[Wien] ifort (ifc) 8.0 and mkl 6.1

[L. D. Marks]

I don't know about the 3.2G numbers; I contributed the 3.4G numbers. You
can gain about 5% by using -mp1 -prec_div and another 5% or so by turning
on some of the ifc optimizations in ifc7.1 (some are on by default in
ifort) or ifort.

For long term stability I'm currently using -mp without the optimizations;
10-15% speed improvment is not worth the angst of inaccurate results. (It
would be nice to have some accuracy benchmarks to go with the speed
benchmark.)

On Thu, 10 Jun 2004, Veerle Vanhoof wrote:

> Dear Prof. Blaha,
>
> We did use mkl6.1, but I also tested the benchmark case with mkl7.0 and
> ifc7.1. Both give 270s for the benchmark.
> Is there maybe someone who already succeeded in reproducing the 228s on a
> 3.2 GHz P4, 512kB L2 with 400MHz without using ifort8.0?
>
> Thank you!
>
> Veerle Vanhoof
>
> ----- Original Message -----
> From: "Peter Blaha" <pblaha at zeus.theochem.tuwien.ac.at>
> To: <wien at zeus.theochem.tuwien.ac.at>
> Sent: Wednesday, June 09, 2004 2:55 PM
> Subject: Re: [Wien] ifort (ifc) 8.0 and mkl 6.1
>
>
> > > I have some problems with compiling wien2k with ifort8.0.
> > > We use a 3.2 GHz P4, 512kB L2 with 400MHz. Compiling with ifc7.1 and
> mkl6.1
> > > works fine, but the time we reach for the benchmark is 270s, while 228s
> > > should be possible with ifort8.0 instead of ifc7.1.
> >
> > I doubt that the differences in speed are due to the compiler. Most likely
> > they come from the mkl library. Are you sure you use mkl 6.1 ?
> > There is quite a difference between those two libraries (the newer mkl
> > should be as good as the "gotolib".
> >
> > I don't like (use) ifort8.0
> >
> >
> >                                       P.Blaha
> > --------------------------------------------------------------------------
> > Peter BLAHA, Inst.f. Materials Chemistry, TU Vienna, A-1060 Vienna
> > Phone: +43-1-58801-15671             FAX: +43-1-58801-15698
> > Email: blaha at theochem.tuwien.ac.at    WWW:
> http://info.tuwien.ac.at/theochem/
> > --------------------------------------------------------------------------
> >
> > _______________________________________________
> > 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
2225 N Campus Drive
Northwestern University
Evanston, IL 60201, USA
Tel: (847) 491-3996 Fax: (847) 491-7820
mailto:L-marks at northwestern.edu
http://www.numis.northwestern.edu
-----------------------------------------------