Xref: utzoo comp.sys.dec:928 comp.arch:7871 Path: utzoo!attcan!uunet!lll-winken!ubvax!ardent!mrk!mac From: mac@mrk.ardent.com (Mike McNamara) Newsgroups: comp.sys.dec,comp.arch Subject: Re: DECstation 3100 info. Message-ID: <1798@ardent.UUCP> Date: 16 Jan 89 17:07:48 GMT References: <979@isieng.UUCP> <85330@sun.uucp> Sender: news@ardent.UUCP Reply-To: mac@mrk.ardent.com (Mike McNamara) Organization: Ardent Computer Corp., Sunnyvale, CA Lines: 27 In article vixie@decwrl.dec.com (Paul A Vixie) writes: |Keith Bierman of Sun writes: |# If you decide to buy a MIPS based processor, stick with one that is |# STANDARD comforming. Why make your life difficult. If you don't like |# the ISI, after a bit, you can go with someone else (MIPS, Ardent, |# etc.). If you don't like the 3100 upgrade choices, you're stuck with |# an OS AND processor change. | |This is just silly. Which STANDARDs? As I said above, the a.out and *.o file |format is different on almost every MIPS-based machine I know of. If someone |wants to compile something on an Ardent and run it on an ISI or SGI to prove |me wrong, go for it. | Ardent Titans and MIPSCO boxes and SGIs will *not* run each others a.outs, although things like /bin/file will recognize foriegn objects as native sons... And it makes sense, The Ardent Titan is up to four Mips R2000 each tightly intergrated with a custom vector processing unit. What do you expect an M120 to do when given an Ardent `dvma' instruction? (double precision A = B*C+D). (Probably bus error...). [I apologize if there appears to be an advertisment up there... ] [These opinons are my own, and all that... ] mac @ ardent.com