Ratified September 4 in Dublin, Ireland, MPI version 2.1 introduces modest changes to the standard in anticipation of more ambitious revisions expected in the next couple of years. According to MPI Forum Chairman Rich Graham of Oak Ridge National Laboratory’s National Center for Computational Sciences, the 600-page MPI 2.1 is primarily an attempt to clarify and correct errors in the 11-year-old standard.
Evidently the changes really are minor
“The 2.0 document has errors in it — typos and the like,” Graham noted. “It’s also not a single document. You sometimes have to look at several locations in the standard to find everything it says about a particular topic, so we made an attempt to bring those together so it’s easier to find.”
There are more revisions in the works. Bill Gropp at UIUC is heading up the MPI 2.2 revision targeted for mid-2009
Graham hopes the forum will decide on textual changes and application performance interfaces by the end of the year, with final ratification in mid-2009. He noted that those changes will also be relatively minor and easy to implement.
And then MPI 3.0, targeted for 2010
That standard will tackle a variety of issues, including remote memory access (the ability for one processor to write to another processor’s memory), fault tolerance (the ability to respond to a problem without crashing the application), and non-blocking collectives (methods for simplifying and improving communication within an application).
Fun MPI fact: I’m mentioned in the acknowledgements for the first edition of “Using MPI: Portable Parallel Programming with the Message-Passing Interface” by Gropp, Lusk, and Skjellum. I was in grad school at the time and working with Tony Skjellum. I ran some test code for him and he graciously mentioned me. Funny how small kindnesses stick with you over the years.