On Apr 28, 2013, at 3:18 PM, Ross Walker wrote:
> In principal if the queuing system is setup correctly then it should
> automatically set OMP_NUM_THREADS to the correct value and any openmp code
> should obey that. This should also work with MPI in that if the user asked
> for 8 tasks and 1 task per core then they would be running with 8 MPI
> threads and OMP_NUM_THREADS would get set to 1. Most queuing systems know
> the difference between sockets, cpus and cores these days (although a lot
> still get confused over hyperthreads) and so it should in principle just
> work.
>
> Of course this is not true on desktop machines or systems without queues
> where the user will need to set OMP_NUM_THREADS themselves.
>
> All the best
> Ross
>
Answering both recent emails:
I did not know queueing systems concerned themselves with threads within
a process. Learn something new every day. Seems to me to lie outside
their domain, somehow, but obviously I should learn more before I comment.
I can imagine that somehow a queueing system might be useful within a
process, but that seems to not be very consistent to the whole concept of
openmp.
Bud Dodson
>
>
> On 4/28/13 4:10 AM, "David A Case" <case.biomaps.rutgers.edu> wrote:
>
>> On Sat, Apr 27, 2013, M. L. Dodson wrote:
>>>
>>>
>>> I don't know how widespread openmp support is among operating systems
>>> likely
>>> to be used for AmberTools installs, but if it is near universal, my
>>> opinion
>>> is that -openmp installs should be the default, not serial installs.
>>> This is
>>> because almost all modern CPUs are multicore, hence fit well with
>>> openmp.
>>
>> Our main concern in making this the default is/was that users might be
>> using
>> multiple cores when they weren't expecting to, potentially violating local
>> queue requirements, etc. But I'm cc-ing this to amber-developers, to get
>> other opinions. You are correct that certain types of workstation jobs
>> would
>> indeed be faster if users routinely made us of the openmp capabilties.
>>
>> ...thanks...dac
>>
>>
>> _______________________________________________
>> AMBER-Developers mailing list
>> AMBER-Developers.ambermd.org
>> http://lists.ambermd.org/mailman/listinfo/amber-developers
>
>
>
> _______________________________________________
> AMBER mailing list
> AMBER.ambermd.org
> http://lists.ambermd.org/mailman/listinfo/amber
--
M. L. Dodson
Business email: activesitedynamics-at-gmail-dot-com
Personal email: mldodson-at-comcast-dot-net
Gmail: mlesterdodson-at-gmail-dot-com
Phone: eight_three_two-five_63-386_one
_______________________________________________
AMBER mailing list
AMBER.ambermd.org
http://lists.ambermd.org/mailman/listinfo/amber
Received on Sun Apr 28 2013 - 14:30:02 PDT
