[petsc-users] How to use PETSc4py/SLEPc4py to solve an eigenvalue problem in parallel

[Jose E. Roman]

El 30/10/2014, a las 04:52, Jed Brown escribió:

> Mengqi Zhang <jollage at gmail.com> writes:
>> It seems that the parallel running doesn't work, the elapsed time is
>> roughly the same. 
> 
> http://www.mcs.anl.gov/petsc/documentation/faq.html#computers
> 
>> You see that in the process of assembling the matrix in the parallel
>> case, the two cores are working according to
>> 
>>    from  0  to  8192  on rank  0
>>    from  8192  to  16384  on rank  1
>> 
>> but in the SLEPc phase, only rank 0 is working (the print command only
>> works for rank 0, but not for rank 1). 
> 
> That is just printing.  If every rank printed, you'd have a jumbled mess
> of output.
> 
> Always send the output of -log_summary if you have questions about performance.
> 
>> I also tried to run the ex1.py in parallel and in serial, the
>> computation times for a relative large matrix are also roughly the
>> same for the two runnings, or in some cases, parallel running is even
>> longer.
> 

As I mentioned in my first email, you need a parallel linear solver as discussed in section 3.4.1. Otherwise you won't see any parallel gain.
Jose