Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!hellgate.utah.edu!caen!uakari.primate.wisc.edu!samsung!crackers!m2c!umvlsi!dime!yodaiken From: yodaiken@chelm.cs.umass.edu (victor yodaiken) Newsgroups: comp.arch Subject: Re: Computers for users not programmers Message-ID: <26337@dime.cs.umass.edu> Date: 8 Feb 91 20:48:04 GMT References: <13615@lanl.gov> <27AF17B9.72E2@tct.uucp> <5275@mentor.cc.purdue.edu> <27B19A39.321E@tct.uucp> <5437@mentor.cc.purdue.edu> Sender: news@dime.cs.umass.edu Reply-To: yodaiken@chelm.cs.umass.edu (victor yodaiken) Distribution: na Organization: University of Massachusetts, Amherst Lines: 31 In article Benjamin Chase writes: >[Warning: This is just article #N in the USENET series of >_Replies_To_Herman_Rubin. It is just like all the others. The >veteran reader may safely skip it. However, Herman _should_ read it.] > >hrubin@pop.stat.purdue.edu (Herman Rubin) writes: > >>That particular step is the first step of any trigonometric or exponential >>function computation when it is not known in advance that the argument is >>small. > >Providing hardware support specifically for these things is unwise. >The expected performance benefit does not justify the required >additional complexity of the hardware. Trigonometric and exponential >functions represent a minute fraction of the average instruction usage >of general purpose computers. We all understand that you are not >doing general purpose computing. We don't care. We are very sorry >that your computer usage represents a minority, and thus has less >clout when it comes time to design hardware, languages, etc., etc. > It might be more interesting to have a discussion about the diffculty of special purpose architectures and the appropriate achitectures for scientific computation than to have a discussion about marketing requirements. Programmable architectures, in which users could configure the machine for a particular algorithm have implications for architectures, programming languages and operating systems. I know that there have been some attempts at such architectures (mostly programmable pipelines), but would like to hear about current efforts and/or reasons why such designs would be good or bad ideas.