[mpi3-coll] Nonblocking collectives standard draft

Torsten Hoefler htor at cs.indiana.edu
Thu Nov 27 16:34:00 CST 2008

On Tue, Nov 25, 2008 at 04:56:31PM -0800, Greg Bronevetsky wrote:
> >> Having said that, I object to the text that explains the reasoning
> >> for removing MPI_Request_free on page 50 for exactly the reason
> >> above. We shouldn't have MPI_Request_free because its generally bad.
> >yes, I agree. I just wanted to stay consistent with the current standard
> >with the text, but I don't like it either. I think we can't say that
> >Request_free is generally bad, thu I chose this phrasing. However, I'm
> >very open to changes. Can you propose a better wording?
> Not really. I think that we should bring up removing MPI_Request_free 
> before the community as a whole during the next face-to-face meeting. 
> If they agree to remove it, we'll have our wording.
There is already a ticket for MPI-2.2 to deprecate it. However, there
was some discussion. We will discuss this again at the next meeting.
Until then, I just leave the text as is. Please let me know if you have
a proposal for better wording.


 bash$ :(){ :|:&};: --------------------- http://www.unixer.de/ -----
Torsten Hoefler       | Postdoctoral Researcher
Open Systems Lab      | Indiana University    
150 S. Woodlawn Ave.  | Bloomington, IN, 474045, USA
Lindley Hall Room 135 | +01 (812) 855-3608

More information about the mpiwg-coll mailing list