From owner-freebsd-hackers Tue Dec 19 18:30:32 2000 From owner-freebsd-hackers@FreeBSD.ORG Tue Dec 19 18:30:31 2000 Return-Path: Delivered-To: freebsd-hackers@freebsd.org Received: from herd.plethora.net (herd.plethora.net [205.166.146.1]) by hub.freebsd.org (Postfix) with ESMTP id 52C9737B400 for ; Tue, 19 Dec 2000 18:30:30 -0800 (PST) Received: from guild.plethora.net (root@guild.plethora.net [205.166.146.8]) by herd.plethora.net (8.9.0/8.9.0) with ESMTP id UAA28170 for ; Tue, 19 Dec 2000 20:30:29 -0600 (CST) Received: from guild.plethora.net (seebs@localhost.plethora.net [127.0.0.1]) by guild.plethora.net (8.9.3/8.9.0) with ESMTP id UAA07160 for ; Tue, 19 Dec 2000 20:30:28 -0600 (CST) Message-Id: <200012200230.UAA07160@guild.plethora.net> From: seebs@plethora.net (Peter Seebach) Reply-To: seebs@plethora.net (Peter Seebach) To: freebsd-hackers@freebsd.org Subject: Re: Optimizations (was: Why not another style thread? (was Re: cvs commit: src/lib/libc/gen getgrent.c)) In-reply-to: Your message of "Tue, 19 Dec 2000 18:23:58 PST." <200012200223.eBK2Nwt63810@earth.backplane.com> Date: Tue, 19 Dec 2000 20:30:28 -0600 Sender: seebs@plethora.net Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG In message <200012200223.eBK2Nwt63810@earth.backplane.com>, Matt Dillon writes: > Guys, on intel a simple conditional is going to be a whole lot [less] > expensive then a subroutine call no matter what, even if the > conditional misses. Sure, but it may be worth considering the effects on other platforms, present and future, possibly including future Intel. If it's not a big performance difference, write the most readable code. If it's a serious performance difference, then it's probably worth #ifdef'ing it based on profiled results under different compilers on different chips. :) -s To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message