Okay, I see it - will fix on Fri. This is unique to master.
> On May 5, 2016, at 1:54 PM, Aurélien Bouteiller wrote:
>
> Ralph,
>
> I still observe these issues in the current master. (npernode is not
> respected either).
>
> Also note that the display_allocation seems to be wrong (slots_inu
Durga,
TCP doesn't need a specialized progress function because we are tied
directly with libevent. In your case you should provide a BTL progress
function, function that will be called at the end of libevent base loop
regularly.
George.
On Thu, May 5, 2016 at 11:30 PM, dpchoudh . wrote:
>
Hi all
Apologies for a 101 level question again, but here it is:
A new BTL layer I am implementing hangs in MPI_Send(). Please keep in mind
that at this stage, I am simply desperate to make MPI data move through
this fabric in any way possible, so I have thrown all good programming
practice out o
I have some good news: I have a fix!!
FWIW: I too can build w/ xlc 12.1 (also BG/Q).
It is just the 13.1.0 on Power7 that crashes building hwloc.
Meanwhile, 13.1.2 on Power8 little-endian does not crash (but is a
different front-end than big-endian if I understand correctly).
I started "bisectin
On May 5, 2016, at 5:27 PM, Josh Hursey wrote:
>
> Since this also happens with hwloc 1.11.3 standalone maybe hwloc folks can
> take point on further investigation?
I think Brice would love your assistance in figuring this out, since I'm
guessing he doesn't have access to these platforms, eith
Thanks. I can confirm that too. I have a power7 with xlc -qversion:
IBM XL C/C++ for Linux, V12.1 (5765-J03, 5725-C73)
Version: 12.01..
And it built v2.0.0rc2 fine.
Unfortunately, I don't have access to a power7 system with v13.1. We might
have to just make this in the release notes.
So
Ralph,
I still observe these issues in the current master. (npernode is not respected
either).
Also note that the display_allocation seems to be wrong (slots_inuse=0 when the
slot is obviously in use).
$ git show
4899c89 (HEAD -> master, origin/master, origin/HEAD) Fix a race condition when
Ok. I started a PR here:
https://github.com/open-mpi/ompi/pull/1639
I want to do a bit of testing (building now), but this should be an easy
fix.
Thanks
On Thu, May 5, 2016 at 3:07 PM, Jeff Squyres (jsquyres)
wrote:
> Agreed, this looks like an oversight.
>
> In dl.h, I even said that you c
Agreed, this looks like an oversight.
In dl.h, I even said that you could pass NULL as fname:
https://github.com/open-mpi/ompi/blob/master/opal/mca/dl/dl.h#L67
These asserts can safely be removed. Thanks!
> On May 5, 2016, at 3:40 PM, Josh Hursey wrote:
>
> We noticed that there is an a
We noticed that there is an assert(fname) in both of the dl components:
*
https://github.com/open-mpi/ompi/blob/master/opal/mca/dl/dlopen/dl_dlopen_module.c#L53
*
https://github.com/open-mpi/ompi/blob/master/opal/mca/dl/libltdl/dl_libltdl_module.c#L21
But according to the dl.h, NULL should be
Hi,
I came across this patch in OMPI opal.
https://www.open-mpi.org/community/lists/devel/2010/12/8819.php
I am looking to add similar support for armv8-A but I have a small query
regarding the implementation of *opal_sys_timer_get_cycles *for AMRv7-A.
It uses the Linux *times *function which ret
On 03/05/16 18:11, Paul Hargrove wrote:
> xlc-13.1.0 on Linux dies compiling the embedded hwloc in this rc
> (details below).
In case it's useful xlc 12.1.0.9-140729 (yay for BGQ living in the past)
doesn't ICE on RHEL6 on Power7.
All the best,
Chris
--
Christopher SamuelSenior Systems
12 matches
Mail list logo
