From owner-freebsd-chat Mon Mar 10 15:20:34 2003 Delivered-To: freebsd-chat@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 5043B37B401 for ; Mon, 10 Mar 2003 15:20:33 -0800 (PST) Received: from storm.FreeBSD.org.uk (storm.FreeBSD.org.uk [194.242.157.42]) by mx1.FreeBSD.org (Postfix) with ESMTP id 9233343FBD for ; Mon, 10 Mar 2003 15:20:31 -0800 (PST) (envelope-from mark@grondar.org) Received: from storm.FreeBSD.org.uk (Ugrondar@localhost [127.0.0.1]) by storm.FreeBSD.org.uk (8.12.7/8.12.7) with ESMTP id h2ANKTIo049088; Mon, 10 Mar 2003 23:20:29 GMT (envelope-from mark@grondar.org) Received: (from Ugrondar@localhost) by storm.FreeBSD.org.uk (8.12.7/8.12.7/Submit) with UUCP id h2ANKTgK049087; Mon, 10 Mar 2003 23:20:29 GMT X-Authentication-Warning: storm.FreeBSD.org.uk: Ugrondar set sender to mark@grondar.org using -f Received: from grondar.org (localhost [127.0.0.1]) by grimreaper.grondar.org (8.12.7/8.12.7) with ESMTP id h2ANHnIg074715; Mon, 10 Mar 2003 23:17:49 GMT (envelope-from mark@grondar.org) From: Mark Murray Message-Id: <200303102317.h2ANHnIg074715@grimreaper.grondar.org> To: Terry Lambert Cc: Peter Jeremy , chat@FreeBSD.ORG Subject: Re: cvs commit: src/lib/libc/i386/string Makefile.inc wcscmp.S In-Reply-To: Your message of "Mon, 10 Mar 2003 14:54:47 PST." <3E6D17B7.5FDCEAFC@mindspring.com> Date: Mon, 10 Mar 2003 23:17:49 +0000 Sender: owner-freebsd-chat@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Terry Lambert writes: > > I'm guessing that this means there will always be room for humans to > > hand-code assembler. How far can this be made redundant, given that > > there is still lots of effort going into hand-coded asm functions? > > I think that in all cases where it's possible, you want to have > C language equivalents. Yeah, they are slow, but they are also > portable. It's really a pain to try to go to a new architecture > when there's all this assembly language code lying around. At the > very least, you want there to be both platform independent and > platform dependent versions of the code. You are missing the point of my question. I _know_ a guru will aways eke out a bit more performance. What I'm asking is "what shape is the performance/effort curve for _compilers_?" and I'm leading towards "When, if ever, will compiler optimization be such that hand coding assembler for system libraries is a waste of time (on average)?" What I _really_ want to know is how much optimization is _not_ done, either because its too hard/slow, or because its too difficult to do. I also want to know how complete we think our optimization understanding is, ie whether there is lots of scope for research or we think we know most of the theory already. M -- Mark Murray iumop ap!sdn w,I idlaH To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-chat" in the body of the message