From: Santosh Kumar Chaudhary (skc_at_physics.iisc.ernet.in)
Date: Sat Dec 20 2014 - 01:53:14 CST
Yes, BluegeneL is very old, institute is trying to bring new one but for
now i have to deal with this. Will certainly ask the people who were aware
of the system and also we have some
GPU based clusters like
(Four AMD Quad-Core Opteron 8378 processors with 2.4Ghz clock speed,
Nvidia Tesla S1070 1U server with 4 GPU's operating at 1.296Ghz, Linux
(composed of five GPU nodes. Node fermi1 to fermi4 are composed of one
Intel(R) Xeon(R) CPU W3550 processor operating at 3.07 Ghz with 16Gb RAM,
one Nvidia C2070 GPGPU card and 1TB local disk space while node fermi5 has
one Intel(R) Xeon(R) CPU ES-2660 processor operating at 2.20Ghz with 64Gb
RAM, three Nvidia M2090 GPGPU cards and 300GB local disk space)
So, Will try to run the job in these clusters also.
Thanks and regards
> You do realize that BlueGene/L is a ten-year-old machine, right? Even
> when they were new no two machines ever had quite the same software
> environment, and virtually all of them are gone now so I would not expect
> anyone outside of your own institution to be able to help you. The
> individual processors were very slow and you will almost certainly get
> better performance running on any other machine that you have access to.
> On Wed, 17 Dec 2014, Santosh Kumar Chaudhary wrote:
>> Dear All,
>> I want to set-up NAMD simulation with amber forcefield in BlueGene.
>> are very less information on web to set up NAMD in bluegene. Please
>> me in this.
>> thanks and regard
>> Santosh Kumar Chaudhary
>> This message has been scanned for viruses and
>> dangerous content by MailScanner, and is
>> believed to be clean.
> This message has been scanned for viruses and
> dangerous content by MailScanner, and is
> believed to be clean.
-- Santosh Kumar Chaudhary Graduate Student Prof.K.Sekar's Lab Supercomputer Education and Research Center Rm.no-352, old CES Building Indian Institute of Science Bangalore - 560012 Ph No - 9739044199 -- This message has been scanned for viruses and dangerous content by MailScanner, and is believed to be clean.
This archive was generated by hypermail 2.1.6 : Wed Dec 31 2014 - 23:23:08 CST