> If someone has a standard "benchmark" NEC input deck that is
>being used to quantify NEC performance on various platforms I can
>run it on a dual processor 167MHz UltraSparc 2 machine to provide
>another data point.
> (Also a stock 50MHz SparcServer 1000 and soon an
>85MHz SuperSparc powered SparcServer 1000e)
If we want to go around this loop, which I am sure we do I don't mind collating the results.
I think people will need to mention special optimisations.
I'll generate a reasonable structure and post it to the list later as I am just about to go home. Maybe about 1000 segments. Everyone ought to be able to run that sort of size. Although saying that everyone could run the little model given at the bottom of "NEC-4.1 performance on PC platforms". However I don't think this is a realistic test as we all run much larger models. Comments please.
Regards John B.
Received on Wed Apr 10 1996 - 21:50:00 EDT
This archive was generated by hypermail 2.2.0 : Sat Oct 02 2010 - 00:10:37 EDT