Newsgroups: php.internals Path: news.php.net Xref: news.php.net php.internals:50179 Return-Path: Mailing-List: contact internals-help@lists.php.net; run by ezmlm Delivered-To: mailing list internals@lists.php.net Received: (qmail 56707 invoked from network); 13 Nov 2010 01:04:04 -0000 Received: from unknown (HELO lists.php.net) (127.0.0.1) by localhost with SMTP; 13 Nov 2010 01:04:04 -0000 Authentication-Results: pb1.pair.com header.from=james.butler@edigitalresearch.com; sender-id=unknown Authentication-Results: pb1.pair.com smtp.mail=james.butler@edigitalresearch.com; spf=unknown; sender-id=unknown Received-SPF: unknown (pb1.pair.com: domain edigitalresearch.com does not designate 217.154.180.62 as permitted sender) X-PHP-List-Original-Sender: james.butler@edigitalresearch.com X-Host-Fingerprint: 217.154.180.62 analysis.edigitalresearch.com Linux 2.6 Received: from [217.154.180.62] ([217.154.180.62:34998] helo=mail.edigitalresearch.com) by pb1.pair.com (ecelerity 2.1.1.9-wez r(12769M)) with ESMTP id 0F/E7-09586-304EDDC4 for ; Fri, 12 Nov 2010 20:04:03 -0500 Received: from localhost (localhost [127.0.0.1]) by mail.edigitalresearch.com (Postfix) with ESMTP id 869D026062C; Sat, 13 Nov 2010 01:03:59 +0000 (GMT) X-Virus-Scanned: amavisd-new at edigitalresearch.com Received: from mail.edigitalresearch.com ([127.0.0.1]) by localhost (mail.edigitalresearch.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id aTIQAGOXnI-x; Sat, 13 Nov 2010 01:03:58 +0000 (GMT) Received: from zarafa.localdomain (unknown [10.0.0.20]) (using TLSv1 with cipher ADH-AES256-SHA (256/256 bits)) (No client certificate requested) by mail.edigitalresearch.com (Postfix) with ESMTPS id D1A74260564; Sat, 13 Nov 2010 01:03:58 +0000 (GMT) Received: from zarafa.edigitalresearch.com (zarafa.edigitalresearch.com [10.0.0.20]) by zarafa.localdomain (Postfix) with SMTP id B84E21003A1; Sat, 13 Nov 2010 01:03:56 +0000 (GMT) To: =?windows-1252?Q?"Andi_Gutmans"?= Cc: =?windows-1252?Q?"Scott_MacVicar"?= , =?windows-1252?Q?"Stefan_Marr"?= , =?windows-1252?Q?"Kenan_Sulayman"?= , =?windows-1252?Q?"PHP_internals"?= Date: Sat, 13 Nov 2010 01:03:56 +0000 Mime-Version: 1.0 Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: quoted-printable X-Mailer: Zarafa 6.40.2-22452 Message-ID: Subject: Re: [PHP-DEV] GPU Acceleration From: james.butler@edigitalresearch.com (=?windows-1252?Q?James_Butler?=) As a slight side note, GPUs have been (and mostly still are) used for high performance workloads where squeezing as much useful 'work' per cycle is the order of the day. CUDA et al still hasn't hit the mainstream fully and is pretty niche. Unfortunately PHP being an interpreted language isn't going to be as efficient (yet=3F :-) ) as C or machine code and therefore you will lose some/alot of the advantage of going GPU.=20 However that is not a reason not to have a go (fork maybe=3F), something cool may come about from it. Nothing ventured, nothing gained. -- James Butler Sent from my iPhone On 13 Nov 2010, at 00:29, "Andi Gutmans" wrote: >> -----Original Message----- >> From: Scott MacVicar [mailto:scott@macvicar.net] >> Sent: Friday, November 12, 2010 8:22 AM >> To: Stefan Marr >> Cc: Kenan Sulayman; PHP internals >> Subject: Re: [PHP-DEV] GPU Acceleration >>=20 >> What's not constructive about it=3F Seems pretty constructive to me. The original >> poster has done research into the issue already. >=20 > What research are you referring to=3F I must have missed that. > There's no magic with GPUs. There are good reasons why few applications/infrastructure components use them. GPUs can be useful for very specific workloads but not necessarily general purpose app server. > Btw there are also some workloads that could benefit from leveraging some of the x86 extensions around encryption, vector computation, ... > So it boils down to being more specific re: where you think it could benefit and why. > Andi >=20 >> The reason most things don't exist is that no one has a patch for it. If it doesn't >> core in core then it heads into a PECL module or lives as a patch on some site. >=20 >=20 > --=20 > PHP Internals - PHP Runtime Development Mailing List > To unsubscribe, visit: http://www.php.net/unsub.php >=20