Return to BSD News archive
Newsgroups: comp.os.386bsd.bugs Path: sserve!newshost.anu.edu.au!harbinger.cc.monash.edu.au!bunyip.cc.uq.oz.au!munnari.oz.au!sgiblab!cs.uoregon.edu!usenet.ee.pdx.edu!fastrac.llnl.gov!lll-winken.llnl.gov!ames!olivea!charnel.ecst.csuchico.edu!yeshua.marcam.com!MathWorks.Com!news.duke.edu!concert!sas!mozart.unx.sas.com!torpid.unx.sas.com!sastdr From: sastdr@torpid.unx.sas.com (Thomas David Rivers) Subject: Re: FreeBSD 1.1.5.1 now benchmarks much slower... Sender: news@unx.sas.com (Noter of Newsworthy Events) Message-ID: <CtJsHy.99p@unx.sas.com> Date: Tue, 26 Jul 1994 12:39:34 GMT References: <MARK.1055.2E347ECA@ardsley.business.uwo.ca> Nntp-Posting-Host: torpid.unx.sas.com Organization: SAS Institute Inc. Lines: 23 In article <MARK.1055.2E347ECA@ardsley.business.uwo.ca> MARK@ardsley.business.uwo.ca (Mark_Bramwell) writes: ... > >The dhrystone benchmark is showing 1/2 the speed of what it was last week. [in FreeBSD 1.1.5.1]. > > >The machine is a p5-66. Should I recompile with some special switch to >activate the math chip support instead of the emulation lib or is it auto >sensing? > The dhrystone benchmark does not exercise floating point (there is a whetstone, and other benchmarks for that.) However, older versions of the dhrystone are quite dependent on the speed of strcmp()... newer versions aren't. Which version are you using? - Dave Rivers - -- Imagine Whirled Peas.