Re: mpb-mpi speedup vs. serial mpb

On Mon, 18 Dec 2006, nate lipkowitz wrote:
> which is pretty bad linearity with respect to the number of processors 
> involved. however this is also a pretty small job.  is this normal for 
> mpb-mpi calculations involving small jobs?  can i expect an improvement 
> with larger jobs, or should i dig into locally-specific issues like 
> interconnects or scheduling priorities and whatnot?

Yes, you should get more of an improvement with larger jobs.  Generally, I 
only use mpb-mpi for very large calculations, especially defect mode 
calculations.

If you want to parallelize small calculations you should look into 
mpb-split, which runs the different k points in parallel (see the manual).

Steven