[Nek5000-users] problems running in parallel

nek5000-users at lists.mcs.anl.gov nek5000-users at lists.mcs.anl.gov
Tue Jun 10 12:38:19 CDT 2014


Hi,

Note also that sometime, for unknown reason, mpiexec does not work
correctly on certain platforms and you should use instead mpiexec.mpich2
That has solved the problem for me few months ago.

++
JC


2014-06-10 19:32 GMT+02:00 <nek5000-users at lists.mcs.anl.gov>:

> You seem to be running on a single proc. You have to start the program
> using one one of the scripts
>
> nekmpi
>
> or
>
> nekbmpi
>
> E.g.
>
> nekmpi jobname 4
>
> to run with 4 procs.
>
> praveen
>
>
> On Tue, Jun 10, 2014 at 7:23 PM, <nek5000-users at lists.mcs.anl.gov> wrote:
>
>> Dear users,
>>
>> I am trying to simulate the flow past a cylinder. If I run my simulation
>> with lelt=2000, lelg=2000 in 1 processor, everything works fine. However,
>> if I increase the resolution to lelt=4200 I get a compilation error.
>>
>> Following this post:
>>
>> http://lists.mcs.anl.gov/pipermail/nek5000-users/2013-April/002101.html
>>
>> I have seen that if I use more processors, the code compiles fine.
>>
>> However, now I am not able to run the code using 4 processors. I get the
>> following error:
>>
>>  Number of processors:           1
>>  REAL    wdsize      :           8
>>  INTEGER wdsize      :           4
>>
>>
>>   Beginning session:
>>   /SL/nek5_svn/test/cyl/cyl.rea
>>
>>
>>  timer accuracy:   1.1920929E-07 sec
>>
>>  read .rea file
>>
>>
>>   Beginning session:
>>   /SL/nek5_svn/test/cyl/cyl.rea
>>
>>
>>  timer accuracy:   9.5367432E-08 sec
>>
>>  read .rea file
>>  nelgt/nelgv/lelt:        4425        4425        2000
>>  lx1  /lx2  /lx3 :           5           5           5
>>
>>
>>   ABORT: Problem size too large!
>>
>>   This solver has been compiled for:
>>      number of elements/proc  (lelt):        2000
>>      total number of elements (lelg):        5000
>>
>>   Recompile with the following SIZE  parameters:
>>      lelt >=         4425  for np =            1
>>      lelg >=         4425
>>
>>
>>
>> I have a 3d mesh with 4425 elemnts. In the SIZE file I have set:
>>
>>
>>       parameter (ldim=3)
>>       parameter (lx1=5,ly1=lx1,lz1=lx1,lelt=2000,lelv=lelt)
>>       parameter (lxd=(3*lx1)/2,lyd=lxd,lzd=lxd)
>>       parameter (lelx=1,lely=lelx,lelz=lely)
>>
>>       parameter (lx2=lx1-0)   ! Pressure array dimensions
>>       parameter (ly2=ly1-0)
>>       parameter (lz2=lz1-0)
>>
>>       parameter (lx3=lx2)
>>       parameter (ly3=ly2)
>>       parameter (lz3=lz2)
>>
>>       parameter (lp = 4)  ! Max # processors
>>       parameter (lelg = 5000) ! Max # elements, total
>>
>>       parameter (lzl=3 + 2*(ldim-3))
>>
>> I have tried to follow this post to solve the problem, but I couldn't:
>>
>> https://lists.mcs.anl.gov/mailman/htdig/nek5000-users/
>> 2013-December/002411.html
>>
>> Could you help me, please?
>>
>> Regards,
>>
>> SL
>> _______________________________________________
>> Nek5000-users mailing list
>> Nek5000-users at lists.mcs.anl.gov
>> https://lists.mcs.anl.gov/mailman/listinfo/nek5000-users
>>
>
>
> _______________________________________________
> Nek5000-users mailing list
> Nek5000-users at lists.mcs.anl.gov
> https://lists.mcs.anl.gov/mailman/listinfo/nek5000-users
>
>


-- 
Jean-Christophe Loiseau
Homepage <https://sites.google.com/site/loiseaujc/>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/nek5000-users/attachments/20140610/07dc1918/attachment.html>


More information about the Nek5000-users mailing list