home *** CD-ROM | disk | FTP | other *** search
- Xref: sparky comp.sys.amiga.programmer:17555 comp.sys.amiga.hardware:21796
- Path: sparky!uunet!uunet.ca!geac!zooid!tndb!jimomura
- From: jimomura@tndb.UUCP (Jim Omura)
- Newsgroups: comp.sys.amiga.programmer,comp.sys.amiga.hardware
- Subject: Re: CISC and RISC
- Distribution: world
- Message-ID: <jimomura.02k4@tndb.UUCP>
- References: <amipb.04wr@amipb.gna.org> <37844@cbmvax.commodore.com> <Bz8FD1.Dxt@ns1.nodak.edu> <BzByvD.FA9@news.cs.andrews.edu> <1gnl0mINNpq2@crcnis1.unl.edu> <1992Dec16.185521.21232@ichips.intel.com>
- Date: 18 Dec 92 09:08:59 EST
- Organization: Not an Organization
- Lines: 52
-
- In article <1992Dec16.185521.21232@ichips.intel.com> tjehl@sedona.intel.com (Timothy Jehl) writes:
- >
- >In article <1gnl0mINNpq2@crcnis1.unl.edu>, tbills@cse.unl.edu (Trent Bills) writes:
- >>
- >> |> >What are the advantages of CISC and RISC?
- >>
- >> RISC is based on several observations made by looking at compiler generated
- >> code. The first is that compiler writers have great difficulty in trying
-
- ...
-
- > There is one (and only one) reason for RISC processors : clock speed.
- >There is absolutely no advantage to having a lesser instruction set unless
- >you can make the device run faster.
-
- ...
-
- > On the die area front, we are rapidly reaching the point where the
- >computational logic on a high end processor is being dwarfed by the
- >on chip storage. Minor area savings in the computation are becoming
- >less important, so expect 1) RISC processors to become more complex,
- >as the process technology becomes available to allow high speed operation
- >while performing complex tasks, and 2) CISC processors to move to both
- >super-scaler and super-pipeline as the processing area becomes cheaper.
- >In addition, expect the instructions sets of both types of processors to
- >start expanding to allow conditional execution commands. As the pipelines
- >get deeper, the penalty for branches get more expensive. Instructions
- >which allow you to do conditional execution without branching will become
- >vital to maintain code throughput.
-
- ...
-
- Putting this into context, with the current trend to multiple
- processing to handle graphics and sound (DSPs are coming), you can
- isolate the various processors to an extent, but there are going to
- be times where the various busses are going to be the main bottlenecks.
- Fancy DMA schemes will have to be used to optimize the resolution
- of the contentions. But the less a processor needs to access the
- buss the better. Well now, doesn't it sound like a good idea if
- I can have 1 instruction that requires 2 buss cycles, leaving the
- buss free for the graphics or sound processors, while the CPU does
- the work of maybe 3 or 4 instructions? Superscalar is going to mean
- even more buss contention problems for such situations. So at bottom,
- there are going to be a lot of good reasons to have CISC processors
- in some systems. In fact, I expect we have seen the last of the
- "everbody will either have either type X or type Y CPUs" and there
- are going to be a fairly wide range of processors commonly used.
-
- --
-
- Jim Omura, (416) 652-3880
- 'jimomura@lsuc'
-