Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!swrinde!zaphod.mps.ohio-state.edu!usc!snorkelwacker!apple!apple.com!pauls From: pauls@apple.com (Paul Sweazey) Newsgroups: comp.arch Subject: Re: What *should* architectural pointers point at? Message-ID: <10057@goofy.Apple.COM> Date: 6 Sep 90 00:35:53 GMT Sender: usenet@Apple.COM Organization: Apple Computer Lines: 24 References: <0887@sheol.UUCP> <11192@celit.fps.com> <2504@l.cc.purdue.edu> <11201@celit.fps.com> Whole issue of bit/byte/etc. address pointers reminds me alot of the big-endian vs. little-endian wars. Most (but not all) people argue for one or the other based on what they think is the "natural" structure. The idea of bit-address pointers was brought up as an architectural issue because the bit is the only non-arbitrary basic quantum of data in binary logic. This is a great academic excercise. I would also add data types of any bit length. For such a machine I want to know what kinds of hardware and software systems we might end up with. It is obvious to most that todays computing systems would not get faster by having the hardware support bit-level addressing, much less an infinite number of data types. But there are entire classes of systems that don't get explored (or even conceived of) because they don't map well into the architectural constraints of computing systems today . I am mildly surprised that brainstorms about revolutionary architectures are rare in comp.arch. We could be just a brainstorm away from the next killer-micro-wave. Paul Sweazey pauls@apple.com 408-974-0253