Ralph,
Is there something I need to do to enable stdout/err encapsulation
(apart from -xml)? Here's what I see:
$ mpirun -mca orte_show_resolved_nodenames 1 -xml -display-map -np 5 /
Users/greg/Documents/workspace1/testMPI/Debug/testMPI
Fixed in r20288. Thanks for the catch.
On Jan 16, 2009, at 2:04 PM, Greg Watson wrote:
FYI, if I configure with --with-platform=contrib/platform/lanl/
macosx-dynamic the build succeeds.
Greg
On Jan 16, 2009, at 1:08 PM, Jeff Squyres wrote:
References: <78c4b4d7-d9bc-4268-97cf-8cbad...@
FYI, if I configure with --with-platform=contrib/platform/lanl/macosx-
dynamic the build succeeds.
Greg
On Jan 16, 2009, at 1:08 PM, Jeff Squyres wrote:
References: <78c4b4d7-d9bc-4268-97cf-8cbad...@computer.org> > <9317bd55-13a2-44be-bcc0-3e42e2322...@computer.org> <5cb48a5d-1ce3-48f7-889
References: <78c4b4d7-d9bc-4268-97cf-8cbad...@computer.org> <9317bd55-13a2-44be-bcc0-3e42e2322...@computer.org>
<5cb48a5d-1ce3-48f7-8890-c99239b0a...@lanl.gov> <22ebe824--47f1-a954-8b54536bf...@computer.org>
<6dda0348-96b4-4e3f-91b4-490631cfe...@computer.org>
<460591d2-bd7b-43ca-9b1
When I try to build trunk, it fails with:
i_f77.lax/libmpi_f77_pmpi.a/pwin_unlock_f.o .libs/libmpi_f77.lax/
libmpi_f77_pmpi.a/pwin_wait_f.o .libs/libmpi_f77.lax/libmpi_f77_pmpi.a/
pwtick_f.o .libs/libmpi_f77.lax/libmpi_f77_pmpi.a/
pwtime_f.o ../../../ompi/.libs/libmpi.0.0.0.dylib /usr/local/
We fixed the openib segv, but I forgot to followup about the timeouts
that I mentioned in my original mail.
The timeouts were from poorly-configured spawn tests. That is, I had
8 cores in the job and ran the spawn test on all 8 cores (all
aggressively polling). The spawn test then spawned
All looks good from my overnight runs with 1.3rc7.
Thumbs up for release.
On Jan 15, 2009, at 10:52 PM, Jeff Squyres wrote:
I did a large MTT run (about 7k tests) with the openib patch on rc6
and all came out good. I'll do the same run on rc7 -- the results
should be identical. Will post
w00t.
(translation: I believe that this is a Good Thing and should be put
back to the trunk when ready)
On Jan 16, 2009, at 7:19 AM, Terry Dontje wrote:
Just wanted to give an update. On a workspace with just the
predefined communicators converted to opaque pointers I've ran
netpipe an
Just wanted to give an update. On a workspace with just the predefined
communicators converted to opaque pointers I've ran netpipe and hpcc
performance tests and compared the results before and after the
changes. The differences in performance with 10 sample run was
undetectable.
I've also
