decent performance from G4 Macs?
David van der Spoel
spoel at xray.bmc.uu.se
Sun Apr 14 03:18:02 EDT 2002
On Sat, 13 Apr 2002, Jarrod Smith wrote:
>> is it just that the performance Apple brags about is strictly
>> in-cache, and/or when doing something ah specialized like
>> single-precision SIMD (altivec/velocity engine)?
>I've been making a foray into OS X on G4 hardware recently. After having
>compiled and benchmarked a couple of our compute-intensive codes, I have
>wondered the same thing...
>So far double-precision floating point has not impressed me in the least
>on the G4.
We have done some single precision (gcc with altivec code) tests using
our molecular dynamics code GROMACS. The results are on
the numbers are simulation time/real time, i.e. higher is better. The G4
is slightly slower than an Athlon (w 3DNow)/P3 (w SSE) at the same clock.
Havent't tested double precision yet.
Dr. David van der Spoel, Biomedical center, Dept. of Biochemistry
Husargatan 3, Box 576, 75123 Uppsala, Sweden
phone: 46 18 471 4205 fax: 46 18 511 755
spoel at xray.bmc.uu.se spoel at gromacs.org http://zorn.bmc.uu.se/~spoel
Beowulf mailing list, Beowulf at beowulf.org
To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
More information about the Beowulf