home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!darwin.sura.net!mips!mash
- From: mash@mips.com (John Mashey)
- Newsgroups: comp.arch
- Subject: Re: More P5 Speculation...
- Date: 23 Jul 1992 18:03:40 GMT
- Organization: MIPS Computer Systems, Inc.
- Lines: 27
- Distribution: usa
- Message-ID: <l6tt3sINNsl7@spim.mips.com>
- References: <1992Jul23.173724.14764@pony.Ingres.COM>
- NNTP-Posting-Host: winchester.mips.com
-
- In article <1992Jul23.173724.14764@pony.Ingres.COM> thall@Ingres.COM (Trevor Hall) writes:
- >According to today's San Jose Mercury News it looks like we're going to
- >get another quarter's worth of speculation on the P5 (where do you get
- >your information, John Mashey?). So I thought I'd start another round by
- Easy, I got one of those special newspaper subscriptions that
- delivers tomorrow's paper today :-)
- >referring everyone to the cover of the July 6 issue of EE Times.
-
- >On the cover there's a block diagram of the P5. It has the expected
- >units: I and D caches, bus, FP and SScalar RISC CPU. But there's one
- >I don't quite follow: Intel386 unit. Does this mean that the P5 will
- >be running some kind of emulation of x86 instructions? Is there a
- >"native" RISC instruction set that differs from the x86 instruction
- >set?
- Well, there are two obvious possibilities:
- 1) The microcode for the stuff that is difficult to hardwire,
- just as some S/370 models have had.
- 2) A "decoded instruction cache", i.e., where you fetch instructions,
- decode them into some more-easily-executed form [perhaps akin to
- RISC instructions, or perhaps more likely, into more horizontal
- microcode-like things], and then use the result to control the
- execution units.
- --
- -john mashey DISCLAIMER: <generic disclaimer, I speak for me only, etc>
- UUCP: mash@mips.com [soon to be mash@sgi.com, but not quite moved yet].
- DDD: 408-524-7015, or 524-8253
- USPS: (soon) Silicon Graphics, 2011 N. Shoreline Blvd, Mountain View, CA 94043
-