[OMPI users] OMPI seg fault by a class with weird address.

2011-03-14 Thread Jack Bryan
Hi, I got a run-time error of a Open MPI C++ program. The following output is from gdb: --Program received signal SIGSEGV, Segmentation fault.0x2b3b0b81 in opal_memory_ptmalloc2_int_malloc () from

Re: [OMPI users] OpenMPI without IPoIB

2011-03-14 Thread Bernardo F Costa
Ok. Native ibverbs/openib is preferable although cannot be used by all applications (those who do not have a native ip interface). I suppose that if I configure my network nodes to use ipoib (by simply probing ib_ipoib module) I'd still be able to use native ibverbs interface without any delay

Re: [OMPI users] Number of processes and spawn

2011-03-14 Thread Ralph Castain
You can try running it as suggested here: http://www.open-mpi.org/faq/?category=running#mpirun-prefix On Mar 14, 2011, at 12:21 PM, Federico Golfrè Andreasi wrote: > > Thank you Jeff, > > my fault :( I didn't find that a link of that file was also mentioned in the > website page. > I was

Re: [OMPI users] Mac Ifort and gfortran together

2011-03-14 Thread David Robertson
Hi all, Sorry for the long Layoff on this but I have been dealing with other issues. I'll report what I've learned then answer Jeff's questions. First of all Doug Reeder is correct in saying the Apple supplied Open MPI is conflicting. Furthermore, it conflicts with both shared and static

Re: [OMPI users] Number of processes and spawn

2011-03-14 Thread Federico Golfrè Andreasi
Thank you Jeff, my fault :( I didn't find that a link of that file was also mentioned in the website page. I was able to build from the trunk the revision 24472. But when I try to run my program I still receive the error that Ralph told me is dued to version mismacth. How can I check which