Path: utzoo!attcan!uunet!seismo!ukma!tut.cis.ohio-state.edu!rutgers!cbmvax!mks From: mks@cbmvax.commodore.com (Michael Sinz - CATS) Newsgroups: comp.sys.amiga.hardware Subject: Re: (B) 68040 vs. gfx coprocessor Message-ID: <9568@cbmvax.commodore.com> Date: 1 Feb 90 20:22:47 GMT References: <1099@lpami.wimsey.bc.ca> Reply-To: mks@cbmvax.cbm.commodore.com (Michael Sinz - CATS) Organization: Commodore, West Chester, PA Lines: 32 In article <1099@lpami.wimsey.bc.ca> lphillips@lpami.wimsey.bc.ca (Larry Phillips) writes: >Yup.. lies, damned lies, and benchmarks. SPARCs are generally measured (by Sun >at least), in 'VAX MIPS', which is a measure of performance based upon a suite >of benchmarks, and using a VAX 11/780 as the 'base', considering it to be 1 >MIPS (Yes, Virginia, there is no singular form of MIPS). > >Motorola's MIPS rating takes a number of 'common' instructions and figures how >many it will do in a second, so the rating is completely different. If you want >to compare them, you can get a 'Motorola-like' MIPS rating of a SPARC (or any >other pure RISC chip) by looking at its clock frequency. ie. a 25 MHz SPARC is >25 MIPS. Ah, but 25 million SPARC instructions != 25 million 68040 instructions. It can take between 1 and 6 (or more) SPARC instructions to do the same thing as some of the 68040 instructions. That is why there is a VAX-MIPS (Meaningless Indicator of Performance) that is supposed to show "real" work with the 780==1. > >How fast are SPARCs and 68040s? Fast! Real fast! Damn fast! and even faster than that! (SPARC at 40MHz is FAST!!) > /----------------------------------------------------------------------\ | /// Michael Sinz -- CATS/Amiga Software Engineer | | /// PHONE 215-431-9422 UUCP ( uunet | rutgers ) !cbmvax!mks | | /// | |\\\/// When people are free to do as they please, | | \XX/ they usually imitate each other. | \----------------------------------------------------------------------/