[Beowulf] Re: vectors vs. loops
Many of your questions may have already been answered in earlier discussions or in the FAQ. The search results page will indicate current discussions as well as past list serves, articles, and papers.
Joe Landman landman at scalableinformatics.comThu Apr 28 08:08:53 PDT 2005
- Previous message: [Beowulf] Re: vectors vs. loops
- Next message: [Beowulf] Re: vectors vs. loops
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Mikhail Kuzminsky wrote: > In message from Joe Landman <landman at scalableinformatics.com> (Wed, 27 > Apr 2005 15:51:49 -0400): > >> Hi Art: >> >> Any particular codes you have in mind? I used to play around with >> lots of DFT (LDA) codes. Back then, large systems were 256 x 256, >> with periodic BC's. > > Most (practically all) DFT codes are not limited by eigenvalues > problem. The limiting stage is computation of 2-electron integrals and > fockian. For the systems we were studying, the rate limiting step was the eigenvalue extraction. We were using table lookups for the 2 and 3 center integrals. Then again, these were approximations built upon approximations ... -- Joseph Landman, Ph.D Founder and CEO Scalable Informatics LLC, email: landman at scalableinformatics.com web : http://www.scalableinformatics.com phone: +1 734 786 8423 fax : +1 734 786 8452 cell : +1 734 612 4615
- Previous message: [Beowulf] Re: vectors vs. loops
- Next message: [Beowulf] Re: vectors vs. loops
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
