forum@abinit.org
Subject: The ABINIT Users Mailing List ( CLOSED )
List archive
- From: Paul Fons <paul-fons@aist.go.jp>
- To: forum@abinit.org
- Subject: IBM Blue Gene
- Date: Tue, 23 Jan 2007 18:27:07 +0900
Now that I just asked the question about the SR11000, I thought I would ask another quick question about another machine. I have been carrying out many body Green's function calculations on a IBM Blue Gene. This machine has batch queues with 2000 processors in it. Seeing the news of the recent parallelization of the fourier transform operation in 5.3 made me wonder if anyone had attempted to run abinit on a Blue Gene cluster. I have yet to try and was curious if there were any major road blocks. One possible problem is a maximum memory of 512 MB /mode (no virtual memory). Any opinions/experience? Dr. Paul Fons Senior Researcher National Institute for Advanced Industrial Science & Technology METI Center for Applied Near-Field Optics Research (CANFOR) AIST Central 4, Higashi 1-1-1 Tsukuba, Ibaraki JAPAN 305-8568 tel. +81-298-61-5636 fax. +81-298-61-2939 email: paul-fons@aist.go.jp The lines below are in a Japanese font 〒305−8568 茨城県つくば市東1−1−1 つくば中央第4 近接場光応用工学センター ポール・フォンス主任研究官 |
- IBM Blue Gene, Paul Fons, 01/23/2007
- Re: [abinit-forum] IBM Blue Gene, Anglade Pierre-Matthieu, 01/23/2007
- Re: [abinit-forum] IBM Blue Gene, Markus Franke, 01/23/2007
Archive powered by MHonArc 2.6.16.