Yes, I tried to add MPI_Barrier and it didn't work. The output is the same with the code without MPI_Barrier.
Any more thoughts? Thanks! Kong On Tue, Feb 22, 2011 at 12:23 PM, Bill Rankin <bill.ran...@sas.com> wrote: >> Hi, >> >> Thanks for the reply. But this can not solve the problem. > > Not sure if this was not your intended meaning (using "can not" instead of > "did not"), but did you try it? > >> The output indicate that both nodes hang at the second MPI_Wait, and >> no one can reaches the MPI_Finalize. > > Flushing the output from stdout and having it make it back to the terminal is > a little uncertain when one or more processes hangs or terminate abnormally. > You cannot rely upon completion in this case (someone correct me if I am > wrong here). > > -bill > > > >> >> >> *********************************************** >> >> >> Hello from processor 0 of 2 >> >> >> >> >> >> Received one message >> >> >> >> >> >> Hello from processor 1 of 2 >> >> >> >> >> >> Sent one message >> >> >> ******************************************************* >> >> Any other thoughts or suggestions? >> Thanks! >> >> Kong >> > > > > _______________________________________________ > users mailing list > us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/users > -- Xianglong Kong Department of Mechanical Engineering University of Rochester Phone: (585)520-4412 MSN: dinosaur8...@hotmail.com
