And the svn ignore properties are missing:
? oshmem/shmem/c/profile/pshmem_addr_accessible.c
? oshmem/shmem/c/profile/pshmem_clear_lock.c
? oshmem/shmem/c/profile/pshmem_set_cache_line_inv.c
? oshmem/shmem/c/profile/pshmem_broadcast.c
? oshmem/shmem/c/profile/pshmem_w
On Linux, with oshmem enabled:
pinit_f.c:26:2: warning: #ident is a GCC extension
pshmem_init.c:31: warning: no previous prototype for 'pstart_pes'
pshmem_align.c:25: warning: no previous prototype for 'pshmemalign'
pshmem_align.c: In function 'pshmemalign':
pshmem_align.c:42: error: implicit decl
Thanks! I'll discuss it with the team and decide how best to handle this for
the 1.8 series. For 1.9, we plan to update to a newer hwloc version anyway.
On Apr 5, 2014, at 12:52 PM, Brice Goglin wrote:
> Hello Ralph,
>
> I took care of the defects under opal/mca/hwloc/hwloc172. Nothing
> impo
Hi,
it is not required by spec but we have a patch which is in the latest
stages of verification.
hope it will make into trunk this week.
M
On Tue, Apr 8, 2014 at 1:35 AM, Jeff Squyres (jsquyres)
wrote:
> Mike / Mellanox --
>
> Does does OpenShmem define that there should be a profiling interfa
Mike / Mellanox --
Does does OpenShmem define that there should be a profiling interface for SHMEM
API functions (like MPI does)?
On Mar 31, 2014, at 7:21 PM, Mike Dubman wrote:
> thanks, we will fix that.
>
>
> On Mon, Mar 31, 2014 at 5:04 PM, Ralph Castain wrote:
> Hmmm...I'll ask the Me
Also -- could you upgrade to Open MPI 1.8? It was released last week, and
should be much more ARM-friendly than Open MPI 1.6.x.
Also, I see some extra configure options. I suggest the following:
# I assume your --build and --host options are correct
# --disable-mpi-f77/f90 changed to --disable
I have just committed a script named contrib/check-help-strings.pl.
It can be used to check for simple show_help errors and warnings. I used it to
find/fix a bunch of warnings and errors in the opal tree and usnic BTL, but it
still find 181 warnings and 60 errors in the orte, ompi, and oshmem t
What: move the sensor framework from ORTE to the ORCM code repo, essentially
"svn delete" it from the OMPI code repo
Why: really isn't used or needed for supporting OMPI itself
When: barring objection, will execute on April 15
Basically, I just need to know if anyone other than myself is actu
