From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from troutmask.apl.washington.edu (troutmask.apl.washington.edu [128.95.76.21]) by sourceware.org (Postfix) with ESMTPS id 39EC33858403 for ; Sat, 3 Feb 2024 16:13:12 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org 39EC33858403 Authentication-Results: sourceware.org; dmarc=none (p=none dis=none) header.from=troutmask.apl.washington.edu Authentication-Results: sourceware.org; spf=none smtp.mailfrom=troutmask.apl.washington.edu ARC-Filter: OpenARC Filter v1.0.0 sourceware.org 39EC33858403 Authentication-Results: server2.sourceware.org; arc=none smtp.remote-ip=128.95.76.21 ARC-Seal: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1706976793; cv=none; b=wHo0fqqyzA/W06I4m4PH7bpfNOPVkrGsY4L6pl2rG2vwpiRFDVhdlukRNGVfo4kyB5zf8os0VfI8VnEDz9qDcg7IOBBUNU2WWh4sFxySEMIROJYasCUqg5J8qCkUX/6T9f1gLNEbYmtKgqtPaFC7JZs6D5BLrKkPqhPNTnSQkCo= ARC-Message-Signature: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1706976793; c=relaxed/simple; bh=1DISHQWAsQrIDmbYWJULCzxlVqeNwPeV5YWXOzK6Shs=; h=DKIM-Signature:Date:From:To:Subject:Message-ID:MIME-Version; b=ecVkZke8AoJ51gFFikW50qwBPTjhRaUHSst/Kq30MryREJiK4xeZrh+/Fo5SdS1yY74+5HZZiKV6olU52qtBnrOEj9kBpuPGO+cr7H5Ga1E2fC6MHTzKil2OF6BuQvRIZvdB4TvQuAuOclq9x1cfYwWj6UTACFLNs2FtMrxGPqg= ARC-Authentication-Results: i=1; server2.sourceware.org Received: from troutmask.apl.washington.edu (localhost [127.0.0.1]) by troutmask.apl.washington.edu (8.17.1/8.17.1) with ESMTP id 413GDBXJ021532; Sat, 3 Feb 2024 08:13:11 -0800 (PST) (envelope-from sgk@troutmask.apl.washington.edu) DKIM-Filter: OpenDKIM Filter v2.10.3 troutmask.apl.washington.edu 413GDBXJ021532 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=troutmask.apl.washington.edu; s=troutmask; t=1706976791; bh=1DISHQWAsQrIDmbYWJULCzxlVqeNwPeV5YWXOzK6Shs=; h=Date:From:To:Cc:Subject:Reply-To:References:In-Reply-To:From; b=ka9UqowT7HSJbgggg8zLOwqp+JDJd3CWS8sktdRCiQOLCRdnPFVYOk8xRCF4sB0HA sSeyTzyEL8Jamx+l16aHLfXyzMT1AESyKkEoR/9lWo3Fsh1olb18oTokcX4UKac/xl Uz3gYJS2dVwPk+xPvo+bj7vxdSS9PMwfDaDlXf/8kXmG7cEC/QXHfp84jCS3MkJjxb C8/Fy7mnFlCacG4bUmp6pjHNZH0upC0GhWYPrxRhjtspC34G8srfbMJX2W0uxd4vBX nJpHI/8GKuUHeHxLKQ4Bstw7E8K0EX3XOrTD3l7VwC1gt5U6BtUXuOEXInKtrgVawK xHOa+nfg5MN6g== Received: (from sgk@localhost) by troutmask.apl.washington.edu (8.17.1/8.17.1/Submit) id 413GDBwm021531; Sat, 3 Feb 2024 08:13:11 -0800 (PST) (envelope-from sgk) Date: Sat, 3 Feb 2024 08:13:11 -0800 From: Steve Kargl To: Richard Biener Cc: fortran@gcc.gnu.org Subject: Re: GPU offloading question Message-ID: Reply-To: sgk@troutmask.apl.washington.edu References: <29F25227-C186-4B29-BC4D-6DC5EA038A71@gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: <29F25227-C186-4B29-BC4D-6DC5EA038A71@gmail.com> X-Spam-Status: No, score=-1.0 required=5.0 tests=BAYES_00,DKIM_INVALID,DKIM_SIGNED,KAM_DMARC_STATUS,SPF_HELO_NONE,SPF_NONE,TXREP,T_SCC_BODY_TEXT_LINE autolearn=no autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on server2.sourceware.org List-Id: On Sat, Feb 03, 2024 at 02:37:05PM +0100, Richard Biener wrote: > > > Am 03.02.2024 um 01:22 schrieb Steve Kargl : > > > > All, > > > > Suppose one is working in a funding-constrained environment > > such as an academician with limited grant funding. If one > > wanted to dabble in GPU offloading with gcc/gfortran, what > > recommendations would one have for minimum required hardware? > > In addition, are there any vendor software layers that are > > required (such as AMD ROCm with an AMD GPU)? > > You need the HSA runtime for AMD which comes with ROCm and libcuda > for NvIDIA which comes with CUDA. Thanks. I'll need to check the level of support for the above in FreeBSD. I suspect it's non-existent, so looks like I'll take a plunge down the linux rabbit hole. > I’ve had success getting both a very low end gtx1650 and a high > end rx6900xt running with simple offloading. The officially supported > set of hardware is way bigger with CUDA when it comes to lower end cards. > > I can’t say anything about performance with regard to how GCC handles both. > > Note that double precision math performance is said to be severely > constrained for consumer hardware. Ah, good point. I'll need to find a card I can afford that supports double precision. -- steve > > Richard > > > > > -- > > Steve -- Steve