[Pw_forum] Use of pool

Gabriele Sclauzero sclauzer at sissa.it
Tue Feb 24 10:16:02 CET 2009


Contrary to what Axel usually says (but my experience is far little than his, so he is in 
the position to blame me) I do not believe that increasing the number of pools always 
gives a better timing for a given system. It depends on the system you are computing (of 
course...): how big is your supercell, how many electrons, how many k-points, how many 
bands...

My experience is that, when working with big supercells is better try to use one pool 
until you have a decent scaling and THEN start using more pools. If you have a smaller 
cell (and consequently many more k-points) and not many electrons (like a slab geometry 
with small periodicity), then using pools would be more beneficial.

However these timings may also depend on the configuration of your machine, i.e. how 
optimized are algebra and fft libraries and how fast are communications.

To have a more precise idea of what's going on you should have a detailed look at the 
timings at the end of pw output.

Last thing, you should be careful that increasing the number of pools you're increasing 
the memory request on your node (as well as the memory traffic on RAM and caches, I 
suppose), and that may also be a severe bottleneck to performance.

Regards

GS

Huiqun Zhou wrote:
> Dear list users:
> 
> I happened to test duration times of calculating the system I'm 
> investigating against number of pools used. There are totally
> 36 k points. But the results surprised me quite a lot. 
> 
> no pool:  6m21.02s CPU time,     6m45.88s wall time
> 2 pools:  7m19.39s CPU time,     7m38.99s wall time
> 4 pools: 11m59.09s CPU time,    12m14.66s wall time
> 8 pools: 21m28.77s CPU time,    21m38.71s wall time
> 
> The machine I'm using is an AMD box with 2 quad core shanghai.
> 
> Is my understanding of usage of pool wrong?
> 
> Huiqun Zhou
> @Nanjing University, China
> _______________________________________________
> Pw_forum mailing list
> Pw_forum at pwscf.org
> http://www.democritos.it/mailman/listinfo/pw_forum
> 

-- 


o ------------------------------------------------ o
| Gabriele Sclauzero, PhD Student                  |
| c/o:   SISSA & CNR-INFM Democritos,              |
|        via Beirut 2-4, 34014 Trieste (Italy)     |
| email: sclauzer at sissa.it                         |
| phone: +39 040 3787 511                          |
| skype: gurlonotturno                             |
o ------------------------------------------------ o


More information about the Pw_forum mailing list