From: Carsten Aulbert Subject: Direct access to GPGPU do-able? Date: Tue, 1 Dec 2009 08:08:07 +0100 Message-ID: <200912010808.07998.carsten.aulbert@aei.mpg.de> Mime-Version: 1.0 Content-Type: Text/Plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: kvm@vger.kernel.org Return-path: Received: from welcomes-you.com ([188.40.94.149]:54413 "EHLO smtp.welcomes-you.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752150AbZLAHRj (ORCPT ); Tue, 1 Dec 2009 02:17:39 -0500 Received: from localhost (localhost.localdomain [127.0.0.1]) by smtp.welcomes-you.com (Postfix) with ESMTP id A189886D68AFA for ; Tue, 1 Dec 2009 08:08:13 +0100 (CET) Sender: kvm-owner@vger.kernel.org List-ID: Hi, I'll start with a one-off question here, so please cc me on the reply. We are running a largish cluster and are currently buying GPGPU systems (Tesla and soon Fermi based). We will have at least 2 possibly 4 of these cards per box and have the problem that some codes need different CUDA kernel drivers to run. As these boxes have 4 CPU cores, 12 GB of memory and CPU-VT support we thought that this might be solvable by creating (para-) virtualized guests on the boxes and passing one GPGPU device into a guest at a time. In there we then can run any kernel/driver combo necessary. But since my current virtualization experience only stretches to OpenVZ and VirtualBox (tinkering with Xen a couple of years back), I don't know if KVM is the right approach here. We need something which we can automatically set-up via CLI, i.e. starting and stopping the guests need to be fully automatic, we don't need a graphical environment within the guests, just plain text is good enough. What do you think, is looking at KVM the right choice for this? Can we pass a device directly into a guest? Cheers Carsten -- Dr. Carsten Aulbert - Max Planck Institute for Gravitational Physics Callinstrasse 38, 30167 Hannover, Germany Phone/Fax: +49 511 762-17185 / -17193 http://www.top500.org/system/9234 | http://www.top500.org/connfam/6/list/3