home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!zaphod.mps.ohio-state.edu!sdd.hp.com!hpscit.sc.hp.com!matthias
- From: matthias@nsr.hp.com (Matthias Kamm)
- Newsgroups: comp.sys.intel
- Subject: Re: Intel claims the Pentium is 64-bit! (who cares if it real
- Date: 17 Dec 1992 22:28:34 GMT
- Organization: Hewlett Packard Santa Clara Site
- Lines: 30
- Message-ID: <1gquuiINNiel@hpscit.sc.hp.com>
- References: <mortenk.140.724539763@dhhalden.no>
- NNTP-Posting-Host: hpmvd069.nsr.hp.com
- X-Newsreader: TIN [version 1.1.2 PL7]
-
- MORTEN KNUDSEN (mortenk@dhhalden.no) wrote:
- : In article <1992Dec10.003011.14950@news.tufts.edu> pmorvill@jade.tufts.edu (Paul Morville) writes:
- : >From: pmorvill@jade.tufts.edu (Paul Morville)
- :
- : Is the 8088 a 16 bit or 8 bit micro? I seem to remember that Intel's
- : referance manual described it as a 8 bit micro.
-
- The 8088 was a 8 bit "version" of the 16 bit 8086. When talking about
- a processor, you need to talk about internal architecture and external
- bus width. The 386SX is 32 bit internal, with a 16 wide bus.
-
- Don't assume 'SX' means 1/2 the internal bus width, though. The 486SX
- actually has the full 32 bit bus, but is missing the coprocessor ("actually"
- the 486SX is a product entirely conceived by a marketing manager!).
-
- I think it's like this. Anyone please correct me if I'm wrong...
-
- processor internal external coprocessor
- 8086 16 16 nope
- 8088 16 8 nada
- 80186 ? ? nix
- 80286 16 16 nyet
- 80386 32 32 na
- 80386DX same as 80386
- 80386SX 32 16 no
- 80486 32 32 yup
- 80486SX 32 32 nope *
-
- * to show what a scam intel pricing is, the first 80486SX's
- had the math coprocessor on chip, but disabled!
-