Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!sdd.hp.com!spool.mu.edu!munnari.oz.au!bruce!labtam!eyrie!asgard!bart From: bart@asgard.pub.uu.oz.au (John Butcher) Newsgroups: comp.sys.amiga.programmer Subject: Re: Short Hello World Message-ID: <1928199b.ARN045c@asgard.pub.uu.oz.au> Date: 17 May 91 21:26:35 GMT References: <1804@tardis.Tymnet.COM> <1991May7.001146.1830@cinnet.com> <19216341.ARN0401@asgard.pub.uu.oz.au> Organization: Private Lines: 33 In article , Matthew Dillon writes: Matt> sub.l D0,D0 is not faster than moveq.l #0,D0 on a 68000. The two Matt> instructions are both one word long. Me> What you say is right, but the reasons behind it are worng. ( wrong even ;-) Me> Instruction length != instruction timing : Me> sub.l d0,d0 == 6 ( or is it 8 ?? ) Me> moveq.l #0,d0 == 4 Matt> Huh? I said that sub.l D0,D0 is not faster than moveq.l #0,D0 on a Matt> 68000 even though they are the same size. Matt> Matt> I NEVER said that instruction length == instruction timing. In fact, Matt> my original statement says the exact reverse. Ah ha, now I know what you ware getting at, it's all crytal clear, what I understood the original 2 lines to mean were something along the lines of "Instruction 1 is not faster than Instruction 2 because they are both 1 word long, and hence the same speed", which is not what you meant ! - I dont agree that your original comment meant exactly the opposite of what I said it did however - it was not clear what you were saying about timing except that sub.l is slower than moveq.l Anyway, it isnt really important, since we both agree that length != time, and sub.l is slower than moveq.l ----------------------------------------------------------------------------- John Butcher : bart@asgard.pub.uu.oz.au ..!munnari!eyrie.oz.au!asgard!bart ``Life! Don't talk to me about life.'' - Marvin the Paranoid Android