Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!swrinde!zaphod.mps.ohio-state.edu!wuarchive!udel!rochester!pt.cs.cmu.edu!o.gp.cs.cmu.edu!TR5.GP.CS.CMU.EDU!spot
From: spot@TR5.GP.CS.CMU.EDU (Scott Draves)
Newsgroups: comp.arch
Subject: Re: speculative execution
Message-ID: <1990Oct12.182759.16989@cs.cmu.edu>
Date: 12 Oct 90 18:27:59 GMT
References: <42062@mips.mips.COM> <3445@bnr-rsc.UUCP>
Sender: netnews@cs.cmu.edu (USENET News Group Software)
Reply-To: spot@TR5.GP.CS.CMU.EDU (Scott Draves)
Organization: Carnegie Mellon University
Lines: 22

In article <3445@bnr-rsc.UUCP>, schow@bcarh185.bnr.ca (Stanley T.H.
Chow) writes:
|> In article <42062@mips.mips.COM> mash@mips.COM (John Mashey) writes:
|> >
|> >	a) The load is an uncached load to a volatile device register.
|> >	Hoisting is of course a no-no, as this will drive OS programmers
|> >	nuts, and in fact, must be carefully synchronized with
|> >	surrounding operations, or else.
|> 
|> This should not be particularly hard, just use "volatile" in C. (I know,
|> the zillions of lines of existing code may break, but as some people say -
|> those programs are brain-damaged :-).
|> 

that looks like a pretty good argument that this should be done by the
compiler rather than the hardware.  the same goes for the exception
stuff that other people have mentioned; a good compiler can determine
when exceptions are impossible and proceed to speculate.

			Consume
Scott Draves		Be Silent
spot@cs.cmu.edu		Die