Path: utzoo!censor!geac!torsqnt!news-server.csri.toronto.edu!rutgers!cs.utexas.edu!wuarchive!zaphod.mps.ohio-state.edu!caen!gilgalad From: gilgalad@caen.engin.umich.edu (Ralph Seguin) Newsgroups: comp.sys.amiga Subject: Re: A3000UX competition Message-ID: <1990Dec8.044805.26886@engin.umich.edu> Date: 8 Dec 90 04:48:05 GMT References: <1990Dec5.061558.21893@engin.umich.edu> <676@storm.UUCP> Sender: news@engin.umich.edu (CAEN Netnews) Organization: University of Michigan Engineering, Ann Arbor Lines: 31 In article <676@storm.UUCP> bostrov@storm.UUCP (Vareck Bostrom) writes: >Though I do favor the NeXT over the Ami, I must say, that statement is >incorrect. The 68040 is NOT "MUCH" faster than ANY 68030, at least not >in interger performance. The 68040 / 25 gets around 23000 dhrys / second, Please do not base performance evluations on pathetic benchmarks like dhrystones. Something like ray-tracing, FFTs, massive matrix inversions, etc. Things that really accomplish something are a better indicator of speed. >POWER system, but hey, it runs AIX (puke here) so who cares!?). Kinda buggy isn't it :)? >Anyway, I can't wait for the 60 MHz 040. Or the 60 MHz POWER, for that >matter. Wouldn't that be interesting, as 20 MHz POWER blasts everything >already. Later. 60 MHz 040? Hmmm... you'll be waiting a long time. They did, after all just start shipping the 25 MHz. There are also many problems involved in producing chips with clockrates that high. Now for the ultimate: A professor here that I did some research for is currently working on a MIPS R2000 clone with a 4ns clock. For those of you who don't do inversions too well, a 4 ns clock is a 250 MHz clock. Make for a peppy DECstation :) See ya, Ralph Ralph Seguin gilgalad@dip.eecs.umich.edu 536 South Forest Apt. #915 gilgalad@caen.engin.umich.edu Ann Arbor, MI 48104 (313) 662-4805