home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.benchmarks
- Path: sparky!uunet!sun-barr!cs.utexas.edu!uwm.edu!caen!destroyer!news.iastate.edu!help.cc.iastate.edu!willmore
- From: willmore@iastate.edu (David Willmore)
- Subject: Re: DEC ALPHA Performance Claims
- Message-ID: <willmore.722223190@help.cc.iastate.edu>
- Sender: news@news.iastate.edu (USENET News System)
- Organization: Iowa State University, Ames IA
- References: <BxH7s7.5Cv@inews.Intel.COM> <4248@bcstec.ca.boeing.com> <BxuCsv.FwE@pix.com> <willmore.722118562@help.cc.iastate.edu> <BxxwF1.D7q@metaflow.com>
- Date: Fri, 20 Nov 1992 01:33:10 GMT
- Lines: 33
-
- rschnapp@metaflow.com (Russ Schnapp) writes:
- >willmore@iastate.edu (David Willmore) writes:
- >>I don't expect that will be much of a problem with the Alpha.From the way the
- >>archetecture is designed, it looks like the most optimization and ordering takes
- >>place on-chip. The compiler orders things in a fairly general way which the CPU
- >>schedules. I wouldn't say that Alpha eliminates all code ordering problems, but
- >>it should be less effected than other archetectures. At least I hope so.
-
- >Are you sure you're talking about the 21064 implementation of Alpha? I
- >believe it's a very vanilla superscalar implementation (kind of an
- >oxymoron at this point, huh?). It doesn't do any of that far-out,
- >register-renaming, out-of-order stuff, as far as I know. Now, I do
- >know of another architecture that will do all this stuff, but I don't
- >want to be too self-serving here... 8-)
-
- I don't see any place in my post where I even mentioned the 21064. I
- was talking of the Alpha architecture specification. It doesn't promise
- anything that should get in the way of performance like many other
- vendors offer. The SPARC specification, on the other hand, has several
- problems which will limit the performance that can be attained without
- getting really ugly to implement. The way I see it, **opinion** only,
- is that the Alpha crew reapplied the RISC principals to what had been
- learned about RISC in the last, what, decade? I don't think that DEC is
- blowing smoke when they say 25 years. It would be a long haul, but it
- could be done. :) But, then again, we don't know what the future holds,
- certainly not that far into it.
-
- Just a few rambleings.
-
- See everyone later. I'm off for Thanksgiving for the next week.
-
- --David Willmore
- willmore@iastate.edu
-