[Wien] MKL 10 linking

[Nils Huntemann]

Hello,

> A minor suggestion: can you please use the standard test from the
> WIen2k page for any timings you quote so everyone can compare them.

But this test is just for lapw1c, or not? I also have segmentation fault in lapw2.
Best regards,
Nils

> On Dec 13, 2007 2:36 AM, Andrey Sobolev <inconnu at list.ru> wrote:
> > Hello Andrzej,
> >
> > Sorry for delayed answer as I've been away from the mailing list a
> while. I've run some benchmarks on my computer (Intel Core2Duo T6400 @ 2.13 GHz,
> 1 GB RAM with Fedora 7) using my default and your pure layered compiler
> options. All programs compiled, linked and executed successfully with -O3
> -xT, including lapw2, so your problem should lie in some system (or 3rd party)
> libraries.
> >
> > The results of the benchmark (fccni as shown in the UG) are 24 secs with
> my default model vs. 21 secs with your pure layered model. What bothers me
> most is the difference in results - it needs 4 cycles to converge with my
> parameters and 3 cycles w/yours. I'd like to ask whether you observed such
> a behaviour in your benchmarks. Now I'll try other systems to see if the
> results obtained are significantly different.
> >
> > Cheers,
> > Andrey.
> >
> >
> >
> >
> > -----Original Message-----
> > From: awronka at uni.lodz.pl
> > To: wien at zeus.theochem.tuwien.ac.at
> > Date: Fri, 7 Dec 2007 17:04:08 +0100 (CET)
> > Subject: Re: [Wien] MKL 10 linking
> >
> > >
> > >      Hello Andrey,
> > >
> > >       I have performed a few quick benchmark runs to fccni example
> from
> > > user manual ("runsp_lapw   ce 0.0001  NI" for 3000 k points) for
> > > your default and my pure layered mkl10 linking models,  on my small
> > > home computers,  and stated as follows:
> > >
> > > 1.  I can  compile all programs on "-O3  -xX" optimization level, 
> except
> > > of lapw2 program, where  only "-O1  xX"  passed, in both cases of
> > > compilation,  and system parameter OMP_NUM_THREADS=2 passed on  pure
> > > layered linking only.
> > >
> > > 2.  Times of execution I obtained , were a little shorter for my pure
> > > layered linking model. Exactly,  it was 51 sec. for my and 1 min. 4
> sec.
> > > for your  linking settings,  on my 3.2 GHz Intel  Pentum  4, 1GB RAM
> (667
> > > HHz) stationary computer  with  Centos 5 operating system (1 min/1
> min. 10
> > > sec. on my Dell laptop   T5600 Core 2 Duo, 1.83 GHz with slow 5600 rpm
> > > hard disk and 2 GB RAM(667 MHz),  Suse 10.3).
> > >
> > > I do not know, why that "-O3" optimization crash for lapw2 on my
> systems.
> > > What about your benchmark results?
> > >
> > > Greetings,
> > >  Andrzej
> > >
> > >
> > >
> > > _______________________________________________
> > > Wien mailing list
> > > Wien at zeus.theochem.tuwien.ac.at
> > > http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien
> > >
> > _______________________________________________
> > Wien mailing list
> > Wien at zeus.theochem.tuwien.ac.at
> > http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien
> >
> 
> 
> 
> -- 
> Laurence Marks
> Department of Materials Science and Engineering
> MSE Rm 2036 Cook Hall
> 2220 N Campus Drive
> Northwestern University
> Evanston, IL 60208, USA
> Tel: (847) 491-3996 Fax: (847) 491-7820
> email: L-marks at northwestern dot edu
> Web: www.numis.northwestern.edu
> Commission on Electron Diffraction of IUCR
> www.numis.northwestern.edu/IUCR_CED
> _______________________________________________
> Wien mailing list
> Wien at zeus.theochem.tuwien.ac.at
> http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien

-- 
Psssst! Schon vom neuen GMX MultiMessenger gehört?
Der kann`s mit allen: http://www.gmx.net/de/go/multimessenger