[Bioclusters] mpiblast on SGI Altix

Joe Landman landman at scalableinformatics.com
Wed Mar 16 13:39:29 EST 2005


It should.  Basically mpiblast partitions the input and the databases.  NCBI
blast could use partitioned databases.  NCBI threads each search, rather than
across searches that MPIblast does.

--
Joseph Landman, Ph.D
Scalable Informatics LLC,
email: landman at scalableinformatics.com
web  : http://scalableinformatics.com
phone: +1 734 612 4615


---------- Original Message -----------
From: Jithesh <p.jithesh at qub.ac.uk>
To: "Clustering,  compute " farming & distributed computing in life science
informatics <bioclusters at bioinformatics.org>
Cc: mpiblast <mpiblast-users at lists.sourceforge.net>, Mike Muratet
<muratem at eng.uah.edu>
Sent: 16 Mar 2005 18:24:40 +0000
Subject: Re: [Bioclusters] mpiblast on SGI Altix

> Does mpiblast provide adavantage over the normal threaded version of
> NCBI BLAST on shared memory machines?
> 
> Jithesh
> 
> On Wed, 2005-03-16 at 17:48, Aaron Darling wrote:
> > Since XFS seems to provide these machines with extremely fast shared 
> > storage I would suggest setting your "Local" directory equal to the 
> > "Shared" storage directory.  Then you can avoid all the fragment copy 
> > overhead.
> > 
> > Also, a google for mpiblast sgi altix 
> > (http://www.google.com/search?q=mpiblast+sgi+altix) reveals what appears 
> > to be some excellent work done by folks at ORNL and NCSU to optimize 
> > mpiblast for the altix architecture.  It may be worthwhile to contact 
> > them for more  info...
> > They benchmarked version 1.2.1.  It would be interesting to see how 
> > their mpiblast benchmark results improve on an altix with shared and 
> > local set identical and with the --disable-mpi-db flag.
> > 
> > -Aaron
> > 
> > Joe Landman wrote:
> > 
> > >Hi Mike:
> > >
> > >  Make sure you configure mpiblast to use the shared memory device (ch_shmem)
> > >rather than the ethernet (ch_p4), or similar devices if you are using MPICH. 
> > >Dont worry about assignments of partitions to nodes, that should not be an
issue
> > >for this machine.
> > >
> > >Joe  
> > >
> > >--
> > >Joseph Landman, Ph.D
> > >Scalable Informatics LLC,
> > >email: landman at scalableinformatics.com
> > >web  : http://scalableinformatics.com
> > >phone: +1 734 612 4615
> > >
> > >
> > >---------- Original Message -----------
> > >From: Mike Muratet <muratem at eng.uah.edu>
> > >To: mpiblast-users at sourceforge.net, bioclusters at bioinformatics.org
> > >Sent: Wed, 16 Mar 2005 11:13:28 -0600 (CST)
> > >Subject: [Bioclusters] mpiblast on SGI Altix
> > >
> > >  
> > >
> > >>Greetings
> > >>
> > >>Does anyone have any experience with mpiblast on the SGI Altix and can 
> > >>you offer any suggestions for configuring jobs? The Altix 350 has 16-
> > >>CPU nodes with shared memory. The machine I'm using has 56 total CPUs. 
> > >>Can anyone offer any advice for how many database partitions to use, 
> > >>and how they get assigned to nodes/CPUs?
> > >>
> > >>Thanks
> > >>
> > >>Mike
> > >>
> > >>_______________________________________________
> > >>Bioclusters maillist  -  Bioclusters at bioinformatics.org
> > >>https://bioinformatics.org/mailman/listinfo/bioclusters
> > >>    
> > >>
> > >------- End of Original Message -------
> > >
> > >_______________________________________________
> > >Bioclusters maillist  -  Bioclusters at bioinformatics.org
> > >https://bioinformatics.org/mailman/listinfo/bioclusters
> > >  
> > >
> > _______________________________________________
> > Bioclusters maillist  -  Bioclusters at bioinformatics.org
> > https://bioinformatics.org/mailman/listinfo/bioclusters
> 
> _______________________________________________
> Bioclusters maillist  -  Bioclusters at bioinformatics.org
> https://bioinformatics.org/mailman/listinfo/bioclusters
------- End of Original Message -------



More information about the Bioclusters mailing list