From owner-freebsd-questions@FreeBSD.ORG Sat Aug 21 09:01:22 2010 Return-Path: Delivered-To: freebsd-questions@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 5544C1065673 for ; Sat, 21 Aug 2010 09:01:22 +0000 (UTC) (envelope-from cbergstrom@pathscale.com) Received: from mail-pw0-f54.google.com (mail-pw0-f54.google.com [209.85.160.54]) by mx1.freebsd.org (Postfix) with ESMTP id 30DF38FC1A for ; Sat, 21 Aug 2010 09:01:21 +0000 (UTC) Received: by pwj8 with SMTP id 8so544794pwj.13 for ; Sat, 21 Aug 2010 02:01:21 -0700 (PDT) Received: by 10.114.52.1 with SMTP id z1mr2838614waz.64.1282381281627; Sat, 21 Aug 2010 02:01:21 -0700 (PDT) Received: from [192.168.5.149] ([119.42.85.51]) by mx.google.com with ESMTPS id q6sm6776657waj.22.2010.08.21.02.01.18 (version=SSLv3 cipher=RC4-MD5); Sat, 21 Aug 2010 02:01:20 -0700 (PDT) Message-ID: <4C6F95F5.1020406@pathscale.com> Date: Sat, 21 Aug 2010 16:01:41 +0700 From: =?ISO-8859-1?Q?=22C=2E_Bergstr=F6m=22?= User-Agent: Thunderbird 2.0.0.22 (X11/20090909) MIME-Version: 1.0 To: "Svein Skogen (Listmail account)" References: 4C666786.6000205@mail.zedat.fu-berlin.de 20100816141324.7de6d7b4@ukr.net 20100816134713.66411ai1w435q5wh@webmail.xroff.net 201008161618.35076.pieter@degoeje.nl 20100816173333.4a1bba57@ukr.net 20100816145001.GA90619@mech-cluster241.men.bris.ac.uk <20100818120455.10870.qmail@dusk.parklogic.com> <4C6C085A.2010009@pathscale.com> <4C6F84DD.3040007@stillbilde.net> In-Reply-To: <4C6F84DD.3040007@stillbilde.net> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 8bit Cc: freebsd-questions@freebsd.org Subject: Re: FreeBSD, GPGPU and OpenCL/CUDA X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 21 Aug 2010 09:01:22 -0000 Svein Skogen (Listmail account) wrote: > On 18.08.2010 18:20, "C. Bergström" wrote: > >> Hi Oliver, >> >> >>> The problem behind the subject is a little bit frustrating, so I do >>> not know were to start. >>> >> Yeah it's a pretty big problem, but I can say others are looking at it >> and taking small steps in the right direction. >> >>> First, and this hasn't changed since the last 15 years, FreeBSD lack >>> in support of professional Compiler vendors. Pprtland Group offers >>> only Linux compilers, as far as I know Intel does not offer a native >>> FreeBSD 64 Bit compiler. So we are stuck with gcc and gfortran >>> > > *SNIP* > > If we see beyond the CUDA part of this question, it should be noted that > ATI/AMD has kept to their promise of actually supporting opensource. > > (see also > http://www.phoronix.com/scan.php?page=article&item=amd_evergreen_3d&num=1) > > I must admit not having tested that code myself (my two 5970s sit in a > windows box), but projects should maybe consider the ATI/AMD cards. > 928GFLOPS double-precision per card (4.64TFLOPS single precision) with > proper documentation should at least give a proper start to things... > I'm sorry, but this is only a half truth.. The firmware they don't release, despite what they want you to believe, is both interesting and should imho be open. Also the documentation they've released clearly has parts chopped out and when you actually try to do something useful it's missing important details. (My perspective is biased since by something useful I mean write an assembler or compute backend) I've had one awesome engineer at AMD trying to help us fill in some of those blanks, but if or when the public docs will be updated. Overall due to ATI hw missing ECC ram, demand paging and a few other hardware features I don't consider it a serious contender in HPC yet. Lastly, you'll see the real efficiency sucks and you can't get anywhere near the peak GFLOPS off those cards. Oh.. and most important to the land of FBSD is that the ATI drivers are still using the rather nasty TTM.. This is *not* very easily ported to FBSD, blocks compute capabilities and our early benchmarks show kicking it out has given nice performance increase in certain areas of graphics. (Hope I don't come across negative... I'm just trying to give real feedback based on our experience) ./C