[Forwarding for archival] -------- Original Message -------- Subject: Re: Subcommittee for Parallel Interface Definition: Global IDs Date: Wed, 17 Oct 2007 11:11:11 -0600 From: Devine, Karen D. <[email protected]> To: Carl Ollivier-Gooch <[email protected]> CC: Onkar Sahni <[email protected]>, Mark Shephard <[email protected]>, Kenneth Jansen <[email protected]>, Tim Tautges <[email protected]>, Vitus Leung <[email protected]>, Lori A. Diachin <[email protected]>, Jason Kraftcheck <[email protected]>, Knupp, Patrick <[email protected]> Carl: Thank you for your thorough review of extensions needed to support parts within the current interface. To get the discussions going (and remind people to review other's contributions), I'll offer the following questions/comments. First a general question: Is determining whether a handle is an entity set handle or a part handle left to the implementation? Or do we need to specify a convention?

1. The use of the root set in the serial interface can be viewed as a convention to allow us to query the whole database (in parallel, all data in an instance) and an entity set using the same function.

Let me make sure I understand. Do you mean that calling, say, iMesh_getNumOfType with the root set returns the global (across all processors) number of entities of a certain type? If so, I'm OK with this -- it fits with the definition of a root set -- but I wondered whether it caused other people heartburn. Lori, for example, said she used one root set per processor that provided local-to-the-processor info. Under this suggestion, local-to-the-processor info would be provided by an iPart, not the root set, right? Thanks again. Karen -- ================================================================ "You will keep in perfect peace him whose mind is steadfast, because he trusts in you." Isaiah 26:3 Tim Tautges Argonne National Laboratory ([email protected]) (telecommuting from UW-Madison) phone: (608) 263-8485 1500 Engineering Dr. fax: (608) 263-4499 Madison, WI 53706