AW: [Wien] help on computer for WIEN2k calculation

[Rossitza Pentcheva]

Dear Wien2k users,

here is a benchmark for AMD Athlon64 x2 3800+ dual core with ifc9.0 and 
mkl running with Suse Linux 10.0 - 321 s.
I haven't checked the wien-benchmark on an SGI-Itanium-2 processor, but 
for other (bigger) cases  the Athlon had a surprizingly good performance 
which was even comparable that of an Itanium-2 CPU.
Best regards,
Rossitza Pentcheva

Peter Blaha wrote:

>I've put new benchmarks for AMD Opterons (directly made by SUN) and 
>Itanium-2 (made by SGI) on the benchmark page. "Nothing new" on the AMD 
>side, but surprisingly good numbers for Itanium-2 (122 sec on a single 
>processor). But beware, usually an Itanium-2 machine is several times 
>more expensive!
>
>I guess the whole discussion about AMD vs. Intel shoulds not be done as a 
>fight between two "religions". Take the code(s) which you want to use most 
>and test the timing. Take whatever is best for you! 
>And don't be surprised, that P4s (sometimes) win. Their theoretical 
>peakperformance is MUCH larger than that on Opterons, simply due to the 
>higher clock-frequency (typically 7200 vs 4800 GFlops). If a program can 
>use this and is not limited by some P4-bottlenecks (memory access), it 
>will be faster. 
>
>  
>
>>>an Intel cpu is significantly faster than AMD (160 vs 260 seconds, see
>>>benchmarks) !!
>>>      
>>>
>>I would appreciate if anybody with current AMD processors _and_ compiler
>>version could contribute benchmarks to the list - a lot of the present
>>entries are for old or unspecified versions of ifc, and furthermore ifc
>>seems to need some "help" to make full use of non-intel cpus, see
>>http://www.swallowtail.org/naughty-intel.html
>>
>>Martin
>>
>>-- 
>>Dr. Martin Kroeker            martin at ruby.chemie.uni-freiburg.de
>>c/o Prof.Dr. Caroline Roehr
>>Institut fuer Anorganische und Analytische Chemie der Universitaet Freiburg
>>
>>_______________________________________________
>>Wien mailing list
>>Wien at zeus.theochem.tuwien.ac.at
>>http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien
>>
>>
>>    
>>
>
>
>                                      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
>
>  
>


-- 

Dr. Rossitza Pentcheva
Department of Earth and Environmental Sciences    phone: +49 89 2180 4352   
Section Crystallography                 fax:   +49 89 2180 4334   
Ludwig-Maximilians-University Munich    e-mail: pentcheva.at.lrz.uni-muenchen.de
Theresienstr. 41         80333 Munich
            www: http://www.krist.geo.uni-muenchen.de/ober/pentche.htm

--------------------key:1-0.0735-11600-23.05--------------------