[gmx-users] Re: latest benchmarks (Itanium/Xeon/Opteron)
lindahl at csb.stanford.edu
Mon Jan 19 15:13:00 CET 2004
> On Mon, 2004-01-19 at 14:46, Michel Cuendet wrote:
>> The --disable-software-sqrt option doesn't help. I noted also that
>> gromacs single precision computes wrong results (box exploding
>> systematically), whereas double precision doesn't take more time and
>> gives more reasonable output.
> This shouldn't be... What system is that? Is it reproducible, i.e. the
> same tpr gives different results in single and double?
I think I've disabled software sqrt by default on ia64, so that
explains the lack of effect.
To help isolate the problem, check if it occurs:
(A) when you use gcc
(B) when you use a lower level of optimization (e.g. -O1)
Using the Intel Fortran compiler might give you slightly better
performance, otherwise you'll have to wait a *little* while longer for
the assembly loops.
>> IPO: performing multi-file optimizations
>> ../mdlib/.libs/libmd.a: could not read symbols: Archive has no index;
>> run ranlib to add one
>> Is there any simple way to work this out ?
> Hm, past experience with IPO on SGI machines taught me that there is
> nothing much to gain there. In particular since we don't really call
> functions from one module that would gain from inlining into another
>> P.S. : If needed, I could run benchmarks for developpers on either
>> opteron+myrinet or itanium2.
> Thanks, that will come in useful at some stage.
> 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
> gmx-users mailing list
> gmx-users at gromacs.org
> Please don't post (un)subscribe requests to the list. Use the
> www interface or send it to gmx-users-request at gromacs.org.
More information about the gromacs.org_gmx-users