From owner-chemistry@ccl.net Sun Nov 4 18:40:00 2012 From: "TJ O Donnell tjo_-_acm.org" To: CCL Subject: CCL: Linux performance using a VM appliance Message-Id: <-47844-121104183129-808-nUxkbFmo0qo53BW4pJ/AZw(0)server.ccl.net> X-Original-From: "TJ O'Donnell" Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset=ISO-8859-1 Date: Sun, 4 Nov 2012 15:31:23 -0800 MIME-Version: 1.0 Sent to CCL by: "TJ O'Donnell" [tjo ~ acm.org] Although I have not run QM codes in a VM, I've been using VMs for about 5 years now. For computationally intense jobs (docking, clustering large databases, etc.) I get about 85-90% of the speed compared to the native machine. VMs suffer when used for graphical tasks, although they are respectable. Be sure to give the VM as much memory as you can and allow it to use all the processors. I only have experience with VMWare on this front. TJ O'Donnell On Sun, Nov 4, 2012 at 10:36 AM, Adrią Cereto Massagué adrian.cereto .. gmail.com wrote: > Performance will heavily depend on the virtualization software used, on its > configuration and on hardware availability of virtualization extensions. > > I have no experience with Microsoft Windows as a host OS, but maybe others > can tell you about that. > > Adrią > > 2012/11/2 John McKelvey jmmckel-*-gmail.com >> >> >> Sent to CCL by: John McKelvey [jmmckel##gmail.com] >> Hello.. >> >> Does anyone have experience running linux QM codes using a Virtual >> Machine under Windows? What is your estimate of efficiency using a V >> M relative to native code? >> >> Many thanks, >> >> John >> >> -- >> John McKelvey >> 10819 Middleford Pl >> Ft Wayne, IN 46818 >> 260-489-2160 >> jmmckel- -gmail.com>> E-mail to subscribers: CHEMISTRY-$-ccl.net or use:>> >> E-mail to administrators: CHEMISTRY-REQUEST-$-ccl.net or use>> >> >