[gmx-users] GROMACS & Speed

[David van der Spoel]

Omololu Akin-Ojo wrote:
> Hi,
> 
> i use GROMACS & i like it because it is so fast. But, i would like to 
> know if GROMACS "cut corners" ? Otherwise, why is it is so fast?
> if you have a fortran compiler on an Opteron box, GROMACS does not use 
> the assembly loops. Right? So, why is it blazingly fast?
> 
> o.

gromacs does not cut corners...
Most important we do not compute stuff that we know will give zero as a 
result anyway, this gives 20-30% compared to other codes.
Single precision is a factor of two faster than double, assembly is a 
factor of two faster than C/Fortran, and finally our innerloops are 
completely unrolled, this probably also gives a factor of 1.5.
So if you multiply it all you have a significant factor (even in double 
precision).


> 
> ------------------------------------------------------------------------
> Sponsored Link
> 
> Try Netflix today! With plans starting at only $5.99 a month what are 
> you waiting for? 
> <http://clk.atdmt.com/NFX/go/yhxxxnfx0020000913nfx/direct/01/>
> 
> 
> ------------------------------------------------------------------------
> 
> _______________________________________________
> gmx-users mailing list    gmx-users at gromacs.org
> http://www.gromacs.org/mailman/listinfo/gmx-users
> Please don't post (un)subscribe requests to the list. Use the 
> www interface or send it to gmx-users-request at gromacs.org.
> Can't post? Read http://www.gromacs.org/mailing_lists/users.php


-- 
David.
________________________________________________________________________
David van der Spoel, PhD, Assoc. 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://folding.bmc.uu.se
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++