home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.arch
- Path: sparky!uunet!ferkel.ucsb.edu!taco!gatech!darwin.sura.net!jvnc.net!yale.edu!qt.cs.utexas.edu!cs.utexas.edu!bcm!rice!miranda.cs.rice.edu!preston
- From: preston@miranda.cs.rice.edu (Preston Briggs)
- Subject: Re: RTX and SC32
- Message-ID: <Bx96zn.ME@rice.edu>
- Sender: news@rice.edu (News)
- Organization: Rice University, Houston
- References: <17131@mindlink.bc.ca> <1992Nov4.191038.12063@news.arc.nasa.gov> <CLIFFC.92Nov5101357@miranda.rice.edu>
- Date: Thu, 5 Nov 1992 17:23:47 GMT
- Lines: 25
-
- cliffc@rice.edu (Cliff Click) writes:
-
- >I try to compare a popular RISC (Sparc) to a hypothetical Forth machine,
-
- >An 8 bit opcode can reference the top 16 stack elements, so 32 bits can
- >do a "push r1", "push r2", "op", "pop r3" - basically imitate a 3-address
- >instruction. And I've seen the chip which can do all 4 in 1 50Mhz cycle
- >(really it was a 200Mhz internal clock). No Viking technology here, it was
- >under 33,000 transistors.
-
- I keep seeing stack machine proponents bragging about small numbers of
- transistors. Aren't most of the forth chips 16 bits (or 21 or
- whatever)? With no FP. And no support for virtual memory?
- Fine for embedded systems, nut you have to remember the greater
- functionality offered by the large transistor counts of a workstation
- CPU.
-
- Now about clock rates. A 50 MHz external clock, accomplishing 50 M
- 3 address equivalents. That's 1/4 of a 200 MHz Alpha, right?
-
- About pipelining...
- What are you going to do when you have to do FP?
- Spend several cycles per FP-ADD or pipeline?
-
- Preston Briggs
-