My checkout from Oct. 6 worked fine for most of the parallel tests ...
with the exception of the serial jobs that were called under MPI (as I
have noted in previous emails).
I have NOT checked in my proposed changes to the sander Makefile to
decouple EVB objects from executables that do not use EVB becasue I was
unable to get an appropriate baseline for the failures (too many
failures) to assure myself that I have not broken other stuff with my
modifications.
... so I think the tree was good up to Oct. 6?
-Kim
Ross Walker wrote:
>> This is for ifort 9.1.033 on emt64, and openmpi-1.1.1.
>> That's only one data
>> point, and Ross is apparently seeing problems too (although
>> his email didn't
>> give any details.)
>>
>
> If I checkout the cvs tree for 1st Oct 2006 it works fine with my setup.
> Ifort 9.1.039 and mpich2 v1.0.3. However, todays cvs tree is completely
> broken for parallel. I am currently trying to track down what changed.
>
> All the best
> Ross
>
> /\
> \/
> |\oss Walker
>
> | HPC Consultant and Staff Scientist |
> | San Diego Supercomputer Center |
> | Tel: +1 858 822 0854 | EMail:- ross.rosswalker.co.uk |
> | http://www.rosswalker.co.uk | PGP Key available on request |
>
> Note: Electronic Mail is not secure, has no guarantee of delivery, may not
> be read every day, and should not be used for urgent or sensitive issues.
>
>
Received on Sun Oct 15 2006 - 06:07:02 PDT
