[CPMD-list] how to speed up on amd64 machines

[Axel Kohlmeyer]

On Sun, 15 Apr 2007, Bin Pan wrote:

BP> Hi CPMD users,
BP> 
BP> I am wondering how to speed up CPMD runs on amd64 cluster using MPI 
BP> parallelization.
BP> Previously I compiled CPMD using pgi compiler with acml. However, I 
BP> found it is very slow.

what kind of problem (supercell size, number of atoms, number of 
electrons), how many nodes, what interconnect? how much memory
does it need, how much do you have?

please have a look at:
http://www.theochem.ruhr-uni-bochum.de/~axel.kohlmeyer/cpmd-bench.html#parallel
this may be a little outdated, but the fundamental truths are 
still the same. for parallel CPMD, the right interconnect is 
a key issue.


BP> The flags I used are:
BP> 
BP> CPPFLAGS = -P -C -traditional -D__Linux -D__PGI -DFFT_DEFAULT 
BP> -DPOINTER8 -D__pgf90 -DPARALLEL -DMYRINET
BP> CC = gcc -O2 -Wall -m64
BP> FC = pgf90 -c -fastsse -tp k8-64
BP> LD = pgf90 -fastsse -tp k8-64
BP> 
BP> Can you please let me know how to improve the performance?

drop the -fastsse and use

-tp=amd64 -pc=64 -O2 -Mnoframe -Munroll -Mcache_align

instead. but that will only give you a few percent speedup.

cheers,
   axel.

BP> Thanks a lot!
BP> 
BP> Best regards,
BP> Bin.
BP> 
BP> _______________________________________________
BP> CPMD-list mailing list
BP> CPMD-list at cpmd.org
BP> http://cpmd.org/mailman/listinfo/cpmd-list
BP> 

-- 
=======================================================================
Axel Kohlmeyer   akohlmey at cmm.chem.upenn.edu   http://www.cmm.upenn.edu
   Center for Molecular Modeling   --   University of Pennsylvania
Department of Chemistry, 231 S.34th Street, Philadelphia, PA 19104-6323
tel: 1-215-898-1582,  fax: 1-215-573-6233,  office-tel: 1-215-898-5425
=======================================================================
If you make something idiot-proof, the universe creates a better idiot.