Newsgroups: php.internals Path: news.php.net Xref: news.php.net php.internals:44265 Return-Path: Mailing-List: contact internals-help@lists.php.net; run by ezmlm Delivered-To: mailing list internals@lists.php.net Received: (qmail 36154 invoked from network); 13 Jun 2009 18:02:26 -0000 Received: from unknown (HELO lists.php.net) (127.0.0.1) by localhost with SMTP; 13 Jun 2009 18:02:26 -0000 Authentication-Results: pb1.pair.com header.from=chris_se@gmx.net; sender-id=pass Authentication-Results: pb1.pair.com smtp.mail=chris_se@gmx.net; spf=pass; sender-id=pass Received-SPF: pass (pb1.pair.com: domain gmx.net designates 213.165.64.20 as permitted sender) X-PHP-List-Original-Sender: chris_se@gmx.net X-Host-Fingerprint: 213.165.64.20 mail.gmx.net Received: from [213.165.64.20] ([213.165.64.20:41680] helo=mail.gmx.net) by pb1.pair.com (ecelerity 2.1.1.9-wez r(12769M)) with ESMTP id AE/74-12802-1B9E33A4 for ; Sat, 13 Jun 2009 14:02:26 -0400 Received: (qmail invoked by alias); 13 Jun 2009 18:02:21 -0000 Received: from p54A14DD4.dip.t-dialin.net (EHLO chris-se.dyndns.org) [84.161.77.212] by mail.gmx.net (mp006) with SMTP; 13 Jun 2009 20:02:21 +0200 X-Authenticated: #186999 X-Provags-ID: V01U2FsdGVkX1/MzrwhMGvM1raVhj8wJSZsgY3T6LZNveObu0cEgu Ne/MKzFE2cQl+D Received: from [192.168.100.13] (cobalt.seiler.lan [192.168.100.13]) by chris-se.dyndns.org (Postfix) with ESMTP id 474DA6930; Sat, 13 Jun 2009 20:02:19 +0200 (CEST) Message-ID: <4A33E979.1030700@gmx.net> Date: Sat, 13 Jun 2009 20:01:29 +0200 User-Agent: Thunderbird 2.0.0.21 (X11/20090302) MIME-Version: 1.0 To: Pierre Joye CC: php-dev List References: In-Reply-To: X-Enigmail-Version: 0.95.7 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit X-Y-GMX-Trusted: 0 X-FuHaFi: 0.64 Subject: Re: [PHP-DEV] float ops and _controlfp_s From: chris_se@gmx.net (Christian Seiler) Hi Pierre, (Btw. you got the wrong Christian as CC. ;-)) > There is still a significant performance impact due to _controlfp_s > usage. Huh? After the modification I made this should only called once (!) at PHP startup Or did we miss something? Anyway, calling it once should not cause any performance problems at all. > Can you explain why we need it and what tests are affected by this > change please? This ensures that FPUs on x86 systems are definitely in double precision mode. The default situation on Windows with MSVC is that the FPU is already in double precision setting as far as I've tested it - however there are situations (PHP embedded into a webserver for example) where this may not be true. Could you please provide some details for "significant performance impact"? Regards, Christian PS: My package arrived a while ago and I remember I didn't say thanks yet - so here it goes: Thanks a lot!