Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!wuarchive!zaphod.mps.ohio-state.edu!lavaca.uh.edu!menudo.uh.edu!lobster!sugar!peter From: peter@sugar.hackercorp.com (Peter da Silva) Newsgroups: comp.sys.amiga.advocacy Subject: Re: NeXT/Amiga Flamage: Get a life. Message-ID: <1991Apr9.130150.23167@sugar.hackercorp.com> Date: 9 Apr 91 13:01:50 GMT References: <2o7G!rpe1@cs.psu.edu> <14026@helios.TAMU.EDU> <1991Apr6.194520.5865@cc.helsinki.fi> Organization: Sugar Land Unix -- Houston, TX Lines: 19 In article <1991Apr6.194520.5865@cc.helsinki.fi> jalkio@cc.helsinki.fi writes: > > Yeah...wait until you try to do some heavy disk activity while playing > > a score file on that DSP.... The DSP requires the *CPU* to feed it > > the sound data; it can't go get it on its own. > Uhh? Quite a hopeless argument here. So, you think NeXT's would be > better if they didn't have the DSP at all? No, they would be better if they had an operating system with the context switch and interrupt service times to support the DSP. The Amiga can play scores with no jerks and hesitations while doing heavy disk activity, or even while doing heavy CPU-dependent activity like ray-tracing... even on a 68000. Mach is not real-time, yet. There is work on a real-time Mach in progress, but I'm not holding my breath: real-time and virtual memory don't care for each other, and Mach is built on VM. -- Peter da Silva. `-_-' .