<p>Hi everybody,</p><p>Sorry for a somewhat technical question, but I'd like to know which is the best way to run GROMACS on a SMP machine (in particular, a multicore PC). The (known) points of interest are:</p><p>- Does GROMACS support multithreaded execution & how efficient is it?
</p><p>- Should I rather use some kind of MPI & which (LAM/Open/MPICH) is better & why?</p><p>Surely, there's always the option to run two serial jobs instead with a greater efficiency, but having some means to boost the single job performance by something like
1.9x would be very useful...</p><p>Thanks in advance,</p><p>Vasilii</p>