[gmx-users] parallel version of gromacs

[David van der Spoel]

On Thu, 18 Dec 2003, Maira d'Alessandro wrote:

>Hallo! 
>I made some tests about the performances of GROMACS when changing the number of
>processors, in the parallel version.
>I found different results in the energy from 1 to 10 processors.
>Do you know if it is well known? 

it is well known, but for double precision it should be small.



>Is it due to the implementation of gromacs parallel version or is it intrinsec
>with the hardware of clusters?
>The communications among processors is in single or double precision (I use
>always the double precision gromacs package)?
>If somebody knows, please give me some references about this problem.
>thank you to everybody.
>
>

-- 
David.
________________________________________________________________________
David van der Spoel, PhD, Assist. Prof., Molecular Biophysics group,
Dept. of Cell and Molecular Biology, Uppsala University.
Husargatan 3, Box 596,  	75124 Uppsala, Sweden
phone:	46 18 471 4205		fax: 46 18 511 755
spoel at xray.bmc.uu.se	spoel at gromacs.org   http://xray.bmc.uu.se/~spoel
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++