Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!think.com!zaphod.mps.ohio-state.edu!mips!ptimtc!nntp-server.caltech.edu!beyond!andrey From: andrey@beyond.caltech.edu (Andre Yew) Newsgroups: comp.sys.amiga.advocacy Subject: Re: AMIGA Message-ID: Date: 5 May 91 17:28:53 GMT References: <1991Jan11.225935.26086@mintaka.lcs.mit.edu> <1991May5.090207.6997@cunixf.cc.columbia.edu> Sender: news@nntp-server.caltech.edu Organization: California Institute of Technology, Pasadena Lines: 27 es1@cunixb.cc.columbia.edu (Ethan Solomita) writes: > As I understand it the 56001 is an integer chip and the >96001 is a floating-point chip. That is the primary difference. >Ray-tracing is certainly helped by the 96001, but digitized sound >certainly wouldn't be.a Actually, the 56001 can do fixed-point as well as integer. The problem with this is that as you get towards really small numbers, you can't just move your decimal point and still get the same number of significant digits, and so you start losing precision. Also, the range of fixed point numbers is more limited than floats. Another difference -- and I don't know if you'd consider this primary or not -- is the 32-bit addressing of 32-bit sized data. Compare this to the 56001 with only a 16-bit address bus and a 24-bit data bus. And the reason it's named the 96001 is because it uses 96 bits of precision internally when doing calculations. Of course, the 96001 runs at a much higher clock speed than the 56001. > -- Ethan >"Brain! Brain! What is Brain?" Andre -- Andre Yew andrey@through.cs.caltech.edu (131.215.131.169)