Re: [OMPI devel] Branching for 1.5.0

This should go ahead with right before the 1.5 changes, as discussed. Greg has put out the changes for testing several months ago, so there has been quite a while to test, and he has done quite a bit of testing himself. Rich - Original Message - From: devel-boun...@open-mpi.org

Re: [OMPI devel] Branching for 1.5.0

Rich and Rainer are encouraging me to follow through with this name change operation sometime in the near future. I understand people's concern that this touches a lot of source code files and has limited benefit other than aesthetical merits. 1. What evidence do you need me to provide in order

Re: [OMPI devel] -display-map behavior in 1.3

Easier than I thought...done in r21147 Let me know if that meets your needs Ralph On Mon, May 4, 2009 at 9:42 AM, Ralph Castain wrote: > Should be doable > > Since the output was going to stderr, we just let it continue to do so and > tagged it. I think I can redirect

Re: [OMPI devel] -display-map behavior in 1.3

Should be doable Since the output was going to stderr, we just let it continue to do so and tagged it. I think I can redirect it when doing xml tagging as that is handled as a separate case - shouldn't be too hard to do. On Mon, May 4, 2009 at 9:29 AM, Greg Watson

Re: [OMPI devel] -display-map behavior in 1.3

Ralph, I did find another issue in 1.3 though. It looks like with the -xml option you're sending output tagged with to stderr, whereas it would probably be better if everything was sent to stdout. Otherwise it's necessary to parse the stderr stream separately. Greg On May 1, 2009, at

Re: [OMPI devel] MTT tests: segv's with sm on large messages

Ralph Castain wrote: In reviewing last night's MTT tests for the 1.3 branch, I am seeing several segfault failures in the shared memory BTL when using large messages. This occurred on both IU's sif machine and on Sun's tests. Here is a typical stack from MTT: MPITEST info (0): Starting

Re: [OMPI devel] size of items in mca_osc_pt2pt_component.p2p_c_buffers

For the mailing lists -- Dorian found a bug here: our one-sided code assumes that the datatype will be "small" (i.e., a packed version of the datatype will fit within the eager limit fragment size in OMPI). Dorian's datatype is much larger than that, leading to an amorphous failure. I've

[OMPI devel] MTT tests: segv's with sm on large messages

Hi folks In reviewing last night's MTT tests for the 1.3 branch, I am seeing several segfault failures in the shared memory BTL when using large messages. This occurred on both IU's sif machine and on Sun's tests. Here is a typical stack from MTT: MPITEST info (0): Starting MPI_Sendrecv:

Re: [OMPI devel] Inherent limit on #communicators?

Hi Edgar, cid's are in fact not recycled in the block algorithm. The problem is that comm_free is not collective, so you can not make any assumptions whether other procs have also released that communicator. well, that's not quite correct. The MPI standard says the following about

Re: [OMPI devel] OS X compilation broken

Hi, the MTT results for Sun were due to missing errno.h. Regards, Rainer On Friday 01 May 2009, Ralph Castain wrote: > The problem is actually broader than OS-X. MTT shows failures on every > platform. > > There are two problems: > > 1. OS-X is missing a string.h header in pstat/darwin module >