Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!uunet!auspex!guy
From: guy@auspex.auspex.com (Guy Harris)
Newsgroups: comp.arch
Subject: Re: Compilers and efficiency
Message-ID: <7738@auspex.auspex.com>
Date: 10 May 91 18:43:18 GMT
References: <9782@mentor.cc.purdue.edu> <653@ctycal.UUCP> <12054@mentor.cc.purdue.edu>
Organization: Auspex Systems, Santa Clara
Lines: 38

>> I have got to ask.  Why is it so generally important that the distance between
>> bits can be determined efficiently.  Note that I want to know, `why is it
>> important to ME, and to the general computing base?'.  This is the question
>> that hardware designers and compiler writers ask themselves.
>
>I believe most people are aware of the existence of simulation, including
>Monte Carlo, or Las Vegas, methods for obtaining answers to otherwise
>intractable problems.

Yes, but unless the person who posed the original question does those
kinds of simulations, it's not important to him, and unless a given
member of the general computing base does them, it's not important to
them, either.

I.e., you answered an interesting question, namely "tell me a use for
finding the distance to the next 1 in a bit stream", but you didn't
answer the question that was asked.

Now, there are other places where finding the distance to the next 1 in
a bit stream is useful.  It may well be that it's worth providing some
kind of hardware assist for it; I'm curious what forms of "hardware
assist" of that sort exist (other than doing it using the obvious
simple-minded loop, but in microcode).

Some questions then are "what other useful hardware would you have to
sacrifice, in some given implementation, to add the hardware assist for
'find next 1'?" and "will we, at some point, not have to sacrifice
anything really useful to get it?" so that you might want to put such an
operation into the instruction set anyway, and have a non-assisted
implementation early on.

(Is 'find next 1' similar enough to floating-point normalization that
the same hardware assistance can be used for both?"

BTW, I assume that by "most people" in "I believe most people are aware
of the existence of simulation..." you mean "most readers of this
group", which may well be true.  I don't know how "find first 1" comes
in handy for those simulations, though.