[Search for users] [Overall Top Noters] [List of all Conferences] [Download this site]

Conference 49.910::kav30

Title:VAX on VMEbus: KAV30
Notice:Could have been as fast as 68K but its a VAX!
Moderator:CSSVMS::KAV30_SUPP
Created:Thu Apr 18 1991
Last Modified:Fri Aug 02 1996
Last Successful Update:Fri Jun 06 1997
Number of topics:159
Total number of notes:645

112.0. "KAV30 & MEDULLA comparison" by MLN010::CASTELLUCCI (Aldo, TOEM MKTG, DTN: 793-2292) Thu Dec 23 1993 15:53

	I have been requested to compare CPU performanches 
	of KAV30 and MEDULLA.
	Data are available in this form:

	KAV30			2.7 VUPS

	MEDULLA  (21068)	30 SPECint92 /  50 SPECfp92
	MEDULLA+ (21066)	70 SPECint92 / 105 SPECfp92
	
	How to compare?
	Any help will be gratly appreciated.
	/Aldo
T.RTitleUserPersonal
Name
DateLines
112.1Hard to compare....BAYERN::WOLFFConformism is for little minds.Thu Jan 13 1994 09:4826
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