org/lp/documentation/php-environment-setup.
> * Relative Standard Deviation (Standard Deviation/Average)
>=20
> Our lab does a nightly source pull and build of the PHP project and
> measures
> performance changes against the previous stable version and the previous
> nightly
> measurement. This is provided as a service to the community so that
> quality
> issues with current hardware can be identified quickly.
>=20
> Intel technologies' features and benefits depend on system configuration
> and may
> require enabled hardware, software or service activation. Performance
> varies
> depending on system configuration.