| You compare two very different processors.
1) when you talk about SPECfp's in the context of Medulla, then you should
also say what kind of FP you want to use. Alphs can do IEEE floating
point what most of the VME boards will either understand or generate
The KAV30 does not do IEEE floating point, but only VAX floating point
So you can say Medulla is indefinite faster then KAV30 with respect to
IEEE FP. Or you can compare the VAX floating point to LCA VAX
compatible floating point in which case you loose again since most VAX
compilers will generate VAX D-Floting instructions which are not implemented
in Alpha - so nothing to compare.
It is however fairly save to say: Medulla is a lot faster then KAV30
2) It is not really a good idea to compare SPECs with VUPS. I would guess, but
don't quote me on that, that Medulla is in the order of 10 to 30 times faster
then KAV30 which really means CPU performance. What you need to look at on
a VMEbus like module is bus thoughput and that's for Medulla not known today.
Your application need to get the data first it computes on, so for the
performance assesment raw CPU power is meaningless.
3) I have answered the questions, however you should not talk about
unannounced products in an open notesfile, this is a general policy which
everyone should adhere to. If you need more information send me mail.
Julian
|