home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!auspex-gw!guy
- From: guy@Auspex.COM (Guy Harris)
- Newsgroups: comp.arch
- Subject: Re: RISC goes CISC?
- Message-ID: <15394@auspex-gw.auspex.com>
- Date: 8 Nov 92 23:40:19 GMT
- References: <1992Nov6.092012.19239@rhein-main.de> <1992Nov8.193946.2210@cs.mcgill.ca>
- Sender: news@auspex-gw.auspex.com
- Organization: Auspex Systems, Santa Clara
- Lines: 23
- Nntp-Posting-Host: auspex.auspex.com
-
- > Intel is slowly finding that the CISC way of doing things is not
- >always optimal. Pipelining a CISC chip is painstaking brutal, and they
- >are thus focusing their efforts on the new Pentium chip, which will largely
- >be a RISC chip which can execute the 486 instruction set if need be.
-
- And, given that the *only* instructions that Pentium can execute, as far
- as I know, are 3andup86 instructions, it needs to be. (NOTE: there may
- well be some additions to the instruction set, just as the 486 added a
- couple of non-privileged instructions.)
-
- Do you, or does *anybody* else, have *any* solid evidence for the claim
- that I've heard advanced on occasion that the 586^H^H^HPentium really
- has a "native RISC mode" that can really execute "native RISC mode" code
- directly?
-
- NOTE: the claim that if you recompile code it may execute faster is not
- sufficient evidence for that claim; remember, Pentium is a superscalar
- chip, and may thus run code faster if instructions are scheduled
- differently.
-
- Neither are block diagrams with a big "RISC engine" block and a small
- "*86 compatibility" block evidence for that claim; the "RISC engine" may
- not expose its internals outside the chip.
-