Path: utzoo!utgpu!news-server.csri.toronto.edu!mailrus!uwm.edu!cs.utexas.edu!uunet!cbmvax!daveh From: daveh@cbmvax.commodore.com (Dave Haynie) Newsgroups: comp.sys.atari.st Subject: Re: Atari TT 030 Launched! Keywords: Atari TT Message-ID: <12551@cbmvax.commodore.com> Date: 11 Jun 90 19:56:07 GMT References: <1990Jun5.143231.4977@watserv1.waterloo.edu> <13266@wpi.wpi.edu> <81214@tut.cis.ohio-state.edu> <1990Jun6.044350.20403@cbnewsh.att.com> <5503@jhunix.HCF.JHU.EDU> Reply-To: daveh@cbmvax (Dave Haynie) Distribution: usa Organization: Commodore, West Chester, PA Lines: 27 In article <5503@jhunix.HCF.JHU.EDU> jheddy@jhunix.UUCP (Jared Brennan) writes: > The 33% speed increase in Atari ST programs run on the TT has aroused >quite a bit of interest on the net recently, because this is rather minimal >compared to the speed increase expected given 2X clock rate, 2X data bus size, >caching, etc. However, I believe that the line A traps are real instructions >on the 68030, while they are invalid on the 68000, which allows them to be >used for ST graphics primitives. No, line A still forces an exception on the 68030. Mac uses them too, though I don't really know why; an exception is considerably more expensive than a subroutine call, even indirect subroutine calls such as used in Amiga libraries. They even produce the same exception stack frame, called type 0 in 68030 parlance (the 68000 only has one kind of exception stack frame). Now some F line instructions are used by the 68030; specifically, those for the MMU and FPU op-codes. Anyone who's used those for OS calls made a big mistake. >. . . Yet another shallow and badly thought-out opinion from: >Jared Brennan BITNET: JHEDDY@JHUNIX,JHUVMS -- Dave Haynie Commodore-Amiga (Amiga 3000) "The Crew That Never Rests" {uunet|pyramid|rutgers}!cbmvax!daveh PLINK: hazy BIX: hazy "I have been given the freedom to do as I see fit" -REM