Open MPI logo

Open MPI User's Mailing List Archives

  |   Home   |   Support   |   FAQ   |  

This web mail archive is frozen.

This page is part of a frozen web archive of this mailing list.

You can still navigate around this archive, but know that no new mails have been added to it since July of 2016.

Click here to be taken to the new web archives of this list; it includes all the mails that are in this frozen archive plus all new mails that have been sent to the list since it was migrated to the new archives.

Subject: Re: [OMPI users] problème with MPI_FINALIZE
From: Jeff Squyres (jsquyres_at_[hidden])
Date: 2011-11-02 13:23:43


On Nov 2, 2011, at 10:34 AM, Durga Choudhury wrote:

> Any particular reason these calls don't nest? In some other HPC-like
> paradigms (e.g. VSIPL) such calls are allowed to nest (i.e. only the
> finalize() that matches the first init() will destroy allocated
> resources.)

I honestly don't remember the Forum's rationale for this; that's just the way it is.

Brian Barrett and I have a proposal up for to the Forum for making it permissible to call INIT multiple times, etc. We proposed it and it was generally well-accepted; we got some good feedback, so we need to revise the proposal and present it at the next meeting in January. I guarantee that nothing will happen with our proposal before SC. :-)

-- 
Jeff Squyres
jsquyres_at_[hidden]
For corporate legal information go to:
http://www.cisco.com/web/about/doing_business/legal/cri/