From: Chris Harrison (charris5_at_gmail.com)
Date: Fri Apr 20 2012 - 19:46:56 CDT
Gianluca,
If the multicore version turns out to be slower, please make sure to
let us know.
Best,
Chris
On Wed, Apr 11, 2012 at 1:05 AM, Norman Geist
<norman.geist_at_uni-greifswald.de> wrote:
> Hi,
>
> easiest way is to just try both. It's hard to say that from datasheets.
> Machines are different and use cases are also. That can make a difference.
>
> Norman Geist.
>
>
>> -----Ursprüngliche Nachricht-----
>> Von: owner-namd-l_at_ks.uiuc.edu [mailto:owner-namd-l_at_ks.uiuc.edu] Im
>> Auftrag von Jim Phillips
>> Gesendet: Freitag, 6. April 2012 05:40
>> An: Gianluca Interlandi
>> Cc: NAMD list
>> Betreff: Re: namd-l: multicore versus net-linux
>>
>>
>> Multicore should be slightly faster and it uses less memory because
>> there
>> is only one copy of the molecular structure rather than 32.
>>
>> -Jim
>>
>> On Thu, 5 Apr 2012, Gianluca Interlandi wrote:
>>
>> > What is the advantage of the multicore version of charm++ versus net-
>> linux?
>> > Is multicore faster if I'm running for example on a 32-core magny-
>> Cours AMD
>> > node?
>> >
>> > Thanks,
>> >
>> > Gianluca
>> >
>> > -----------------------------------------------------
>> > Gianluca Interlandi, PhD gianluca_at_u.washington.edu
>> > +1 (206) 685 4435
>> > http://artemide.bioeng.washington.edu/
>> >
>> > Postdoc at the Department of Bioengineering
>> > at the University of Washington, Seattle WA U.S.A.
>> > -----------------------------------------------------
>> >
>
>
-- Chris Harrison, Ph.D. NIH Center for Macromolecular Modeling and Bioinformatics Theoretical and Computational Biophysics Group Beckman Institute for Advanced Science and Technology University of Illinois, 405 N. Mathews Ave., Urbana, IL 61801 http://www.ks.uiuc.edu/Research/namd Voice: 773-570-6078 http://www.ks.uiuc.edu/~char Fax: 217-244-6078
This archive was generated by hypermail 2.1.6 : Tue Dec 31 2013 - 23:21:54 CST