home *** CD-ROM | disk | FTP | other *** search
- Xref: sparky comp.sys.amiga.programmer:17380 comp.sys.amiga.hardware:21547
- Path: sparky!uunet!spool.mu.edu!agate!doc.ic.ac.uk!uknet!edcastle!dcs.ed.ac.uk!jxp
- From: jxp@dcs.ed.ac.uk (Joe Potter)
- Newsgroups: comp.sys.amiga.programmer,comp.sys.amiga.hardware
- Subject: Re: CISC and RISC
- Message-ID: <BzAxFw.Is6@dcs.ed.ac.uk>
- Date: 15 Dec 92 12:59:56 GMT
- References: <70436@cup.portal.com> <amipb.04wr@amipb.gna.org> <37844@cbmvax.commodore.com> <Bz8FD1.Dxt@ns1.nodak.edu> <1992Dec14.155039.7747@ugle.unit.no>
- Sender: cnews@dcs.ed.ac.uk (UseNet News Admin)
- Reply-To: jxp@dcs.ed.ac.uk (Joe Potter)
- Organization: Laboratory for the Foundations of Computer Science, Edinburgh U
- Lines: 92
-
- In article <1992Dec14.155039.7747@ugle.unit.no> skogaas@solan.unit.no (John Olav Skog}s) writes:
- >RISC - reduced instruction set computer:
- >
- >Fewer and less complex intructions than in CISC processors
-
- Fewer and sometimes MORE complex, surely? Each instruction is very
- simple in its operation, but takes a complicated parameter. Look at the
- ARM series for a worst-case scenario!
-
- >Only one or two instruction formats (usually - results in fast decoding)
- >Large register file: 32-2048 internal registers
- >Few adressing modes (1-2 usually)
-
- Several for Load/Store Main Memory operations, few internal ones
- because there's only so much you can do with Reg <op> Reg to Reg!
-
- >Optimizing compilers (it is easy to generate good code for the RISC
- >architecture)
-
- Actually, I'm of the understanding that current compiler
- technology is rather left behind by the sheer complexity of RISC coding.
- It's easy to generate code for RISC machines, but getting turbopowered
- optimisations is hard. CISC is easier to optimise.
-
- >Support for high-level languages (when it comes to passing parameters etc.)
-
- I doubt it's that much better than CISC, just in keeping with
- the RISC philosophy (which is the old line about 20% of the instructions
- doing 80% of the code, so provide only 20% of a useable instruction set
- :-)
-
- >Hard-wired control unit
-
- As distinct from microcoded control? Hmm... What did the 6510
- use? Probably microcode as well, actually.
-
- >Optimized instruction pipeline
- >LOAD/STORE - architecture
-
- What's actually so good about this, by itself? Given all the
- other parts of RISC philosophy, great, but as a point by itself?
-
- >One clock-cycle pr. instruction
-
- Ideally. More usually four cycles, but with a four stage pipeline.
-
-
- >CISC - complex instruction set computer:
- >
- >Has a big software base (Amiga, Mac, DOS...)
- >The newest CISC processors are now using RISC techniques to archieve
- >performance (partly hardwired control-units, and one clock-cycle pr.
- >instruction). It may be easier to make op.sys.-software on a CISC processor.
-
- Source/destination operand address is more efficiently done via
- decoding circuitry anyway. If the source and dest. are not part of the
- opcode, that's the way they are decoded.
-
- >The code size for RISC-processors will usually be larger than it would be for a
- >CISC processor.
-
- RISC philosophy suggests that it won't be that much bigger.
-
- >Nowadays, it seems like that the RISC and CISC-prosessors are approaching each
- >other. The manufacturers incorporate RISC-features in CISC-processors and
- >visa versa.
-
- Yes, and hopefully the good points get copied, not the bad!
-
- Now perhaps we'll have something to do with the Amiga?
-
-
- >More interesting is multiprocessor-systems, with maybe thousands of processors.
- >Or just 16 68040's in a "hypercube" system. Such HyperCubes are at the moment
- >being developed at the Norwegian Institute of Technology. An early prototype,
- >16 i486 connected together (with local memory and disk), was capable to raytrace
- >a picture much faster than any other HyperCube in the world (i think it was by
- >a factor of 10). It was done in just a couple of seconds. Merging and sorting
- >two files were done 10-100 times the performance of a big mainframe. This system
- >was originally designed to be a fault-tolerant system, with at least two copies
- >of every byte on different disks. What about an Amiga HyperCube with 8 68040
- >processors with XX MB local memory...? :-) However, AmigaDOS would then have
- >to be rewritten quite a lot... Another Amiga model: Amiga NevroNet... :-)
-
- You first!
-
- Joe.
- Wondering why he didn't
- redirect this to the
- theory groups...
-
- "I SAID I'd like to BUY you a CHICKEN-LEG!"
-