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 jsquy...@cisco.com For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/
