Path: utzoo!utgpu!watmath!clyde!att!osu-cis!tut.cis.ohio-state.edu!mailrus!nrl-cmf!ames!amdcad!sun!pitstop!sundc!seismo!uunet!mcvax!ukc!stl!stc!praxis!gauss!mph
From: mph@praxis.co.uk (Martin Hanley)
Newsgroups: comp.arch
Subject: Re: A simple question on RISC
Message-ID: <3343@newton.praxis.co.uk>
Date: 16 Nov 88 09:20:05 GMT
References: <6544@xanth.cs.odu.edu> <75577@sun.uucp> <1618@imagine.PAWL.RPI.EDU> <419@augean.OZ>
Sender: news@praxis.co.uk
Reply-To: mph@praxis.co.uk (Martin Hanley)
Organization: Praxis Systems plc, Bath, UK
Lines: 26

In article <419@augean.OZ> idall@augean.OZ (Ian Dall) writes:
>In article <75577@sun.uucp> khb@sun.UUCP (Keith Bierman) writes:
>>
>> Or if they (wizzbang instructions) got used, it was
>> so rare that it didn't matter. Or they got used, and it was slower
>> than some combination of simple instructions. Or all of the above.
>
>Can anyone tell me *why* some of these microcoded instructions were
>slower than a combination of simpler instructions on the same machine?
>-- 
> Ian Dall

I think, in general, the microcoded instructions tend to be more
general than the simple ones, and thus have more cases to consider.

Also, the decode path (is that the right term?) is shorter for a
non-microcoded instruction, and thus again is quicker. The difference
here is akin to the difference between machine code and interpreted
code, though of course the magnitudes of difference vary.

							Martin Hanley.

-------------------------------------------------------------------------------
| "I'm not a god, I was just       | This drivel was brought to you by:       |
| misquoted" - Lister, "Red Dwarf" |                        mph@praxis.co.uk  |
-------------------------------------------------------------------------------