Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!think.com!paperboy!meissner From: meissner@osf.org (Michael Meissner) Newsgroups: comp.arch Subject: Re: Instruction Scheduling Message-ID: Date: 16 Apr 91 16:13:31 GMT References: <32097@shamash.cdc.com> <1991Apr8.224717.14402@aero.org> <1991Apr10.131341.26357@b11.ingr.com> <20632@cbmvax.commodore.com> Sender: news@OSF.ORG Organization: Open Software Foundation Lines: 21 In-reply-to: jesup@cbmvax.commodore.com's message of 15 Apr 91 07:39:35 GMT In article <20632@cbmvax.commodore.com> jesup@cbmvax.commodore.com (Randell Jesup) writes: | >One of the compilers I'm using actually does instruction reordering | >within the linker! | | That's the right place to do it! If you have deep pipelines, being | forced to make worst-case assumptions at routine entry can be quite limiting. | By doing reorganization in (or after) the linker, you know all the pre- | conditions a routine will have to deal with (unless someone takes it's | address, of course - then you go back to worst-case, unless you have a VERY | smart and lucky linker). Except of course if you are using object oriented techniques, and are calling through a function pointer. In which case, the linker has to fall back to the normal case of using fixed defaults. -- Michael Meissner email: meissner@osf.org phone: 617-621-8861 Open Software Foundation, 11 Cambridge Center, Cambridge, MA, 02142 Considering the flames and intolerance, shouldn't USENET be spelled ABUSENET?