From owner-freebsd-questions Thu Apr 19 13:41:16 2001 Delivered-To: freebsd-questions@freebsd.org Received: from oahu.WURLDLINK.NET (oahu.WURLDLINK.NET [216.235.52.1]) by hub.freebsd.org (Postfix) with ESMTP id D34B137B42C for ; Thu, 19 Apr 2001 13:41:11 -0700 (PDT) (envelope-from vince@oahu.WURLDLINK.NET) Received: from localhost (vince@localhost) by oahu.WURLDLINK.NET (8.9.3/8.9.3) with ESMTP id KAA39751; Thu, 19 Apr 2001 10:40:30 -1000 (HST) (envelope-from vince@oahu.WURLDLINK.NET) Date: Thu, 19 Apr 2001 10:40:29 -1000 (HST) From: Vincent Poy To: Jeremiah Gowdy Cc: Charles Burns , , , , , Subject: Re: the AMD factor in FreeBSD In-Reply-To: <001b01c0c8e3$a65f78e0$015778d8@sherline.net> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-questions@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG On Thu, 19 Apr 2001, Jeremiah Gowdy wrote: > > > > Thanks for the insight but what about in a Single CPU environment? > > > > > > This depends on what you plan to do. The general consensus among the > > > hardware reviewers is that the Athlon is overall faster than any other > x86 > > > compatible CPU. > > > > Yep, that's what I read as well but are there any drawbacks to > > being faster such as compatibilty and all that stuff? > > The compatibility and all that stuff days of the K5 and K6 are long gone. > Today, generally, if a cpu is x86 compatible, that's that. There are no > compatibility issues with the Athlon. That's good to hear but isn't there the issue of whether the software is optimized for the Intel CPU or the AMD CPU? I thought that factor still exists. > > > The only significant performance advantage that the Pentium 3 has over > the > > > Athlon is that its l2 cache memory is _much_ faster than that of the > Athlon. > > Could you explain this ? If you're comparing Thunderbirds to Coppermines, I > didn't think that was the case. > > > > The Athlon has a superior floating point unit that is, in addition, more > > > deeply pipelined. When using software that isn't optimized for any > > > particular FPU, the Athlon is typically just under 30% faster. (Some > > > examples of this can be seen on comparisons between the two at > Anandtech) > > > > Yeah, that's what I am concerned about. It seems that most things > > are optimized for the Intel CPU's. While the FPU is faster on the Athlon > > than the Intel, what about the non-FPU area? > > In business applications benchmarks the Athlon always stomps the P3. True but isn't business applications more of what's run on the Microsoft platform and not really the FreeBSD platform? > > > The Athlon can take more advantage of higher memory bandwidth than the > P3 > > > (but probably not the P4), thus you can get a greater performance > benefit in > > > some cases using DDR RAM. > > > > Speaking about DDR RAM, what kind of performance hits would there > > be using DDR versus non-DDR RAM? > > If I remember correctly, depending on the type the best SDRAM gets about 800 > megs/sec. DDR SDRAM comes in two flavors, 1.6 gigs/sec and 2.1gigs/sec. Interesting but what about percentage wise? > > > The Athlon is much, much cheaper. Motherboards, however, are more > expensive. > > > The overall cost ends up lower with the Athlon, especially if you are > > > considering the price/perormance ratio. > > > > Yeah, that's what I realized as well. It seems like the VIA and > > AMD chipset based motherboards costs a lot more than the Intel variants. > > You can get an Athlon motherboard for $100. Even if the Intel motherboard > was half that, at $50, the difference in the prices of the cpus is FAR more > than $50. Up to $200 in the higher end processors. People always speak of > the higher cost of Athlon motherboards but I don't see the point if the AMD > cpu is 40% cheaper and the difference in motherboard prices is relatively > pennies when you're speaking of a multi-hundred dollar purchase. Yeah but the Athlon motherboards at $100 are probably crappy. I'll give a example. the ABIT BE6II v2.0 which is Intel 440BX based and the ABIT KT7A-RAID which is VIA based. > > Thanks, I'm familiar with all of those. I guess I just wanted to > > know how they do under FreeBSD since all the sites really benchmark it > > under Windows. > > It's the same. If the code is written and compiled properly, the difference > should be seen in all OSes. True but isn't most code still optimized for Intel CPU's though? Cheers, Vince - vince@WURLDLINK.NET - Vice President ________ __ ____ Unix Networking Operations - FreeBSD-Real Unix for Free / / / / | / |[__ ] WurldLink Corporation / / / / | / | __] ] San Francisco - Honolulu - Hong Kong / / / / / |/ / | __] ] HongKong Stars/Gravis UltraSound Mailing Lists Admin /_/_/_/_/|___/|_|[____] Almighty1@IRC - oahu.DAL.NET Hawaii's DALnet IRC Network Server Admin To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-questions" in the body of the message