Many thanks to everyone for the informative and helpful answers about
MPI-IO.
David
On 6/11/07, Ross Walker <ross.rosswalker.co.uk> wrote:
>
> > petascale machines and/or if you routinely run off NSF mounted disks
> > and/or if you run a really large system. We do worry about I/O
>
> Note if you are writing to a NFS filesystem MPI/IO likely won't help you
> anyway. If anything it will likely just slow things down. In this
> situation
> your only real option is to use binary trajectory files or reduce the
> frequency of trajectory writing to get the I/O load down.
>
> MPI/IO will only really help you if you have a decent SAN connected to
> each
> of your nodes with a decent parallel filesystem like GPFS or Lustre.
>
> Just my 2c...
>
> Ross
>
> /\
> \/
> |\oss Walker
>
> | HPC Consultant and Staff Scientist |
> | San Diego Supercomputer Center |
> | Tel: +1 858 822 0854 | EMail:- ross.rosswalker.co.uk |
> | http://www.rosswalker.co.uk | PGP Key available on request |
>
> Note: Electronic Mail is not secure, has no guarantee of delivery, may not
> be read every day, and should not be used for urgent or sensitive issues.
>
>
>
> -----------------------------------------------------------------------
> The AMBER Mail Reflector
> To post, send mail to amber.scripps.edu
> To unsubscribe, send "unsubscribe amber" to majordomo.scripps.edu
>
-----------------------------------------------------------------------
The AMBER Mail Reflector
To post, send mail to amber.scripps.edu
To unsubscribe, send "unsubscribe amber" to majordomo.scripps.edu
Received on Wed Jun 13 2007 - 06:07:27 PDT
