Open MPI logo

Open MPI Development Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Development mailing list

Subject: Re: [OMPI devel] SC13 birds of a feather
From: Christopher Samuel (samuel_at_[hidden])
Date: 2013-12-03 19:54:13


-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

On 04/12/13 09:27, Jeff Squyres (jsquyres) wrote:

> 2. The MPI_T performance variables are new. There's only a few
> created right now (e.g., in the Cisco usnic BTL). But the field
> is pretty wide open here -- the infrastructure is there, but we're
> really not exposing much information yet. There's lots that can
> be done here.

Random thought - please shoot it down if crazy...

Would it make any sense to expose system/environmental/thermal
information to the application via MPI_T ?

For our sort of systems with a grab bag of jobs it's not likely
useful, but if you had a system dedicated to running an in house code
then you could conceive of situations where you might want to react to
over-temperature cores, nodes, etc.

cheers,
Chris
- --
 Christopher Samuel Senior Systems Administrator
 VLSCI - Victorian Life Sciences Computation Initiative
 Email: samuel_at_[hidden] Phone: +61 (0)3 903 55545
 http://www.vlsci.org.au/ http://twitter.com/vlsci

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.14 (GNU/Linux)
Comment: Using GnuPG with Thunderbird - http://www.enigmail.net/

iEYEARECAAYFAlKefTUACgkQO2KABBYQAh8pCACaAo1Bf+5mKHWT2ZLysWkSG9fs
Rc8An3H4NwI0MwqkGxG2PWMJ+4U/Vdsv
=2YN+
-----END PGP SIGNATURE-----