From owner-freebsd-chat@FreeBSD.ORG Sun Mar 7 09:44:58 2004 Return-Path: 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 CDE8316A4CE for ; Sun, 7 Mar 2004 09:44:58 -0800 (PST) Received: from haldjas.folklore.ee (Haldjas.folklore.ee [193.40.6.121]) by mx1.FreeBSD.org (Postfix) with ESMTP id 1AA5D43D46 for ; Sun, 7 Mar 2004 09:44:58 -0800 (PST) (envelope-from narvi@haldjas.folklore.ee) Received: from haldjas.folklore.ee (localhost [127.0.0.1]) by haldjas.folklore.ee (8.12.10/8.12.10) with ESMTP id i27HioUA068389; Sun, 7 Mar 2004 19:44:50 +0200 (EET) (envelope-from narvi@haldjas.folklore.ee) Received: from localhost (narvi@localhost)i27HiovV068386; Sun, 7 Mar 2004 19:44:50 +0200 (EET) (envelope-from narvi@haldjas.folklore.ee) Date: Sun, 7 Mar 2004 19:44:49 +0200 (EET) From: Narvi To: stephan mantler In-Reply-To: <404A465A.1040009@stephanmantler.com> Message-ID: <20040307052509.F38020@haldjas.folklore.ee> References: <20040306005744.T38020@haldjas.folklore.ee> <20040306013914.D38020@haldjas.folklore.ee> <404A465A.1040009@stephanmantler.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-Spam-Status: No, hits=0.0 required=8.0 tests=none autolearn=no version=2.63 X-Spam-Checker-Version: SpamAssassin 2.63 (2004-01-11) on haldjas.folklore.ee cc: freebsd-chat@freebsd.org Subject: Re: FreeBSD Most wanted X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 07 Mar 2004 17:44:59 -0000 On Sat, 6 Mar 2004, stephan mantler wrote: > Narvi wrote: > >>"Familiarity with the target machine and its instruction set is a > >>prerequisite for designing a good code generator. Unfortunately, in a > >>general discussion of code generation it is not possible to describe > >>the nuances of any target machine in sufficient detail to be able to > >>generate good code for a complete language on that machine." > >> -- The "Dragon" Book, pp 519 > > > > Sure - but code generation is but one part of the compiler and usualy not > > the largest. > > Well, it is still a crucial part of the compiler and deeply tied into the > rest. It is also the reason why simply using the Intel C++ compiler instead > of .NET2003 (both at full optimization) made our vector math library run > five times faster... guess who knows the target architecture ;-) In this Umm... It soudns far more plausible that Intel's compiler was able to make use of vectorisiation so that it uses SSE2 instead of x87 fpu. This is for the most part not ASM, but code analysis / rewriting. Sure, you need to be able to isse the SSE2 opcoides but that is a tiny part. Knowing any amount of SSE2 tricks will not help you one bit if the compiler cannot flatten the loop so you can make use of SIMD / vector instructions. Once you have that part done, you canthen relatively easily (at least in comparison to the ananlysis you need to be able to do) interface this to SSE2 && SSE and Altivec and VIS. > highly specific example hand optimized assembler code is another four times > faster for some functions, but I think this is not a problem of compilers per > se. I guess the C/C++ language simply isn't giving the compiler all the > information it would need. I haven't yet tried Intel's feedback optimization > feature, but it will be interesting to see what it will do to our library. > Its not all the information, its that it is unable to assume some things. If you have a compiler that can do interfile optimisations and profile feedback, it might generate better code. alternatively, if you want to see what the compiler can achieve, rewrite the routines in fortran (no i'm not kidding). In C, it is often very hard for the compiler to make assumptions about array overlap or aliasing. > Also, to get a bit closer to the original topic. I can't remember where I > read this (DDJ probably), but apparently programmers who have a deep > understanding of computer architecture through low level programming also > produce "better" code in high level languages. My interpretation is that > they are simply feeding the compiler a better foundation to work with. > The understanding would probably be about things like memory hierarchy and not ASM though. > Cheers, > -stephan > > -- > stephan mantler | web www.stephanmantler.com > ----------------------------| net step@stephanmantler.com > It's not an adventure | fon +43 (699) 104 128 42 > until something f--ks up. | fax +43 (699) 404 128 42 > From owner-freebsd-chat@FreeBSD.ORG Sun Mar 7 10:23:06 2004 Return-Path: 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 C282A16A4CE for ; Sun, 7 Mar 2004 10:23:06 -0800 (PST) Received: from haldjas.folklore.ee (Haldjas.folklore.ee [193.40.6.121]) by mx1.FreeBSD.org (Postfix) with ESMTP id 2048143D1F for ; Sun, 7 Mar 2004 10:23:06 -0800 (PST) (envelope-from narvi@haldjas.folklore.ee) Received: from haldjas.folklore.ee (localhost [127.0.0.1]) by haldjas.folklore.ee (8.12.10/8.12.10) with ESMTP id i27IMxUA069015; Sun, 7 Mar 2004 20:22:59 +0200 (EET) (envelope-from narvi@haldjas.folklore.ee) Received: from localhost (narvi@localhost)i27IMxZD069012; Sun, 7 Mar 2004 20:22:59 +0200 (EET) (envelope-from narvi@haldjas.folklore.ee) Date: Sun, 7 Mar 2004 20:22:59 +0200 (EET) From: Narvi To: Colin Percival In-Reply-To: <6.0.1.1.1.20040306214526.08c5ed70@imap.sfu.ca> Message-ID: <20040307202113.I68396@haldjas.folklore.ee> References: <20040306005744.T38020@haldjas.folklore.ee> <20040306013914.D38020@haldjas.folklore.ee> <6.0.1.1.1.20040306214526.08c5ed70@imap.sfu.ca> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-Spam-Status: No, hits=0.0 required=8.0 tests=none autolearn=no version=2.63 X-Spam-Checker-Version: SpamAssassin 2.63 (2004-01-11) on haldjas.folklore.ee cc: freebsd-chat@freebsd.org Subject: Re: FreeBSD Most wanted X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 07 Mar 2004 18:23:06 -0000 On Sat, 6 Mar 2004, Colin Percival wrote: > At 21:44 06/03/2004, stephan mantler wrote: > >Also, to get a bit closer to the original topic. I can't remember where I > >read this (DDJ probably), but apparently programmers who have a deep > >understanding of computer architecture through low level programming also > >produce "better" code in high level languages. My interpretation is that > >they are simply feeding the compiler a better foundation to work with. > > Having seen quite a lot of undergraduate "computer science" students > over past decade, I can certainly support that interpretation. Nobody > quite understands why hash tables are not a perfect data structure > until they've tried to implement one in assembly language. (And, after > performing such a task, few people will use hash tables without asking > themselves, at least for a moment, if there might be a cheaper solution > to the problem at hand.) yeah, so they go for a simple singly linked list instead :( hash tables are a very non-trivial data structure, and the majority of way of implementing them are really gross from the point of view of having a deep memory hierarchy. > > Colin Percival > From owner-freebsd-chat@FreeBSD.ORG Sun Mar 7 10:43:36 2004 Return-Path: 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 05AF816A4CE for ; Sun, 7 Mar 2004 10:43:36 -0800 (PST) Received: from haldjas.folklore.ee (Haldjas.folklore.ee [193.40.6.121]) by mx1.FreeBSD.org (Postfix) with ESMTP id 3CA4143D1F for ; Sun, 7 Mar 2004 10:43:35 -0800 (PST) (envelope-from narvi@haldjas.folklore.ee) Received: from haldjas.folklore.ee (localhost [127.0.0.1]) by haldjas.folklore.ee (8.12.10/8.12.10) with ESMTP id i27IgxUA069365; Sun, 7 Mar 2004 20:42:59 +0200 (EET) (envelope-from narvi@haldjas.folklore.ee) Received: from localhost (narvi@localhost)i27IgxMS069362; Sun, 7 Mar 2004 20:42:59 +0200 (EET) (envelope-from narvi@haldjas.folklore.ee) Date: Sun, 7 Mar 2004 20:42:59 +0200 (EET) From: Narvi To: Colin Percival In-Reply-To: <6.0.1.1.1.20040306221435.03a97e20@imap.sfu.ca> Message-ID: <20040307202336.K68396@haldjas.folklore.ee> References: <20040306005744.T38020@haldjas.folklore.ee> <20040306013914.D38020@haldjas.folklore.ee> <6.0.1.1.1.20040306214526.08c5ed70@imap.sfu.ca> <20040306141742.4f41ba27.cpressey@catseye.mine.nu> <6.0.1.1.1.20040306221435.03a97e20@imap.sfu.ca> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-Spam-Status: No, hits=0.0 required=8.0 tests=none autolearn=no version=2.63 X-Spam-Checker-Version: SpamAssassin 2.63 (2004-01-11) on haldjas.folklore.ee cc: Chris Pressey cc: freebsd-chat@freebsd.org Subject: Re: FreeBSD Most wanted X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 07 Mar 2004 18:43:36 -0000 On Sat, 6 Mar 2004, Colin Percival wrote: > At 22:17 06/03/2004, Chris Pressey wrote: > >Colin Percival wrote: > > > Nobody > > > quite understands why hash tables are not a perfect data structure > > > until they've tried to implement one in assembly language. (And, > > > after performing such a task, few people will use hash tables without > > > asking themselves, at least for a moment, if there might be a cheaper > > > solution to the problem at hand.) > > > >Not sure what you mean here... surely it's no easier to implement (say) > >an AVL tree or a red-black tree in assembly? > > Perhaps not, but it's much easier to implement an unsorted list. :-) > Yes, but this is unlikely to be efficent in any but the rarest cases, and should the number be in some cases large, you get corner cases where your perfomance suddenly sucks for mysterious reasons. > I've often seen people using hash tables to keep track of very small > numbers of objects, where a simple sequential scan will be much faster > than a hash table lookup; I also see people using hash tables for data > where the keys rarely, if ever, change. If you know the max number of elements, use an array of pointers + counter instead of list. scanning an array is much nicer than scanning a list - this is also the reson why you have to work hard to make say chained hash tables be as efficent as liner probing. > > >In fact, I'd think a hash function would often be a good candidate for > >hand-coded assembly - if you want to play "Beat the Compiler" :) > > Quite likely, yes[0]. But the act of writing usually makes people > realize just how much work the processor does every time a hashlookup() > call is made. The amount of work the programmer does isn't really > important. (You're not planning on assembly-coding a hash table more > than once, are you?) > > Of course, part of the problem is that most undergraduate courses > still teach the myth that random access memory is, err, random access. I think the problem is that they don't have a course on how to select data structures at all AFAICT. And I don't think this is a problem that is restricted to undergraduates either. > > Colin Percival > [0] With the exception of cryptographic hash functions, which tend to > be constructed in such a way that any half-decent compiler will output > exactly the same code as a human would. > From owner-freebsd-chat@FreeBSD.ORG Sun Mar 7 10:47:06 2004 Return-Path: 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 9904116A4CE for ; Sun, 7 Mar 2004 10:47:06 -0800 (PST) Received: from haldjas.folklore.ee (Haldjas.folklore.ee [193.40.6.121]) by mx1.FreeBSD.org (Postfix) with ESMTP id EC3DC43D1D for ; Sun, 7 Mar 2004 10:47:05 -0800 (PST) (envelope-from narvi@haldjas.folklore.ee) Received: from haldjas.folklore.ee (localhost [127.0.0.1]) by haldjas.folklore.ee (8.12.10/8.12.10) with ESMTP id i27IkWUA069432; Sun, 7 Mar 2004 20:46:32 +0200 (EET) (envelope-from narvi@haldjas.folklore.ee) Received: from localhost (narvi@localhost)i27IkWdi069429; Sun, 7 Mar 2004 20:46:32 +0200 (EET) (envelope-from narvi@haldjas.folklore.ee) Date: Sun, 7 Mar 2004 20:46:32 +0200 (EET) From: Narvi To: Chris Pressey In-Reply-To: <20040306155513.6a75e264.cpressey@catseye.mine.nu> Message-ID: <20040307204413.W68396@haldjas.folklore.ee> References: <20040306005744.T38020@haldjas.folklore.ee> <20040306013914.D38020@haldjas.folklore.ee> <6.0.1.1.1.20040306214526.08c5ed70@imap.sfu.ca> <20040306141742.4f41ba27.cpressey@catseye.mine.nu> <20040306155513.6a75e264.cpressey@catseye.mine.nu> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-Spam-Status: No, hits=0.0 required=8.0 tests=none autolearn=no version=2.63 X-Spam-Checker-Version: SpamAssassin 2.63 (2004-01-11) on haldjas.folklore.ee cc: freebsd-chat@freebsd.org Subject: Re: FreeBSD Most wanted X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 07 Mar 2004 18:47:06 -0000 On Sat, 6 Mar 2004, Chris Pressey wrote: > > And, yeah. A hash table is really nothing by itself. It's just a way > of taking a long list (or other structure) and splitting it up into N > smaller structures. If your lists are never that long in the first > place, there's no point. > URKH! No it doesn't. Or rather, it should - there are almost no good reasons to use a naive chaining hash table. > > -Chris > From owner-freebsd-chat@FreeBSD.ORG Sun Mar 7 10:59:18 2004 Return-Path: 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 C128816A4CE for ; Sun, 7 Mar 2004 10:59:18 -0800 (PST) Received: from tx3.oucs.ox.ac.uk (tx3.oucs.ox.ac.uk [163.1.2.167]) by mx1.FreeBSD.org (Postfix) with ESMTP id 2C41043D1D for ; Sun, 7 Mar 2004 10:59:18 -0800 (PST) (envelope-from colin.percival@wadham.ox.ac.uk) Received: from scan3.oucs.ox.ac.uk ([163.1.2.166] helo=localhost) by tx3.oucs.ox.ac.uk with esmtp (Exim 4.24) id 1B03Ub-0008SL-NP for freebsd-chat@freebsd.org; Sun, 07 Mar 2004 18:59:17 +0000 Received: from rx3.oucs.ox.ac.uk ([163.1.2.165]) by localhost (scan3.oucs.ox.ac.uk [163.1.2.166]) (amavisd-new, port 25) with ESMTP id 32126-09 for ; Sun, 7 Mar 2004 18:59:17 +0000 (GMT) Received: from gateway.wadham.ox.ac.uk ([163.1.161.253]) by rx3.oucs.ox.ac.uk with smtp (Exim 4.24) id 1B03Ub-0008SE-A0 for freebsd-chat@freebsd.org; Sun, 07 Mar 2004 18:59:17 +0000 Received: (qmail 8714 invoked by uid 1004); 7 Mar 2004 18:59:16 -0000 Received: from colin.percival@wadham.ox.ac.uk by gateway by uid 71 with qmail-scanner-1.20 (clamscan: 0.67. sweep: 2.18/3.79. Clear:RC:1(163.1.161.131):. Processed in 0.073537 secs); 07 Mar 2004 18:59:16 -0000 Received: from dhcp1131.wadham.ox.ac.uk (HELO piii600.wadham.ox.ac.uk) (163.1.161.131) by gateway.wadham.ox.ac.uk with SMTP; 7 Mar 2004 18:59:16 -0000 Message-Id: <6.0.1.1.1.20040307184942.08d74718@imap.sfu.ca> X-Sender: cperciva@imap.sfu.ca (Unverified) X-Mailer: QUALCOMM Windows Eudora Version 6.0.1.1 Date: Sun, 07 Mar 2004 18:59:14 +0000 To: Narvi From: Colin Percival In-Reply-To: <20040307202336.K68396@haldjas.folklore.ee> References: <20040306005744.T38020@haldjas.folklore.ee> <20040305153505.74061868.cpressey@catseye.mine.nu> <20040306013914.D38020@haldjas.folklore.ee> <404A465A.1040009@stephanmantler.com> <6.0.1.1.1.20040306214526.08c5ed70@imap.sfu.ca> <20040306141742.4f41ba27.cpressey@catseye.mine.nu> <6.0.1.1.1.20040306221435.03a97e20@imap.sfu.ca> <20040307202336.K68396@haldjas.folklore.ee> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed cc: freebsd-chat@freebsd.org Subject: Re: FreeBSD Most wanted X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 07 Mar 2004 18:59:18 -0000 At 18:42 07/03/2004, Narvi wrote: >On Sat, 6 Mar 2004, Colin Percival wrote: > > Perhaps not, but it's much easier to implement an unsorted list. :-) > ... >If you know the max number of elements, use an array of pointers + counter >instead of list. scanning an array is much nicer than scanning a list Sorry, bad choice of words on my part. When I said "unsorted list", I meant "array". (That's what I get for skipping an undergraduate CS degree and going straight to the doctorate...) >I think the problem is that [most undergraduate programs] don't have a >course on how to select data structures at all AFAICT. Many do, but they are usually taught entirely from the point of view of asymptotics. "Hash tables operate in O(1) time!" (Or somewhere around O(log(n)) if they're being unusually honest.) "Scanning an array takes O(n) time!" Obviously hash tables are better than arrays for all n > 1, right? Colin Percival From owner-freebsd-chat@FreeBSD.ORG Sun Mar 7 10:59:26 2004 Return-Path: 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 21F6D16A4CE for ; Sun, 7 Mar 2004 10:59:26 -0800 (PST) Received: from priv-edtnes40.telusplanet.net (outbound05.telus.net [199.185.220.224]) by mx1.FreeBSD.org (Postfix) with ESMTP id BE6DC43D1F for ; Sun, 7 Mar 2004 10:59:25 -0800 (PST) (envelope-from cpressey@catseye.mine.nu) Received: from catseye.biscuit.boo ([154.5.85.228]) by priv-edtnes40.telusplanet.netSMTP <20040307185925.HHXF12629.priv-edtnes40.telusplanet.net@catseye.biscuit.boo>; Sun, 7 Mar 2004 11:59:25 -0700 Date: Sun, 7 Mar 2004 11:04:27 -0800 From: Chris Pressey To: Narvi Message-Id: <20040307110427.67a4394e.cpressey@catseye.mine.nu> In-Reply-To: <20040307204413.W68396@haldjas.folklore.ee> References: <20040306005744.T38020@haldjas.folklore.ee> <20040305153505.74061868.cpressey@catseye.mine.nu> <20040306013914.D38020@haldjas.folklore.ee> <404A465A.1040009@stephanmantler.com> <6.0.1.1.1.20040306214526.08c5ed70@imap.sfu.ca> <20040306141742.4f41ba27.cpressey@catseye.mine.nu> <6.0.1.1.1.20040306221435.03a97e20@imap.sfu.ca> <20040306155513.6a75e264.cpressey@catseye.mine.nu> <20040307204413.W68396@haldjas.folklore.ee> Organization: Cat's Eye Technologies X-Mailer: Sylpheed version 0.9.9 (GTK+ 1.2.10; i386-portbld-freebsd4.9) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit cc: freebsd-chat@freebsd.org Subject: Re: FreeBSD Most wanted X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 07 Mar 2004 18:59:26 -0000 On Sun, 7 Mar 2004 20:46:32 +0200 (EET) Narvi wrote: > > On Sat, 6 Mar 2004, Chris Pressey wrote: > > > > > And, yeah. A hash table is really nothing by itself. It's just a way > > of taking a long list (or other structure) and splitting it up into N > > smaller structures. If your lists are never that long in the first > > place, there's no point. > > > > URKH! No it doesn't. Or rather, it should - I don't know what you are referring to here. > there are almost no good > reasons to use a naive chaining hash table. I did say list *(or other structure)*. -Chris From owner-freebsd-chat@FreeBSD.ORG Sun Mar 7 11:32:31 2004 Return-Path: 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 CD92416A4CE for ; Sun, 7 Mar 2004 11:32:31 -0800 (PST) Received: from haldjas.folklore.ee (Haldjas.folklore.ee [193.40.6.121]) by mx1.FreeBSD.org (Postfix) with ESMTP id 29C2643D1D for ; Sun, 7 Mar 2004 11:32:31 -0800 (PST) (envelope-from narvi@haldjas.folklore.ee) Received: from haldjas.folklore.ee (localhost [127.0.0.1]) by haldjas.folklore.ee (8.12.10/8.12.10) with ESMTP id i27JVuUA070100; Sun, 7 Mar 2004 21:31:56 +0200 (EET) (envelope-from narvi@haldjas.folklore.ee) Received: from localhost (narvi@localhost)i27JVuQS070097; Sun, 7 Mar 2004 21:31:56 +0200 (EET) (envelope-from narvi@haldjas.folklore.ee) Date: Sun, 7 Mar 2004 21:31:56 +0200 (EET) From: Narvi To: Chris Pressey In-Reply-To: <20040307110427.67a4394e.cpressey@catseye.mine.nu> Message-ID: <20040307210125.Y68396@haldjas.folklore.ee> References: <20040306005744.T38020@haldjas.folklore.ee> <20040306013914.D38020@haldjas.folklore.ee> <6.0.1.1.1.20040306214526.08c5ed70@imap.sfu.ca> <20040306141742.4f41ba27.cpressey@catseye.mine.nu> <20040306155513.6a75e264.cpressey@catseye.mine.nu> <20040307110427.67a4394e.cpressey@catseye.mine.nu> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-Spam-Status: No, hits=0.0 required=8.0 tests=none autolearn=no version=2.63 X-Spam-Checker-Version: SpamAssassin 2.63 (2004-01-11) on haldjas.folklore.ee cc: freebsd-chat@freebsd.org Subject: Re: FreeBSD Most wanted X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 07 Mar 2004 19:32:31 -0000 On Sun, 7 Mar 2004, Chris Pressey wrote: > On Sun, 7 Mar 2004 20:46:32 +0200 (EET) > Narvi wrote: > > > > > On Sat, 6 Mar 2004, Chris Pressey wrote: > > > > > > > > And, yeah. A hash table is really nothing by itself. It's just a way > > > of taking a long list (or other structure) and splitting it up into N > > > smaller structures. If your lists are never that long in the first > > > place, there's no point. > > > > > > > URKH! No it doesn't. Or rather, it should - > > I don't know what you are referring to here. > The *traditional* hash table is one that uses linear probing, that is, it converts a list to a nice cache friendly array and provides you with a hint where you should start looking. The hash table constructions that uses a list (aka a chain) to handle conflicts is a derivative that has some nice features (esp if you want to delete values) and some drawbacks. There are many different hashing schemes and the research into more hasn't stopped (nor is likely to stop anytime soon). > > there are almost no good > > reasons to use a naive chaining hash table. > > I did say list *(or other structure)*. This makes it only marginaly less incorrect. > > -Chris > From owner-freebsd-chat@FreeBSD.ORG Sun Mar 7 11:45:42 2004 Return-Path: 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 A4D5A16A4CE for ; Sun, 7 Mar 2004 11:45:42 -0800 (PST) Received: from tx3.oucs.ox.ac.uk (tx3.oucs.ox.ac.uk [163.1.2.167]) by mx1.FreeBSD.org (Postfix) with ESMTP id 77E7F43D41 for ; Sun, 7 Mar 2004 11:45:42 -0800 (PST) (envelope-from colin.percival@wadham.ox.ac.uk) Received: from scan3.oucs.ox.ac.uk ([163.1.2.166] helo=localhost) by tx3.oucs.ox.ac.uk with esmtp (Exim 4.24) id 1B04DV-0000Ga-Nn for freebsd-chat@freebsd.org; Sun, 07 Mar 2004 19:45:41 +0000 Received: from rx3.oucs.ox.ac.uk ([163.1.2.165]) by localhost (scan3.oucs.ox.ac.uk [163.1.2.166]) (amavisd-new, port 25) with ESMTP id 00613-10 for ; Sun, 7 Mar 2004 19:45:41 +0000 (GMT) Received: from gateway.wadham.ox.ac.uk ([163.1.161.253]) by rx3.oucs.ox.ac.uk with smtp (Exim 4.24) id 1B04DU-0000Fw-Cg for freebsd-chat@freebsd.org; Sun, 07 Mar 2004 19:45:41 +0000 Received: (qmail 23263 invoked by uid 1004); 7 Mar 2004 19:45:39 -0000 Received: from colin.percival@wadham.ox.ac.uk by gateway by uid 71 with qmail-scanner-1.20 (clamscan: 0.67. sweep: 2.18/3.79. Clear:RC:1(163.1.161.131):. Processed in 0.68935 secs); 07 Mar 2004 19:45:39 -0000 Received: from dhcp1131.wadham.ox.ac.uk (HELO piii600.wadham.ox.ac.uk) (163.1.161.131) by gateway.wadham.ox.ac.uk with SMTP; 7 Mar 2004 19:45:38 -0000 Message-Id: <6.0.1.1.1.20040307194055.08e83008@imap.sfu.ca> X-Sender: cperciva@imap.sfu.ca (Unverified) X-Mailer: QUALCOMM Windows Eudora Version 6.0.1.1 Date: Sun, 07 Mar 2004 19:45:35 +0000 To: Narvi From: Colin Percival In-Reply-To: <20040307210125.Y68396@haldjas.folklore.ee> References: <20040306005744.T38020@haldjas.folklore.ee> <20040306013914.D38020@haldjas.folklore.ee> <6.0.1.1.1.20040306214526.08c5ed70@imap.sfu.ca> <20040306141742.4f41ba27.cpressey@catseye.mine.nu> <20040306155513.6a75e264.cpressey@catseye.mine.nu> <20040307110427.67a4394e.cpressey@catseye.mine.nu> <20040307210125.Y68396@haldjas.folklore.ee> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed cc: freebsd-chat@freebsd.org Subject: Re: FreeBSD Most wanted X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 07 Mar 2004 19:45:42 -0000 At 19:31 07/03/2004, Narvi wrote: >The *traditional* hash table is one that uses linear probing, that is, it >converts a list to a nice cache friendly array and provides you with a >hint where you should start looking. Does anyone actually do that any more? When I absolutely need a hash table, I normally use double hashing and gradual rehashing. But maybe that's just a personal quirk. Colin Percival From owner-freebsd-chat@FreeBSD.ORG Sun Mar 7 11:54:35 2004 Return-Path: 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 7206E16A4CE for ; Sun, 7 Mar 2004 11:54:35 -0800 (PST) Received: from haldjas.folklore.ee (Haldjas.folklore.ee [193.40.6.121]) by mx1.FreeBSD.org (Postfix) with ESMTP id C4FF743D1D for ; Sun, 7 Mar 2004 11:54:34 -0800 (PST) (envelope-from narvi@haldjas.folklore.ee) Received: from haldjas.folklore.ee (localhost [127.0.0.1]) by haldjas.folklore.ee (8.12.10/8.12.10) with ESMTP id i27JsSUA070477; Sun, 7 Mar 2004 21:54:28 +0200 (EET) (envelope-from narvi@haldjas.folklore.ee) Received: from localhost (narvi@localhost)i27JsSsl070474; Sun, 7 Mar 2004 21:54:28 +0200 (EET) (envelope-from narvi@haldjas.folklore.ee) Date: Sun, 7 Mar 2004 21:54:28 +0200 (EET) From: Narvi To: Colin Percival In-Reply-To: <6.0.1.1.1.20040307194055.08e83008@imap.sfu.ca> Message-ID: <20040307214622.Y68396@haldjas.folklore.ee> References: <20040306013914.D38020@haldjas.folklore.ee> <20040306141742.4f41ba27.cpressey@catseye.mine.nu> <20040306155513.6a75e264.cpressey@catseye.mine.nu> <20040307210125.Y68396@haldjas.folklore.ee> <6.0.1.1.1.20040307194055.08e83008@imap.sfu.ca> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-Spam-Status: No, hits=0.0 required=8.0 tests=none autolearn=no version=2.63 X-Spam-Checker-Version: SpamAssassin 2.63 (2004-01-11) on haldjas.folklore.ee cc: freebsd-chat@freebsd.org Subject: Re: FreeBSD Most wanted X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 07 Mar 2004 19:54:35 -0000 On Sun, 7 Mar 2004, Colin Percival wrote: > At 19:31 07/03/2004, Narvi wrote: > >The *traditional* hash table is one that uses linear probing, that is, it > >converts a list to a nice cache friendly array and provides you with a > >hint where you should start looking. > > Does anyone actually do that any more? When I absolutely need a hash It is still around. It plays *exteremely* nicely with cache, for example. Sure, it takes some extra care to make sure you don't run into nastiness, but it can give you a very fast and efficent hash. > table, I normally use double hashing and gradual rehashing. But maybe > that's just a personal quirk. > Have you looked at cuckoo hashing? > Colin Percival > > From owner-freebsd-chat@FreeBSD.ORG Sun Mar 7 12:02:56 2004 Return-Path: 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 75AA516A4CE for ; Sun, 7 Mar 2004 12:02:56 -0800 (PST) Received: from priv-edtnes14-hme0.telusplanet.net (outbound03.telus.net [199.185.220.222]) by mx1.FreeBSD.org (Postfix) with ESMTP id 2A55243D2D for ; Sun, 7 Mar 2004 12:02:56 -0800 (PST) (envelope-from cpressey@catseye.mine.nu) Received: from catseye.biscuit.boo ([154.5.85.228]) by priv-edtnes14-hme0.telusplanet.netSMTP <20040307200255.EVEH21205.priv-edtnes14-hme0.telusplanet.net@catseye.biscuit.boo>; Sun, 7 Mar 2004 13:02:55 -0700 Date: Sun, 7 Mar 2004 12:07:58 -0800 From: Chris Pressey To: Narvi Message-Id: <20040307120758.13f24851.cpressey@catseye.mine.nu> In-Reply-To: <20040307210125.Y68396@haldjas.folklore.ee> References: <20040306005744.T38020@haldjas.folklore.ee> <20040306013914.D38020@haldjas.folklore.ee> <6.0.1.1.1.20040306214526.08c5ed70@imap.sfu.ca> <20040306141742.4f41ba27.cpressey@catseye.mine.nu> <20040306155513.6a75e264.cpressey@catseye.mine.nu> <20040307110427.67a4394e.cpressey@catseye.mine.nu> <20040307210125.Y68396@haldjas.folklore.ee> Organization: Cat's Eye Technologies X-Mailer: Sylpheed version 0.9.9 (GTK+ 1.2.10; i386-portbld-freebsd4.9) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit cc: freebsd-chat@freebsd.org Subject: Re: FreeBSD Most wanted X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 07 Mar 2004 20:02:56 -0000 On Sun, 7 Mar 2004 21:31:56 +0200 (EET) Narvi wrote: > > On Sun, 7 Mar 2004, Chris Pressey wrote: > > > On Sun, 7 Mar 2004 20:46:32 +0200 (EET) > > Narvi wrote: > > > > > > > > On Sat, 6 Mar 2004, Chris Pressey wrote: > > > > > > > > > > > And, yeah. A hash table is really nothing by itself. It's just > > > > a way of taking a long list (or other structure) and splitting > > > > it up into N smaller structures. If your lists are never that > > > > long in the first place, there's no point. > > > > > > > > > > URKH! No it doesn't. Or rather, it should - > > > > I don't know what you are referring to here. > > > > The *traditional* hash table is one that uses linear probing, that is, > it converts a list to a nice cache friendly array and provides you > with a hint where you should start looking. The hash table > constructions that uses a list (aka a chain) to handle conflicts is a > derivative that has some nice features (esp if you want to delete > values) and some drawbacks. > > There are many different hashing schemes and the research into more > hasn't stopped (nor is likely to stop anytime soon). > > > > there are almost no good > > > reasons to use a naive chaining hash table. > > > > I did say list *(or other structure)*. > > This makes it only marginaly less incorrect. I don't think that this invalidates my (/Colin's) point, which I'll restate for clarity: The goal of computing a hash value is to reduce the search space. (Surely this hasn't really changed, even in the most new-fangled variation on the hash table theme?) And if the search space is already small, the reduction will be insignificant compared to the time taken to compute the hash value. -Chris From owner-freebsd-chat@FreeBSD.ORG Sun Mar 7 12:34:41 2004 Return-Path: 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 1687516A4CE for ; Sun, 7 Mar 2004 12:34:41 -0800 (PST) Received: from haldjas.folklore.ee (Haldjas.folklore.ee [193.40.6.121]) by mx1.FreeBSD.org (Postfix) with ESMTP id 690AF43D31 for ; Sun, 7 Mar 2004 12:34:40 -0800 (PST) (envelope-from narvi@haldjas.folklore.ee) Received: from haldjas.folklore.ee (localhost [127.0.0.1]) by haldjas.folklore.ee (8.12.10/8.12.10) with ESMTP id i27KY6UA071066; Sun, 7 Mar 2004 22:34:06 +0200 (EET) (envelope-from narvi@haldjas.folklore.ee) Received: from localhost (narvi@localhost)i27KY6Kj071063; Sun, 7 Mar 2004 22:34:06 +0200 (EET) (envelope-from narvi@haldjas.folklore.ee) Date: Sun, 7 Mar 2004 22:34:06 +0200 (EET) From: Narvi To: Chris Pressey In-Reply-To: <20040307120758.13f24851.cpressey@catseye.mine.nu> Message-ID: <20040307220525.X68396@haldjas.folklore.ee> References: <20040306013914.D38020@haldjas.folklore.ee> <20040306141742.4f41ba27.cpressey@catseye.mine.nu> <20040306155513.6a75e264.cpressey@catseye.mine.nu> <20040307210125.Y68396@haldjas.folklore.ee> <20040307120758.13f24851.cpressey@catseye.mine.nu> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-Spam-Status: No, hits=0.0 required=8.0 tests=none autolearn=no version=2.63 X-Spam-Checker-Version: SpamAssassin 2.63 (2004-01-11) on haldjas.folklore.ee cc: freebsd-chat@freebsd.org Subject: Re: FreeBSD Most wanted X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 07 Mar 2004 20:34:41 -0000 On Sun, 7 Mar 2004, Chris Pressey wrote: > > I don't think that this invalidates my (/Colin's) point, which I'll > restate for clarity: > > The goal of computing a hash value is to reduce the search space. > (Surely this hasn't really changed, even in the most new-fangled > variation on the hash table theme?) > > And if the search space is already small, the reduction will be > insignificant compared to the time taken to compute the hash value. > I'm not saying that hash tables are the be and end all of data structures at all. so, can we agree to be in violent agreement? > -Chris > From owner-freebsd-chat@FreeBSD.ORG Sun Mar 7 13:04:46 2004 Return-Path: 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 1C31C16A4CE for ; Sun, 7 Mar 2004 13:04:46 -0800 (PST) Received: from priv-edtnes03-hme0.telusplanet.net (outbound01.telus.net [199.185.220.220]) by mx1.FreeBSD.org (Postfix) with ESMTP id C7BB143D1F for ; Sun, 7 Mar 2004 13:04:45 -0800 (PST) (envelope-from cpressey@catseye.mine.nu) Received: from catseye.biscuit.boo ([154.5.85.228]) by priv-edtnes03-hme0.telusplanet.netSMTP <20040307210445.FRST15181.priv-edtnes03-hme0.telusplanet.net@catseye.biscuit.boo>; Sun, 7 Mar 2004 14:04:45 -0700 Date: Sun, 7 Mar 2004 13:09:48 -0800 From: Chris Pressey To: Narvi Message-Id: <20040307130948.6d9f45c0.cpressey@catseye.mine.nu> In-Reply-To: <20040307220525.X68396@haldjas.folklore.ee> References: <20040306013914.D38020@haldjas.folklore.ee> <20040306141742.4f41ba27.cpressey@catseye.mine.nu> <20040306155513.6a75e264.cpressey@catseye.mine.nu> <20040307210125.Y68396@haldjas.folklore.ee> <20040307120758.13f24851.cpressey@catseye.mine.nu> <20040307220525.X68396@haldjas.folklore.ee> Organization: Cat's Eye Technologies X-Mailer: Sylpheed version 0.9.9 (GTK+ 1.2.10; i386-portbld-freebsd4.9) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit cc: freebsd-chat@freebsd.org Subject: Re: FreeBSD Most wanted X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 07 Mar 2004 21:04:46 -0000 On Sun, 7 Mar 2004 22:34:06 +0200 (EET) Narvi wrote: > > On Sun, 7 Mar 2004, Chris Pressey wrote: > > > > > I don't think that this invalidates my (/Colin's) point, which I'll > > restate for clarity: > > > > The goal of computing a hash value is to reduce the search space. > > (Surely this hasn't really changed, even in the most new-fangled > > variation on the hash table theme?) > > > > And if the search space is already small, the reduction will be > > insignificant compared to the time taken to compute the hash value. > > > > I'm not saying that hash tables are the be and end all of data structures > at all. OK; I didn't think you were saying that anyway. > so, can we agree to be in violent agreement? Logically not, if you hold my statements to be incorrect. :) -Chris From owner-freebsd-chat@FreeBSD.ORG Mon Mar 8 16:05:05 2004 Return-Path: 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 B350116A4CE for ; Mon, 8 Mar 2004 16:05:05 -0800 (PST) Received: from haldjas.folklore.ee (Haldjas.folklore.ee [193.40.6.121]) by mx1.FreeBSD.org (Postfix) with ESMTP id 127AD43D1F for ; Mon, 8 Mar 2004 16:05:05 -0800 (PST) (envelope-from narvi@haldjas.folklore.ee) Received: from haldjas.folklore.ee (localhost [127.0.0.1]) by haldjas.folklore.ee (8.12.10/8.12.10) with ESMTP id i29052UA006730; Tue, 9 Mar 2004 02:05:02 +0200 (EET) (envelope-from narvi@haldjas.folklore.ee) Received: from localhost (narvi@localhost)i29052gq006727; Tue, 9 Mar 2004 02:05:02 +0200 (EET) (envelope-from narvi@haldjas.folklore.ee) Date: Tue, 9 Mar 2004 02:05:02 +0200 (EET) From: Narvi To: Colin Percival In-Reply-To: <6.0.1.1.1.20040307184942.08d74718@imap.sfu.ca> Message-ID: <20040307213212.N68396@haldjas.folklore.ee> References: <20040306005744.T38020@haldjas.folklore.ee> <20040306013914.D38020@haldjas.folklore.ee> <6.0.1.1.1.20040306214526.08c5ed70@imap.sfu.ca> <20040306141742.4f41ba27.cpressey@catseye.mine.nu> <20040307202336.K68396@haldjas.folklore.ee> <6.0.1.1.1.20040307184942.08d74718@imap.sfu.ca> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-Spam-Status: No, hits=0.0 required=8.0 tests=none autolearn=no version=2.63 X-Spam-Checker-Version: SpamAssassin 2.63 (2004-01-11) on haldjas.folklore.ee cc: freebsd-chat@freebsd.org Subject: Re: FreeBSD Most wanted X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Mar 2004 00:05:05 -0000 On Sun, 7 Mar 2004, Colin Percival wrote: > At 18:42 07/03/2004, Narvi wrote: > >On Sat, 6 Mar 2004, Colin Percival wrote: > > > Perhaps not, but it's much easier to implement an unsorted list. :-) > > ... > >If you know the max number of elements, use an array of pointers + counter > >instead of list. scanning an array is much nicer than scanning a list > > Sorry, bad choice of words on my part. When I said "unsorted list", I > meant "array". (That's what I get for skipping an undergraduate CS degree > and going straight to the doctorate...) > I guess i should consistently say 'linked list' when I mean that. > >I think the problem is that [most undergraduate programs] don't have a > >course on how to select data structures at all AFAICT. > > Many do, but they are usually taught entirely from the point of view > of asymptotics. > > "Hash tables operate in O(1) time!" > (Or somewhere around O(log(n)) if they're being unusually honest.) > > "Scanning an array takes O(n) time!" > Heh. Well, I guess its important that people know about asymptotic complexity. But that doesn't really help them all that much when picking a data structre for an application where you need to juggle a lot of extra parameters like: * memory hierarchy * online vs offline * in-core vs out-of-core * memory over head per item * overhead in case of more than one thread > Obviously hash tables are better than arrays for all n > 1, right? > > Colin Percival > > From owner-freebsd-chat@FreeBSD.ORG Tue Mar 9 06:35:27 2004 Return-Path: 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 51DCA16A4CE for ; Tue, 9 Mar 2004 06:35:27 -0800 (PST) Received: from web13811.mail.yahoo.com (web13811.mail.yahoo.com [216.136.175.219]) by mx1.FreeBSD.org (Postfix) with SMTP id 2742043D31 for ; Tue, 9 Mar 2004 06:35:27 -0800 (PST) (envelope-from little_sunshine_1998@yahoo.com) Message-ID: <20040309143525.4367.qmail@web13811.mail.yahoo.com> Received: from [141.84.69.17] by web13811.mail.yahoo.com via HTTP; Tue, 09 Mar 2004 06:35:25 PST Date: Tue, 9 Mar 2004 06:35:25 -0800 (PST) From: LittleSunshine To: freebsd-chat@freebsd.org MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Subject: ISDN-Router, WLAN, Least Cost Dial Up X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Mar 2004 14:35:27 -0000 Hello ! I'm new to FreeBSD/Unix, and maybe there are other ways to find a howto to my question, but after searching for hours ... I'd like to have a FreeBSD Box, which works as an ISDN-Router with Firewall and WLAN Access Point. The hardware works, Wlan is working, ISDN too. Now I'd like to set up some rules for dial-up, to dial the cheapest provider. Next problem is, howto prevent BSD to dial up because of some bull§$)-ing DNS-requests of Win or Win-progs. Is there a better way to trigger the dial-up ? I would appreciate some newbie-help ... Thanks, David W. __________________________________ Do you Yahoo!? Yahoo! Search - Find what you’re looking for faster http://search.yahoo.com From owner-freebsd-chat@FreeBSD.ORG Tue Mar 9 07:21:15 2004 Return-Path: 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 2AE9216A4CE for ; Tue, 9 Mar 2004 07:21:15 -0800 (PST) Received: from smtp.des.no (flood.des.no [217.116.83.31]) by mx1.FreeBSD.org (Postfix) with ESMTP id ADD1743D45 for ; Tue, 9 Mar 2004 07:21:14 -0800 (PST) (envelope-from des@des.no) Received: by smtp.des.no (Pony Express, from userid 666) id 3AD56530E; Tue, 9 Mar 2004 16:21:13 +0100 (CET) Received: from dwp.des.no (des.no [80.203.228.37]) by smtp.des.no (Pony Express) with ESMTP id 50443530A; Tue, 9 Mar 2004 16:21:03 +0100 (CET) Received: by dwp.des.no (Postfix, from userid 2602) id F40C033CA4; Tue, 9 Mar 2004 16:21:02 +0100 (CET) To: LittleSunshine References: <20040309143525.4367.qmail@web13811.mail.yahoo.com> From: des@des.no (Dag-Erling =?iso-8859-1?q?Sm=F8rgrav?=) Date: Tue, 09 Mar 2004 16:21:02 +0100 In-Reply-To: <20040309143525.4367.qmail@web13811.mail.yahoo.com> (little_sunshine_1998@yahoo.com's message of "Tue, 9 Mar 2004 06:35:25 -0800 (PST)") Message-ID: User-Agent: Gnus/5.090024 (Oort Gnus v0.24) Emacs/21.3 (berkeley-unix) MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: quoted-printable X-Spam-Checker-Version: SpamAssassin 2.63 (2004-01-11) on flood.des.no X-Spam-Level: X-Spam-Status: No, hits=0.0 required=5.0 tests=AWL autolearn=no version=2.63 cc: freebsd-chat@freebsd.org Subject: Re: ISDN-Router, WLAN, Least Cost Dial Up X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Mar 2004 15:21:15 -0000 LittleSunshine writes: > Now I'd like to set up some rules for dial-up, to dial > the cheapest provider. > > Next problem is, howto prevent BSD to dial up because > of some bull=A7$)-ing DNS-requests of Win or Win-progs. > Is there a better way to trigger the dial-up ? 'man ppp' and /usr/share/examples/ppp/ should have most of the information you need. DES --=20 Dag-Erling Sm=F8rgrav - des@des.no From owner-freebsd-chat@FreeBSD.ORG Tue Mar 9 08:48:12 2004 Return-Path: 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 4AB4516A4CE for ; Tue, 9 Mar 2004 08:48:12 -0800 (PST) Received: from papagena.rockefeller.edu (papagena.rockefeller.edu [129.85.41.71]) by mx1.FreeBSD.org (Postfix) with ESMTP id D6D7643D39 for ; Tue, 9 Mar 2004 08:48:11 -0800 (PST) (envelope-from rsidd@papagena.rockefeller.edu) Received: from papagena.rockefeller.edu (localhost.localdomain [127.0.0.1]) i29GmBQi026998 for ; Tue, 9 Mar 2004 11:48:11 -0500 Received: (from rsidd@localhost) by papagena.rockefeller.edu (8.12.8/8.12.8/Submit) id i29GmA2D026996 for chat@freebsd.org; Tue, 9 Mar 2004 11:48:10 -0500 Date: Tue, 9 Mar 2004 11:48:10 -0500 From: Rahul Siddharthan To: chat@freebsd.org Message-ID: <20040309164810.GA26987@online.fr> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.4.1i X-Operating-System: Linux 2.4.20-20.9smp i686 Subject: svg converter? X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Mar 2004 16:48:12 -0000 Does anyone know of a (preferably command-line) tool that converts SVG (scalable vector graphics) to other vector formats, in particular EPS and/or PDF? convert (from imagemagick) does EPS, but it's bitmap EPS. I think sketch can read SVG and save EPS, but I'd prefer non-interactive use. Thanks Rahul From owner-freebsd-chat@FreeBSD.ORG Wed Mar 10 16:01:21 2004 Return-Path: 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 2D9E616A4CE for ; Wed, 10 Mar 2004 16:01:21 -0800 (PST) Received: from mail19a.dulles19-verio.com (mail19a.dulles19-verio.com [198.170.241.2]) by mx1.FreeBSD.org (Postfix) with SMTP id D99C643D2D for ; Wed, 10 Mar 2004 16:01:20 -0800 (PST) (envelope-from rob@pythonemproject.com) Received: from www.pythonemproject.com (198.104.176.109)2-0415293277 for ; Wed, 10 Mar 2004 19:01:17 -0500 (EST) Message-ID: <404FAC50.6070603@pythonemproject.com> Date: Wed, 10 Mar 2004 16:01:20 -0800 From: Rob User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.6) Gecko/20040217 X-Accept-Language: en-us, en MIME-Version: 1.0 To: chat@freebsd.org Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Loop-Detect: 1 Subject: What makes Centrino so fast? X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 11 Mar 2004 00:01:21 -0000 I have my own benchmark program that I use for number crunching. It uses a mixture of Python and Numeric Python. Athlon 2166Mhz as reported by OS: 2m38.7s Intel Centrino Pentium 1700 Mhz: 2m17s Is it just compiler optimization at play? Sincerely, Rob From owner-freebsd-chat@FreeBSD.ORG Wed Mar 10 16:03:43 2004 Return-Path: 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 A585816A4CE for ; Wed, 10 Mar 2004 16:03:43 -0800 (PST) Received: from mail19f.dulles19-verio.com (mail19f.dulles19-verio.com [198.170.241.24]) by mx1.FreeBSD.org (Postfix) with SMTP id 2C15643D31 for ; Wed, 10 Mar 2004 16:03:43 -0800 (PST) (envelope-from rob@pythonemproject.com) Received: from www.pythonemproject.com (198.104.176.109)0-0887153420 for ; Wed, 10 Mar 2004 19:03:40 -0500 (EST) Message-ID: <404FACDD.2040606@pythonemproject.com> Date: Wed, 10 Mar 2004 16:03:41 -0800 From: Rob User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.6) Gecko/20040217 X-Accept-Language: en-us, en MIME-Version: 1.0 References: <404FAC50.6070603@pythonemproject.com> In-Reply-To: <404FAC50.6070603@pythonemproject.com> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit To: chat@freebsd.org X-Loop-Detect: 1 cc: chat@freebsd.org Subject: Re: What makes Centrino so fast? X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 11 Mar 2004 00:03:43 -0000 I forgot to add that the Athlon system has 1Gig of Ram while the Centrino has 512k. Rob. Rob wrote: > I have my own benchmark program that I use for number crunching. > It uses a mixture of Python and Numeric Python. > > Athlon 2166Mhz as reported by OS: 2m38.7s > Intel Centrino Pentium 1700 Mhz: 2m17s > > Is it just compiler optimization at play? > > Sincerely, > > Rob > _______________________________________________ > freebsd-chat@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-chat > To unsubscribe, send any mail to "freebsd-chat-unsubscribe@freebsd.org" > From owner-freebsd-chat@FreeBSD.ORG Wed Mar 10 16:56:49 2004 Return-Path: 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 6E95A16A4CE for ; Wed, 10 Mar 2004 16:56:49 -0800 (PST) Received: from seven.Alameda.net (seven.alameda.net [64.81.53.71]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5A9F243D1D for ; Wed, 10 Mar 2004 16:56:49 -0800 (PST) (envelope-from ulf@Alameda.net) Received: by seven.Alameda.net (Postfix, from userid 1000) id 1E7773A236; Wed, 10 Mar 2004 16:56:49 -0800 (PST) Date: Wed, 10 Mar 2004 16:56:49 -0800 From: Ulf Zimmermann To: Rob Message-ID: <20040311005648.GN89845@seven.alameda.net> References: <404FAC50.6070603@pythonemproject.com> <404FACDD.2040606@pythonemproject.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <404FACDD.2040606@pythonemproject.com> User-Agent: Mutt/1.4.1i Organization: Alameda Networks, Inc. X-Operating-System: FreeBSD 4.8-RELEASE-p5 cc: chat@freebsd.org Subject: Re: What makes Centrino so fast? X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list Reply-To: ulf@Alameda.net List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 11 Mar 2004 00:56:49 -0000 On Wed, Mar 10, 2004 at 04:03:41PM -0800, Rob wrote: > I forgot to add that the Athlon system has 1Gig of Ram while the > Centrino has 512k. Rob. > > > Rob wrote: > >I have my own benchmark program that I use for number crunching. > >It uses a mixture of Python and Numeric Python. > > > >Athlon 2166Mhz as reported by OS: 2m38.7s > >Intel Centrino Pentium 1700 Mhz: 2m17s > > > >Is it just compiler optimization at play? > > > >Sincerely, > > > >Rob 512k or 512MB ? ;-) -- Regards, Ulf. --------------------------------------------------------------------- Ulf Zimmermann, 1525 Pacific Ave., Alameda, CA-94501, #: 510-865-0204 You can find my resume at: http://seven.Alameda.net/~ulf/resume.html From owner-freebsd-chat@FreeBSD.ORG Wed Mar 10 17:25:43 2004 Return-Path: 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 AA92C16A4CE; Wed, 10 Mar 2004 17:25:43 -0800 (PST) Received: from cain.gsoft.com.au (cain.gsoft.com.au [203.31.81.10]) by mx1.FreeBSD.org (Postfix) with ESMTP id 9912743D1F; Wed, 10 Mar 2004 17:25:42 -0800 (PST) (envelope-from doconnor@gsoft.com.au) Received: from inchoate.gsoft.com.au (localhost [127.0.0.1]) (authenticated bits=0) by cain.gsoft.com.au (8.12.9/8.12.8) with ESMTP id i2B1PcQ9057806; Thu, 11 Mar 2004 11:55:39 +1030 (CST) (envelope-from doconnor@gsoft.com.au) From: "Daniel O'Connor" To: freebsd-chat@freebsd.org Date: Thu, 11 Mar 2004 11:55:39 +1030 User-Agent: KMail/1.6 References: <404FAC50.6070603@pythonemproject.com> In-Reply-To: <404FAC50.6070603@pythonemproject.com> MIME-Version: 1.0 Content-Disposition: inline Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Message-Id: <200403111155.39591.doconnor@gsoft.com.au> X-Spam-Score: -1.5 () CARRIAGE_RETURNS,IN_REP_TO,QUOTED_EMAIL_TEXT,REFERENCES,SPAM_PHRASE_00_01,USER_AGENT X-Scanned-By: MIMEDefang 2.16 (www . roaringpenguin . com / mimedefang) cc: Rob cc: chat@freebsd.org Subject: Re: What makes Centrino so fast? X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 11 Mar 2004 01:25:43 -0000 On Thu, 11 Mar 2004 10:31, Rob wrote: > I have my own benchmark program that I use for number crunching. > It uses a mixture of Python and Numeric Python. > > Athlon 2166Mhz as reported by OS: 2m38.7s > Intel Centrino Pentium 1700 Mhz: 2m17s > > Is it just compiler optimization at play? Here's an interesting article on it -> http://arstechnica.com/cpu/004/pentium-m/pentium-m-1.html but in short.. better branch prediction, and micro-architecture improvments in general, and a slightly longer pipeline (for higher clocks vs a PIII) -- Daniel O'Connor software and network engineer for Genesis Software - http://www.gsoft.com.au "The nice thing about standards is that there are so many of them to choose from." -- Andrew Tanenbaum GPG Fingerprint - 9A8C 569F 685A D928 5140 AE4B 319B 41F4 5D17 FDD5 From owner-freebsd-chat@FreeBSD.ORG Wed Mar 10 17:25:43 2004 Return-Path: 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 AA92C16A4CE; Wed, 10 Mar 2004 17:25:43 -0800 (PST) Received: from cain.gsoft.com.au (cain.gsoft.com.au [203.31.81.10]) by mx1.FreeBSD.org (Postfix) with ESMTP id 9912743D1F; Wed, 10 Mar 2004 17:25:42 -0800 (PST) (envelope-from doconnor@gsoft.com.au) Received: from inchoate.gsoft.com.au (localhost [127.0.0.1]) (authenticated bits=0) by cain.gsoft.com.au (8.12.9/8.12.8) with ESMTP id i2B1PcQ9057806; Thu, 11 Mar 2004 11:55:39 +1030 (CST) (envelope-from doconnor@gsoft.com.au) From: "Daniel O'Connor" To: freebsd-chat@freebsd.org Date: Thu, 11 Mar 2004 11:55:39 +1030 User-Agent: KMail/1.6 References: <404FAC50.6070603@pythonemproject.com> In-Reply-To: <404FAC50.6070603@pythonemproject.com> MIME-Version: 1.0 Content-Disposition: inline Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Message-Id: <200403111155.39591.doconnor@gsoft.com.au> X-Spam-Score: -1.5 () CARRIAGE_RETURNS,IN_REP_TO,QUOTED_EMAIL_TEXT,REFERENCES,SPAM_PHRASE_00_01,USER_AGENT X-Scanned-By: MIMEDefang 2.16 (www . roaringpenguin . com / mimedefang) cc: Rob cc: chat@freebsd.org Subject: Re: What makes Centrino so fast? X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 11 Mar 2004 01:25:43 -0000 On Thu, 11 Mar 2004 10:31, Rob wrote: > I have my own benchmark program that I use for number crunching. > It uses a mixture of Python and Numeric Python. > > Athlon 2166Mhz as reported by OS: 2m38.7s > Intel Centrino Pentium 1700 Mhz: 2m17s > > Is it just compiler optimization at play? Here's an interesting article on it -> http://arstechnica.com/cpu/004/pentium-m/pentium-m-1.html but in short.. better branch prediction, and micro-architecture improvments in general, and a slightly longer pipeline (for higher clocks vs a PIII) -- Daniel O'Connor software and network engineer for Genesis Software - http://www.gsoft.com.au "The nice thing about standards is that there are so many of them to choose from." -- Andrew Tanenbaum GPG Fingerprint - 9A8C 569F 685A D928 5140 AE4B 319B 41F4 5D17 FDD5 From owner-freebsd-chat@FreeBSD.ORG Wed Mar 10 23:19:12 2004 Return-Path: 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 EF8B416A4CE for ; Wed, 10 Mar 2004 23:19:11 -0800 (PST) Received: from mail.blarg.net (zoot.blarg.net [206.124.128.9]) by mx1.FreeBSD.org (Postfix) with ESMTP id CFB5C43D3F for ; Wed, 10 Mar 2004 23:19:11 -0800 (PST) (envelope-from abowhill@blarg.net) Received: from kosmos.my.net (c-24-16-247-101.client.comcast.net [24.16.247.101]) by mail.blarg.net (Postfix) with ESMTP id 30EA934145 for ; Wed, 10 Mar 2004 23:19:10 -0800 (PST) Received: from kosmos.my.net (localhost [127.0.0.1]) by kosmos.my.net (8.12.11/8.12.10) with ESMTP id i2B7J0LF003020 for ; Wed, 10 Mar 2004 23:19:05 -0800 (PST) (envelope-from kosmos@kosmos.my.net) Received: (from kosmos@localhost) by kosmos.my.net (8.12.11/8.12.10/Submit) id i2B7J0Xh003019 for freebsd-chat@freebsd.org; Wed, 10 Mar 2004 23:19:00 -0800 (PST) (envelope-from kosmos) Date: Wed, 10 Mar 2004 23:18:59 -0800 From: Allan Bowhill To: freebsd-chat@freebsd.org Message-ID: <20040311071859.GA2970@kosmos.my.net> Mail-Followup-To: freebsd-chat@freebsd.org References: <200403041513.00003.DavidJohnson@Siemens.com> <200403050615.55106.dgw@liwest.at> <20040305155015.Y38020@haldjas.folklore.ee> <40489B55.1060407@centtech.com> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="qDbXVdCdHGoSgWSk" Content-Disposition: inline In-Reply-To: <40489B55.1060407@centtech.com> X-URL: http://www.blarg.net/~abowhill/ User-Agent: Mutt/1.5.6i Subject: Re: FreeBSD Most wanted X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 11 Mar 2004 07:19:12 -0000 --qDbXVdCdHGoSgWSk Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On 0, Eric Anderson wrote: :Narvi wrote: :[..snip snip snippety snip..] : :>>I'm not speaking of your average code, I'm speaking of high-speed assemb= ly :>>language programs. :>> :> :> :>and how many millions of lines of that have you written and maintained? :>Are you sure it would not be faster if it was re-written in C and compiled :>? : :I started this thread for more as a list of features FreeBSD needs in=20 :order to gain additional user base - I think it has successfully=20 :dribbled into -chat worthy commentary, so let's move it off advocacy pleas= e? If you like small and fast, check out the "Whirlwind tutorial on creating r= eally=20 teensy elf executables for Linux": http://www.muppetlabs.com/~breadbox/software/tiny/teensy.html --=20 Allan Bowhill abowhill@blarg.net 328b9bc80ca0b5c14518554adde19cea "It's kind of fun to do the impossible." -- Walt Disney --qDbXVdCdHGoSgWSk Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.3 (FreeBSD) iD8DBQFAUBLiBC/kSIeFE54RAmReAKC3q4Jv6/c8ht++wAxyL+H0Dm2cBwCfbf39 x+/0Qc1Oaqd5Yz791UMFSCg= =zicV -----END PGP SIGNATURE----- --qDbXVdCdHGoSgWSk-- From owner-freebsd-chat@FreeBSD.ORG Thu Mar 11 03:27:02 2004 Return-Path: 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 9DB9416A4CE for ; Thu, 11 Mar 2004 03:27:02 -0800 (PST) Received: from haldjas.folklore.ee (Haldjas.folklore.ee [193.40.6.121]) by mx1.FreeBSD.org (Postfix) with ESMTP id F0B4443D49 for ; Thu, 11 Mar 2004 03:27:01 -0800 (PST) (envelope-from narvi@haldjas.folklore.ee) Received: from haldjas.folklore.ee (localhost [127.0.0.1]) by haldjas.folklore.ee (8.12.10/8.12.10) with ESMTP id i2BBQvUA087753; Thu, 11 Mar 2004 13:26:57 +0200 (EET) (envelope-from narvi@haldjas.folklore.ee) Received: from localhost (narvi@localhost)i2BBQvtJ087750; Thu, 11 Mar 2004 13:26:57 +0200 (EET) (envelope-from narvi@haldjas.folklore.ee) Date: Thu, 11 Mar 2004 13:26:57 +0200 (EET) From: Narvi To: Rob In-Reply-To: <404FAC50.6070603@pythonemproject.com> Message-ID: <20040311024415.R68396@haldjas.folklore.ee> References: <404FAC50.6070603@pythonemproject.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-Spam-Status: No, hits=0.0 required=8.0 tests=none autolearn=no version=2.63 X-Spam-Checker-Version: SpamAssassin 2.63 (2004-01-11) on haldjas.folklore.ee cc: chat@freebsd.org Subject: Re: What makes Centrino so fast? X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 11 Mar 2004 11:27:02 -0000 On Wed, 10 Mar 2004, Rob wrote: > I have my own benchmark program that I use for number crunching. > It uses a mixture of Python and Numeric Python. > > Athlon 2166Mhz as reported by OS: 2m38.7s > Intel Centrino Pentium 1700 Mhz: 2m17s > it has 1mb 1.7ghz l2 cache? it also probably has a tweaked version of the P3 core (with sse2 added) instead of P4 core. but intel doesn't talk much about how the centrino core is different (in non-marketing terms) from p6 (used in ppro/pii/piii) or pentium4 core. > Is it just compiler optimization at play? > > Sincerely, > > Rob > From owner-freebsd-chat@FreeBSD.ORG Thu Mar 11 07:01:52 2004 Return-Path: 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 B523B16A4CE for ; Thu, 11 Mar 2004 07:01:52 -0800 (PST) Received: from imf07aec.mail.bellsouth.net (imf07aec.mail.bellsouth.net [205.152.59.55]) by mx1.FreeBSD.org (Postfix) with ESMTP id 4218843D1F for ; Thu, 11 Mar 2004 07:00:37 -0800 (PST) (envelope-from freebsd-mar2004@threespace.com) Received: from vwinxp.threespace.com ([68.215.179.49]) by imf20aec.mail.bellsouth.netESMTP <20040311140214.IEOD4834.imf20aec.mail.bellsouth.net@vwinxp.threespace.com> for ; Thu, 11 Mar 2004 09:02:14 -0500 Message-Id: <4.3.2.7.2.20040311090102.0167fc18@mail.threespace.com> X-Sender: ThreeSpace Corporation Private E-Mail User X-Mailer: Secure Internet E-Mail ver. 1.1 Beta Date: Thu, 11 Mar 2004 09:01:59 -0500 To: FreeBSD Chat From: Chip Morton Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed Organization: ThreeSpace Corporation Subject: I'm glad to see that somebody "gets it." X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 11 Mar 2004 15:01:52 -0000 http://www.infoworld.com/article/03/10/10/40OPconnection_1.html From owner-freebsd-chat@FreeBSD.ORG Thu Mar 11 07:19:10 2004 Return-Path: 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 C3EC216A4CE for ; Thu, 11 Mar 2004 07:19:10 -0800 (PST) Received: from ns1.tiadon.com (SMTP.tiadon.com [69.27.132.161]) by mx1.FreeBSD.org (Postfix) with ESMTP id BAE0743D41 for ; Thu, 11 Mar 2004 07:19:09 -0800 (PST) (envelope-from kdk@daleco.biz) Received: from daleco.biz ([69.27.131.0]) by ns1.tiadon.com with Microsoft SMTPSVC(6.0.3790.0); Thu, 11 Mar 2004 09:19:34 -0600 Message-ID: <40508368.6000403@daleco.biz> Date: Thu, 11 Mar 2004 09:19:04 -0600 From: "Kevin D. Kinsey, DaleCo, S.P." User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.6) Gecko/20040212 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Chip Morton References: <4.3.2.7.2.20040311090102.0167fc18@mail.threespace.com> In-Reply-To: <4.3.2.7.2.20040311090102.0167fc18@mail.threespace.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-OriginalArrivalTime: 11 Mar 2004 15:19:34.0750 (UTC) FILETIME=[429337E0:01C4077C] cc: FreeBSD Chat Subject: Re: I'm glad to see that somebody "gets it." X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 11 Mar 2004 15:19:10 -0000 Chip Morton wrote: > http://www.infoworld.com/article/03/10/10/40OPconnection_1.html > Heh...maybe he needs to switch anyway. "./configure make, etc.?" If we tell him it's just *one* command line, surely he'd be running to us with open arms.... :-) Kevin Kinsey DaleCo, S.P. From owner-freebsd-chat@FreeBSD.ORG Thu Mar 11 07:35:11 2004 Return-Path: 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 548B916A4D0 for ; Thu, 11 Mar 2004 07:35:11 -0800 (PST) Received: from mail19a.dulles19-verio.com (mail19a.dulles19-verio.com [198.170.241.2]) by mx1.FreeBSD.org (Postfix) with SMTP id D282D43D46 for ; Thu, 11 Mar 2004 07:35:10 -0800 (PST) (envelope-from rob@pythonemproject.com) Received: from www.pythonemproject.com (198.104.176.109)3-0948229308 for ; Thu, 11 Mar 2004 10:35:09 -0500 (EST) Message-ID: <4050872D.90503@pythonemproject.com> Date: Thu, 11 Mar 2004 07:35:09 -0800 From: Rob User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.6) Gecko/20040217 X-Accept-Language: en-us, en MIME-Version: 1.0 References: <404FAC50.6070603@pythonemproject.com> <200403111155.39591.doconnor@gsoft.com.au> In-Reply-To: <200403111155.39591.doconnor@gsoft.com.au> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit To: chat@freebsd.org X-Loop-Detect: 1 cc: chat@freebsd.org Subject: Re: What makes Centrino so fast? X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 11 Mar 2004 15:35:11 -0000 Daniel O'Connor wrote: > On Thu, 11 Mar 2004 10:31, Rob wrote: > >>I have my own benchmark program that I use for number crunching. >>It uses a mixture of Python and Numeric Python. >> >>Athlon 2166Mhz as reported by OS: 2m38.7s >>Intel Centrino Pentium 1700 Mhz: 2m17s >> >>Is it just compiler optimization at play? > > > Here's an interesting article on it -> > http://arstechnica.com/cpu/004/pentium-m/pentium-m-1.html > > but in short.. better branch prediction, and micro-architecture improvments in > general, and a slightly longer pipeline (for higher clocks vs a PIII) > Great article Dan! Thanks for the pointer. Rob. From owner-freebsd-chat@FreeBSD.ORG Sat Mar 13 21:12:04 2004 Return-Path: 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 2743E16A4CE for ; Sat, 13 Mar 2004 21:12:04 -0800 (PST) Received: from VARK.homeunix.com (adsl-68-121-162-101.dsl.pltn13.pacbell.net [68.121.162.101]) by mx1.FreeBSD.org (Postfix) with ESMTP id EC0F043D1F for ; Sat, 13 Mar 2004 21:12:03 -0800 (PST) (envelope-from das@FreeBSD.ORG) Received: from VARK.homeunix.com (localhost [127.0.0.1]) by VARK.homeunix.com (8.12.11/8.12.10) with ESMTP id i2E5BSuo057493; Sat, 13 Mar 2004 21:11:29 -0800 (PST) (envelope-from das@FreeBSD.ORG) Received: (from das@localhost) by VARK.homeunix.com (8.12.11/8.12.10/Submit) id i2E5BSYI057492; Sat, 13 Mar 2004 21:11:28 -0800 (PST) (envelope-from das@FreeBSD.ORG) Date: Sat, 13 Mar 2004 21:11:28 -0800 From: David Schultz To: "Daniel O'Connor" Message-ID: <20040314051128.GA57404@VARK.homeunix.com> Mail-Followup-To: Daniel O'Connor , freebsd-chat@FreeBSD.ORG, Rob References: <404FAC50.6070603@pythonemproject.com> <200403111155.39591.doconnor@gsoft.com.au> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <200403111155.39591.doconnor@gsoft.com.au> cc: Rob cc: freebsd-chat@FreeBSD.ORG Subject: Re: What makes Centrino so fast? X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 14 Mar 2004 05:12:04 -0000 On Thu, Mar 11, 2004, Daniel O'Connor wrote: > On Thu, 11 Mar 2004 10:31, Rob wrote: > > I have my own benchmark program that I use for number crunching. > > It uses a mixture of Python and Numeric Python. > > > > Athlon 2166Mhz as reported by OS: 2m38.7s > > Intel Centrino Pentium 1700 Mhz: 2m17s > > > > Is it just compiler optimization at play? > > Here's an interesting article on it -> > http://arstechnica.com/cpu/004/pentium-m/pentium-m-1.html > > but in short.. better branch prediction, and micro-architecture improvments in > general, and a slightly longer pipeline (for higher clocks vs a PIII) You're right that the longer pipeline allows the processor to be clocked higher, but for a *given* speed (e.g. 1700 MHz), a longer pipeline is actyually a disadvantage; longer pipelines cause more stalls and higher branch misprediction costs. The better branch predition merely attempts to hide the penalty of the longer pipeline. I don't know why the Centrino performs better than the Athlon in this case, though. If you really care, you'll probably have to factor the benchmark into specific, simple tests that demonstrate the performance difference, play with compiler optimizations, etc. From owner-freebsd-chat@FreeBSD.ORG Sat Mar 13 22:06:38 2004 Return-Path: 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 4772D16A4CE; Sat, 13 Mar 2004 22:06:38 -0800 (PST) Received: from cain.gsoft.com.au (cain.gsoft.com.au [203.31.81.10]) by mx1.FreeBSD.org (Postfix) with ESMTP id 3589F43D1D; Sat, 13 Mar 2004 22:06:37 -0800 (PST) (envelope-from doconnor@gsoft.com.au) Received: from inchoate.gsoft.com.au (localhost [127.0.0.1]) (authenticated bits=0) by cain.gsoft.com.au (8.12.9/8.12.8) with ESMTP id i2E66WQ9063517; Sun, 14 Mar 2004 16:36:33 +1030 (CST) (envelope-from doconnor@gsoft.com.au) From: "Daniel O'Connor" To: David Schultz Date: Sun, 14 Mar 2004 16:36:29 +1030 User-Agent: KMail/1.6 References: <404FAC50.6070603@pythonemproject.com> <200403111155.39591.doconnor@gsoft.com.au> <20040314051128.GA57404@VARK.homeunix.com> In-Reply-To: <20040314051128.GA57404@VARK.homeunix.com> MIME-Version: 1.0 Content-Disposition: inline Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Message-Id: <200403141636.29686.doconnor@gsoft.com.au> X-Spam-Score: -1.5 () CARRIAGE_RETURNS,IN_REP_TO,QUOTED_EMAIL_TEXT,REFERENCES,SPAM_PHRASE_00_01,USER_AGENT X-Scanned-By: MIMEDefang 2.16 (www . roaringpenguin . com / mimedefang) cc: Rob cc: freebsd-chat@FreeBSD.ORG Subject: Re: What makes Centrino so fast? X-BeenThere: freebsd-chat@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Non technical items related to the community List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 14 Mar 2004 06:06:38 -0000 On Sun, 14 Mar 2004 15:41, David Schultz wrote: > > but in short.. better branch prediction, and micro-architecture > > improvments in general, and a slightly longer pipeline (for higher clocks > > vs a PIII) > > You're right that the longer pipeline allows the processor to be > clocked higher, but for a *given* speed (e.g. 1700 MHz), a longer > pipeline is actyually a disadvantage; longer pipelines cause more > stalls and higher branch misprediction costs. The better branch > predition merely attempts to hide the penalty of the longer > pipeline. I don't know why the Centrino performs better than the > Athlon in this case, though. If you really care, you'll probably > have to factor the benchmark into specific, simple tests that > demonstrate the performance difference, play with compiler > optimizations, etc. I said the longer pipeline was for higher clocks, the improved branch prediction could have a benefit over and above the penalty imposed by a longer pipeline, but as always I would imagine it would depend on the type of code being run through it :) -- Daniel O'Connor software and network engineer for Genesis Software - http://www.gsoft.com.au "The nice thing about standards is that there are so many of them to choose from." -- Andrew Tanenbaum GPG Fingerprint - 9A8C 569F 685A D928 5140 AE4B 319B 41F4 5D17 FDD5