home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!utcsri!newsflash.concordia.ca!mizar.cc.umanitoba.ca!bison!draco!gremlin!charles
- From: charles@gremlin.muug.mb.ca (Charles)
- Newsgroups: comp.sys.ibm.pc.hardware
- Subject: Re: Cyrix "486" cpu really compatible ?
- Message-ID: <1992Nov18.031830.10170@gremlin.muug.mb.ca>
- Date: Wed, 18 Nov 1992 03:18:30 GMT
- References: <1992Nov16.173224.3075@opus40.ix.de> <1992Nov17.012544.9122@reed.edu>
- Organization: The Haunted Unix Box
- Lines: 16
-
- rseymour@reed.edu (Robert Seymour) writes:
-
- > The Cyrix chip is not a true 486. I mean this in the sense that it does
- >not support all of the 486 features, not that it isn't made by Intel. An
- >example of this is the fact that NeXTstep 486 will not support the Cyrix chip,
- >since it uses instructions particular to the 486 (as opposed to just a 386
- >instruction set, which the Cyrix chip mirrors along with most 486
- >instructions).
-
- Could you elaborate on this? It is my understanding that the 486 only has
- 5-6 more instructions than the 386, most of those dealing with cache
- manipulation. What would NeXTstep be doing that wouldn't run on this
- chip? Or at the minimal, require extremely small code changes? (Assuming
- the Cyrix is 100% 386 compatible of course).
-
-
-