From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail4-relais-sop.national.inria.fr (mail4-relais-sop.national.inria.fr [192.134.164.105]) by walapai.inria.fr (8.13.6/8.13.6) with ESMTP id p7QCcIkM000514 for ; Fri, 26 Aug 2011 14:38:18 +0200 X-IronPort-Anti-Spam-Filtered: true X-IronPort-Anti-Spam-Result: AnAHAA6TV05KfVI0kGdsb2JhbABCFpg0hBeLLwgUAQEBAQkJDQcUBCGBQAEBAQEBAhICJgYBFBkLAQMMAQUFGA0IGRQgAQUBAQkYExIQh1SdPAqPEIUciSgCAwYIgy2CMWAEmU+DQ4JnPIFEgiM X-IronPort-AV: E=Sophos;i="4.68,285,1312149600"; d="scan'208";a="106722275" Received: from mail-ww0-f52.google.com ([74.125.82.52]) by mail4-smtp-sop.national.inria.fr with ESMTP/TLS/RC4-SHA; 26 Aug 2011 14:38:12 +0200 Received: by wwe6 with SMTP id 6so4278659wwe.9 for ; Fri, 26 Aug 2011 05:38:12 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=sender:date:from:to:cc:subject:message-id:references:mime-version :content-type:content-disposition:in-reply-to:user-agent; bh=0mSr/E6y8Q+PA3Wyy4h9bm3tGuqZzNlRMmtImcL1G2Y=; b=mQj023K5OprUNIoc2A2H3c8WnruDi2VSqf03UhXB2QDwcb9ykiy98HD+liVhiqCc1b 0nx85+El6f1tjNw/elwRb0xwvHrKSibKzDfFYuGBtXCRpLghLSRnipcukII2ArKI2AR7 wCEdC2uINB5tJCLz6yDNwwqmjk4E8jNC1hWxw= Received: by 10.216.188.207 with SMTP id a57mr820202wen.94.1314362292539; Fri, 26 Aug 2011 05:38:12 -0700 (PDT) Received: from voyager (guest-rocq-134234.inria.fr [128.93.134.234]) by mx.google.com with ESMTPS id i51sm1004587wed.43.2011.08.26.05.38.10 (version=TLSv1/SSLv3 cipher=OTHER); Fri, 26 Aug 2011 05:38:11 -0700 (PDT) Sender: Roberto Di Cosmo Received: from dicosmo by voyager with local (Exim 4.72) (envelope-from ) id 1Qwvhi-0002mY-Ag; Fri, 26 Aug 2011 14:40:10 +0200 Date: Fri, 26 Aug 2011 14:40:04 +0200 From: Roberto Di Cosmo To: Benedikt Meurer Cc: caml-list@inria.fr Message-ID: <20110826124004.GA10448@voyager> References: <93199F3B-E9CF-4D93-9B2B-BAAB03F4FC08@googlemail.com> <4EF51F29-D437-4F6F-9C91-DBEA3D4C3EB8@googlemail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <4EF51F29-D437-4F6F-9C91-DBEA3D4C3EB8@googlemail.com> User-Agent: Mutt/1.5.20 (2009-06-14) Subject: Re: [Caml-list] Linear Scan Register Allocator for ocamlopt/ocamlnat Dear Benedikt, this is a typical case where the FSF compile farm may come in handy. You can find more information on the machines available for this kind of tests here: http://gcc.gnu.org/wiki/CompileFarm To get an account on the machines, just follow the instructions on "How to get involved" on the page, you should be up and running in very little time --Roberto On Wed, Aug 24, 2011 at 09:35:56PM +0200, Benedikt Meurer wrote: > > On Aug 1, 2011, at 17:04 , Gabriel Scherer wrote: > > > Do you have more precise measurements on > > Also posting Marcell's timing results here for reference (taken from bug 5324). > > > - the performance cost of this new allocator in the generated code? I > > suppose the results may vary between different architectures (eg. x86 > > is probably more sensitive to good allocation decisions than x86_64). > > - http://ps.informatik.uni-siegen.de/~meurer/tmp/compiletime_timings.pdf contains a comparison of the ocamlopt invocations. > - http://ps.informatik.uni-siegen.de/~meurer/tmp/runtime_timings.pdf contains comparison of the generated code. > > As can be seen from the results, amd64 is more sensitive to register allocator changes than i386. Not really surprising to me. Would be interesting to see how this affects PPC/Sparc/Mips, but we don't have appropriate hardware available right now. Anyone with appropriate hardware and some spare time? :-) > > Benedikt > > > -- > Caml-list mailing list. Subscription management and archives: > https://sympa-roc.inria.fr/wws/info/caml-list > Beginner's list: http://groups.yahoo.com/group/ocaml_beginners > Bug reports: http://caml.inria.fr/bin/caml-bugs > -- --Roberto Di Cosmo ------------------------------------------------------------------ Professeur En delegation a l'INRIA PPS E-mail: roberto@dicosmo.org Universite Paris Diderot WWW : http://www.dicosmo.org Case 7014 Tel : ++33-(0)1-57 27 92 20 5, Rue Thomas Mann F-75205 Paris Cedex 13 Identica: http://identi.ca/rdicosmo FRANCE. Twitter: http://twitter.com/rdicosmo ------------------------------------------------------------------ Attachments: MIME accepted Word deprecated, http://www.rfc1149.net/documents/whynotword ------------------------------------------------------------------ Office location: Bureau 6C08 (6th floor) 175, rue du Chevaleret, XIII Metro Chevaleret, ligne 6 ------------------------------------------------------------------