[gmx-users] benchmarking results

vipin sachdeva vipin at cs.unm.edu
Sun Apr 8 07:55:51 CEST 2007


Hi,
    I was going over the benchmarking page, for single-node results on 
different platforms. I don't understand what are the numbers mentioned 
for each of the benchmarks ? Are they ps/day metric ? Also, what are the 
compilation flags used in each of the cases ? I would assume "-O3" with 
SSE/Altivec included for these results ? Were there also system 
specific options for each of these platforms ? In particular I am 
interested in ppc970/woodcrest numbers ? How many threads per node are 
being run for the Woodcrest or the other platforms on the benchmarking 
page? Is there any benefiton running single/multiple threads on
multi-core platforms ? Could someone help me with these questions ?


Regards
vipin



More information about the gromacs.org_gmx-users mailing list