Path: utzoo!utgpu!news-server.csri.toronto.edu!mailrus!iuvax!cica!tut.cis.ohio-state.edu!zaphod.mps.ohio-state.edu!usc!snorkelwacker!bu.edu!xylogics!transfer!crackers!m2c!umvlsi!dime!dime.cs.umass.edu!moss From: moss@cs.umass.edu (Eliot Moss) Newsgroups: comp.arch Subject: Re: Timers on Suns/Sparcs Message-ID: Date: 11 Jun 90 20:04:28 GMT References: Sender: news@dime.cs.umass.edu Reply-To: moss@cs.umass.edu Distribution: usa Organization: Dept of Comp and Info Sci, Univ of Mass (Amherst) Lines: 17 In-reply-to: ramamurb@turing.cs.rpi.edu's message of 11 Jun 90 18:13:01 GMT While I do not experience with these *particular* machines, I do have experience with VAXStations and DECStations, and suspects Suns and SparcStations are similar. Though the time is stated in units down to microseconds on many machines, the actual update frequency is multiple of milliseconds, generally on interval timer ticks used for time slicing. Typical granularities are 10 to 50 milliseconds. To get accurate timings you usually have to average over *many* events and you have to be careful not to get synchronized with the interval timer ticks. (Sigh; for those of use who like to measure performance, coarse granularity clocks are a real pain!) -- J. Eliot B. Moss, Assistant Professor Department of Computer and Information Science Lederle Graduate Research Center University of Massachusetts Amherst, MA 01003 (413) 545-4206; Moss@cs.umass.edu