Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!sdd.hp.com!wuarchive!udel!nigel.ee.udel.edu!mccalpin From: mccalpin@perelandra.cms.udel.edu (John D. McCalpin) Newsgroups: comp.benchmarks Subject: Re: benchmarks and interprocedural optimization Message-ID: Date: 21 Mar 91 20:26:38 GMT References: <1991Mar21.184428.8226@convex.com> Sender: usenet@ee.udel.edu Organization: College of Marine Studies, U. Del. Lines: 31 Nntp-Posting-Host: perelandra.cms.udel.edu In-reply-to: metzger@convex.com's message of 21 Mar 91 18:44:28 GMT >>>>> On 21 Mar 91 18:44:28 GMT, metzger@convex.com (Robert Metzger) said: >>Article 326 of comp.benchmarks: >>Date: 3 Jan 91 15:46:45 GMT >>From: borasky@ogicse.ogi.edu (M. Edward Borasky) >>Even discounting blatant cheats like the ones I describe above, there >>is a wider issue here about how much COMPILE time a user is willing >>to expend for "perfect" compiles. It is possible using techniques of >>whole-program compiling to optimize out all the unnecessary checks in >>the LINPACK benchmark -- [....] Robert> CONVEX's experience with its new Application Compiler (performs Robert> interprocedural optimization on codes in written in FORTRAN and/or C) Robert> contradicts these assertions. I was told by a source within Convex that the Application Compiler did not, in fact, manage to eliminate all of the unnecessary checks in the level-1 BLAS routines used in the LINPACK code. The reason had something to do with being able to optimize expressions after the inlining, but not logical predicates -- though I never really understood the explanation. Is there a "definitive answer" from Convex on this? -- John D. McCalpin mccalpin@perelandra.cms.udel.edu Assistant Professor mccalpin@brahms.udel.edu College of Marine Studies, U. Del. J.MCCALPIN/OMNET