Path: utzoo!attcan!uunet!husc6!uwvax!oddjob!ncar!ames!mailrus!cornell!uw-beaver!teknowledge-vaxc!sri-unix!garth!smryan
From: smryan@garth.UUCP (Steven Ryan)
Newsgroups: comp.arch
Subject: Re: Memory latency / cacheing / scientific programs
Message-ID: <854@garth.UUCP>
Date: 1 Jul 88 21:03:38 GMT
References: <243@granite.dec.com> <779@garth.UUCP> <2033@pt.cs.cmu.edu> <11052@ames.arc.nasa.gov> <12259@mimsy.UUCP>
Reply-To: smryan@garth.UUCP (Steven Ryan)
Organization: INTERGRAPH (APD) -- Palo Alto, CA
Lines: 6

>        (It bothers me that people talk about per-function optimisation,
>or even per-module, as `global optimisation'.  Global means global,
>not function-level, not module-level.

I think it started out as local referring to basic block optimisation and
global as everything else (anything with a jump or label).