Path: utzoo!attcan!uunet!cbmvax!bagate!dsinc!unix.cis.pitt.edu!zaphod.mps.ohio-state.edu!rpi!uwm.edu!ux1.cso.uiuc.edu!uxa.cso.uiuc.edu!lrg7030 From: lrg7030@uxa.cso.uiuc.edu (Loren Rittle) Newsgroups: comp.sys.amiga Subject: Re: A3000UX competition Message-ID: <1990Dec5.234035.23604@ux1.cso.uiuc.edu> Date: 5 Dec 90 23:40:35 GMT References: <6057@crash.cts.com> <1990Dec5.061558.21893@engin.umich.edu> Sender: news@ux1.cso.uiuc.edu (News) Organization: University of Illinois at Urbana Lines: 64 In an article seen not too long ago, Ralph writes: >In article eachus@linus.mitre.org (Robert I. Eachus) writes: >>In article <6057@crash.cts.com> seanc@pro-party.cts.com (Sean Cunningham) writes: >> Also there seems to be a defensive attitude about wait til the >>68040 Amigas get here... I saw a system with a GVP 50 MHz 68030, >>Video Toaster, multiple monitors, etc. over a month ago. A customer >>system, not a dealer demo. Ran a couple of (integer) benchmarks >>faster than the NeXT 040 demo machine. I guess it depends on which > >Preposterous. The 68040 at 25 MHz is MUCH faster than ANY 68030. I'd like >to see the benchmarks and results you used. What benchmarks did you use? Also, >please do not use pitiful benchmarks like dhrystones. Does anybody in the >Amiga community have SPECmarks for them? I'd love to see what they are. >I love the Amiga just as much as the next guy, but please do not post clearly >false results. I will dig up some benchmark code from somewhere and run it >on an 040 NeXT and then on a 50 MHz 030 Amiga and we'll see what we get. > > See ya, Ralph > >Ralph Seguin gilgalad@dip.eecs.umich.edu Actually not as preposterous as one NeXTer might think: (the facts as I see them :-) With identical memory sub-systems, Motorola has claimed that an '040 will run about 3-4 times faster than a like '030 system clocked at the same speed running the code, running under the same operating system! Sounds good to me, let's start here. 1) GVP's memory sub-system (on the A3001 card at least) is better than the orignal NeXT cube's memory sub-system. (I can and will send proof, if needed) Maybe NeXT improved the memory sub-system in the new design, who knows. In any event, GVP's was only slightly better, so I won't worry about it. :-) I'll give the NeXT the benifit of the doubt. 2) 040@25MHz vs. 030@50MHz, according to the above if these systems were running the same code under the same OS, we could expect the '040 system to be about 1.5 to 2 times faster. (Based upon seeing that CPU bound programs really do run twice as fast on GVP 030@50MHz vs GVP 030@25MHz) 3) Ah, now the wild-card, the OS! UNIX, even NeXT Mach has quite a bit of overhead even when just running normal user processes. AmigaOS being a multi-tasking OS has overhead also, of course, but it is on the order of 10% (Yes I have made some measurments myself!), as compared to 30% to 50% for UNIX (CS friend looked into this out at ISU when I was an undergrad there.) Let's not play a number game here, get out the UNIforum papers and look for yourself. Add all this up and what do we see: Yes, an Amiga with 030@50MHz running AmigaOS could compare to a NeXT 040@25MHz running UNIX. I can't wait for 040 boards for the Amiga when we will be able to see the 040 really fly. So see, Ralph, this statement that Sean makes is really not out of line. In terms of how responsive a system feels, AmigaOS wins hands down over UNIX (even UNIX running with GUI on a really big powerful and costly machine). Enjoy your new NeXT and leave the comments in comp.sys.next please! Loren -- ``In short, this is the absolute coolest computer device ever invented!'' -Tom Denbo speaking about The VideoToaster by NewTek ``Think about NewTek's VideoToaster! Now think about the Amiga!'' Loren J. Rittle lrg7030@uxa.cso.uiuc.edu