Re: [mpi-21] Ballot 4 - MPI_THREAD_FUNNELED - was Re: Attending, topics, etc
Greg - you are correct and I am a bit embarassed by my word choice. To "insure" can mean "to join with others to distribute or smooth risk". To "ensure" is to "make certain it will be so". Thanks Dick Treumann - MPI Team/TCEM IBM Systems & Technology Group Dept 0lva / MS P963 -- 2455 South Road -- Poughkeepsie, NY 12601 Tele (845) 433-7846 Fax (845) 433-8363 mpi-21-bounces_at_[hidden] wrote on 01/31/2008 05:56:55 PM:
On Thu, Jan 31, 2008 at 09:26:07PM +0100, Rolf Rabenseifner wrote:
Dick, I fully agree. I withdraw my proposals with OpenMP and come back to your text, adding the forward reference to MPI_IS_THREAD_MAIN:
MPI_THREAD_FUNNELED The process may be multi-threaded, but the application must insure that only the main thread makes MPI calls (for the definition of main thread, see MPI_IS_THREAD_MAIN).
By the way, this clarification is independent of any additional level of thread support taht may be specified in further MPI versions.
I also agree with this version of the clarification.
BTW, it should be "ensure", not "insure". The current MPI 2.0 doc has "ensure" 28 times and "insure" 0 times.
-- greg
_______________________________________________ mpi-21 mailing list mpi-21_at_[hidden] http://lists.cs.uiuc.edu/mailman/listinfo/mpi-21
*
participants (1)
-
unknown@example.com