I have done the measurements, at least with some of the code I have built for spatial pattern analysis. If you are on a networked machine, with lots of network processes running in the background, turning off hyperthreading increases speed by 30-50% (at least on my network). I have tried it on a non-networked machine, and speed increased by 60% or better.
Mike Mike R. Saunders Forest Biometrician Cooperative Forest Research Unit University of Maine 5755 Nutting Hall Orono, ME 04469-5755 207-581-2763 (O) 207-581-2833 (F) ----- Original Message ----- From: "Duncan Murdoch" <[EMAIL PROTECTED]> To: "Markus Preisetanz" <[EMAIL PROTECTED]> Cc: <[email protected]> Sent: Monday, August 07, 2006 8:42 AM Subject: Re: [R] CPU Usage with R 2.1.0 in Windows (and with R 2.3.1) Markus Preisetanz wrote: > ... I have exactly the same issue with R 2.3.1 . The Question is: Why is R > unable to take more CPU space to make the calculation process go faster? > > In my case no hardisk nor any network device is involved (data in RAM, 600 > of 1024 MB filled) - and the CPU usage of the rgui-process does not exceed > 50%. > > Has anybody an idea? Is there a setting a can change? > You are probably on a dual core or hyperthreaded machine. R does almost all of its work in one thread, so it will max out the usage on one cpu, but not more than one. If you are on a hyperthreaded machine, you can disable hyperthreading and the report should show 100% usage, but that doesn't mean things will be going twice as fast. (I have heard that hyperthreading does slow down some computations, so turning it off might be a good idea, but I have never done the measurements myself.) Duncan Murdoch > > Sincerely, Markus > ____________________________ > Markus Preisetanz > Consultant > > Client Vela GmbH > Albert-Roßhaupter-Str. 32 > 81369 München > fon: +49 (89) 74217-113 > main: +49 (89) 74217-150 > fax: +49 (89) 74217-250 > [EMAIL PROTECTED] <mailto:[EMAIL PROTECTED]> > http://www.clientvela.com <http://www.clientvela.com/> > > Diese E-Mail enthält vertrauliche und/oder rechtlich geschützte > Informationen. Wenn Sie nicht der richtige Adressat sind oder diese E-Mail > irrtümlich erhalten haben, informieren Sie bitte sofort den Absender und > vernichten Sie diese Mail. Das unerlaubte Kopieren sowie die unbefugte > Weitergabe dieser E-Mail ist nicht gestattet. > > This e-mail may contain confidential and/or privileged information. If you > are not the intended recipient (or have received the e-mail in error) > please notify the sender immediately and destroy this e-mail. Any > unauthorized copying, disclosure or distribution of the material in this > e-mail is strictly forbidden > > xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx > From: Doran, Harold <HDoran_at_air.org > <mailto:HDoran_at_air.org?Subject=Re:%20%5BR%5D%20CPU%20Usage%20with%20R%202.1.0%20in%20Windows> > > > > Date: Wed 20 Jul 2005 - 04:59:34 EST > > > > Dear Michael: > > Why is it a problem that R is not using more CPU space than it seems to > need? > > -----Original Message----- > From: [EMAIL PROTECTED] > [mailto:[EMAIL PROTECTED] On Behalf Of Greene, Michael > Sent: Tuesday, July 19, 2005 2:29 PM > To: '[EMAIL PROTECTED]' > Subject: [R] CPU Usage with R 2.1.0 in Windows > > Hi, > > I'm using a fairly simple HP Compaq desktop PC running Windows 2K. When > running a large process in R, the process "RGUI.exe" will never exceed 50% > of the CPU usage. > > The program used to be able to use more of the computer, but does not now. > I don't believe this is a multiple processor machine. > > Can anyone give any advice on how to solve the problem? > > Thanks, > > Michael Greene > > Product Management > Plymouth Rock Assurance Corp > 617-951-1682 > > > [[alternative HTML version deleted]] > > > ------------------------------------------------------------------------ > > ______________________________________________ > [email protected] mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide > http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. > ______________________________________________ [email protected] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. ______________________________________________ [email protected] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
