All of which are highly unlikely to be using Open MPI. Sandia won't be
maintaining the code anymore. Is ORNL or UTK willing to handle the
maintenance and testing for the 1.7 / 1.8 series? If not, that pushes me
towards wanting to remove it.
Brian
On 3/27/12 2:15 PM, "Aurélien Bouteiller" wrot
FWIW:
1. There were definitely some issues with binding to cores and process layouts
on Opterons that should be fixed in the 1.5.5 that was finally released today.
2. It is strange that the performance of barrier is so much different between
1.5.4 and 1.5.5. Is there a reason you were choosing
Outside of national labs, there must be some users also. Cray has sold a number
of XT4/XT5 in the industry.
Aurelien
Le 27 mars 2012 à 14:32, Shamis, Pavel a écrit :
> Probably ORNL-UT Kraken system still use it. I would not be so eager to
> remove it.
>
>
> Pavel (Pasha) Shamis
> ---
> Ap
Probably ORNL-UT Kraken system still use it. I would not be so eager to remove
it.
Pavel (Pasha) Shamis
---
Application Performance Tools Group
Computer Science and Math Division
Oak Ridge National Laboratory
On Mar 23, 2012, at 9:56 AM, Barrett, Brian W wrote:
> Hi all -
>
> This is not
For any archive readers or otherwise interested parties:
Apparently Ubuntu 11.10 onwards includes Open MPI 1.4.3 with an ARM patch
set different from mine. It was lacking a functional
opal_sys_timer_get_cycles() implementation.
There is an open bug being tracked through:
https://bugs.launchpad.ne
