Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!uwm.edu!ux1.cso.uiuc.edu!ux1.cso.uiuc.edu!aglew From: aglew@dwarfs.crhc.uiuc.edu (Andy Glew) Newsgroups: comp.arch Subject: Re: 64 bits for times.... Message-ID: Date: 29 Aug 90 17:04:33 GMT References: <703@exodus.Eng.Sun.COM> <67633@sgi.sgi.com> <957@halley.UUCP> <1990Aug24.181208.29581@rice.edu> <41090@mips.mips.COM> <8526@tetons.UUCP> Sender: usenet@ux1.cso.uiuc.edu (News) Organization: University of Illinois, Computer Systems Group Lines: 14 In-Reply-To: bdg@tetons.UUCP's message of 29 Aug 90 15:42:57 GMT >A final important reason for high precision timers is to help >architects manage the software implementation. The cavalier way in >which OS types often treat timing facility implementation is only >exacerbated by letting them hide behind a coarse grain clock. If only the architects would give us a high precision timer, OSers would not treat timing (and accounting) cavalierly. But, when you create the high precision timer, you also have to budget for the OS development time necessary to undo years of reliance on low-precision timers because they were the only thing going. (Hi, Blaine! Just ribbing you...) -- Andy Glew, a-glew@uiuc.edu [get ph nameserver from uxc.cso.uiuc.edu:net/qi]