From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Original-To: caml-list@yquem.inria.fr Delivered-To: caml-list@yquem.inria.fr Received: from mail3-relais-sop.national.inria.fr (mail3-relais-sop.national.inria.fr [192.134.164.104]) by yquem.inria.fr (Postfix) with ESMTP id 43093BC57 for ; Fri, 19 Nov 2010 21:20:04 +0100 (CET) X-IronPort-Anti-Spam-Filtered: true X-IronPort-Anti-Spam-Result: AkMJAEdq5kxQDPIuZmdsb2JhbACiYRUNCwgIEgMfiCubEJo0hUsEhFqJDw X-IronPort-AV: E=Sophos;i="4.59,225,1288566000"; d="scan'208";a="67530351" Received: from smtp21.orange.fr ([80.12.242.46]) by mail3-smtp-sop.national.inria.fr with ESMTP; 19 Nov 2010 21:20:03 +0100 Received: from me-wanadoo.net (localhost [127.0.0.1]) by mwinf2126.orange.fr (SMTP Server) with ESMTP id 760EA1C0009E; Fri, 19 Nov 2010 21:20:03 +0100 (CET) Received: from me-wanadoo.net (localhost [127.0.0.1]) by mwinf2126.orange.fr (SMTP Server) with ESMTP id 67B4A1C00088; Fri, 19 Nov 2010 21:20:03 +0100 (CET) Received: from [172.24.130.66] (out1-1601fw.corp.tfbnw.net [66.220.144.27]) by mwinf2126.orange.fr (SMTP Server) with ESMTP id 5C8DC1C0009E; Fri, 19 Nov 2010 21:20:02 +0100 (CET) X-ME-UUID: 20101119202002379.5C8DC1C0009E@mwinf2126.orange.fr X-ME-User-Auth: padator@wanadoo.fr Subject: Re: [Caml-list] OCamlJit 2.0 Mime-Version: 1.0 (Apple Message framework v1081) Content-Type: text/plain; charset=us-ascii From: Yoann Padioleau In-Reply-To: <980786.74593.qm@web111507.mail.gq1.yahoo.com> Date: Fri, 19 Nov 2010 12:20:01 -0800 Cc: Benedikt Meurer , caml-list@yquem.inria.fr Content-Transfer-Encoding: quoted-printable Message-Id: <023DB1B5-B4D6-4C2A-AAF6-2368F93BEBB6@wanadoo.fr> References: <980786.74593.qm@web111507.mail.gq1.yahoo.com> To: Dario Teixeira X-Mailer: Apple Mail (2.1081) X-Spam: no; 0.00; bytecode:01 compiler:01 speedup:01 bytecode:01 cheers:01 wiki:01 2.0:98 gimmicks:98 imho:01 wrote:01 caml-list:01 implemented:02 slower:02 slower:02 shootout:02 On Nov 19, 2010, at 11:46 AM, Dario Teixeira wrote: > Hi, >=20 >> What would be really nice is to make a JIT for a language that really >> need one, like PHP! There are lots of companies out there (Yahoo, >> Facebook, wikimedia) that spend hundreds of millions of dollars on >> machines that run PHP bytecode interpreters implemented by people who >> are not Xavier Leroy. >=20 > Actually, Facebook has a compiler that transforms PHP source code into = C++ [1], > and they claim a 50% reduction in CPU usage. Yes, which is good. But if you think about it is "only" a x2 speedup vs = a really slow bytecode interpreter (the Zend PHP interpreter). PHP is = known for being more than 30 times slower than C.=20 It's even slower than Ruby on = http://shootout.alioth.debian.org/u32/which-programming-languages-are-fast= est.php There are lots of opportunities to do better IMHO. > It's an interesting approach, > though I suspect that even as we speak a new circle of hell is being = warmed > up Oh yeah. > especially for those who are enabling PHP's continued existence thanks > to gimmicks such as this one... >=20 > Cheers, > Dario Teixeira >=20 > [1] https://github.com/facebook/hiphop-php/wiki/ >=20 >=20 >=20 >=20