Follow Slashdot stories on Twitter

 


Forgot your password?
Close
typodupeerror
×
Hardware

Linux Intel Chipset Comparison 38

Posted by timothy from the don't-want-those-nt-performance-levels dept.
Diabolus writes: "AnandTech have done a comparison of Intel-CPU chipsets on Linux here. It talks about performance, stability and support issues for the various chipsets; apparently an Athlon chipset comparison is due shortly. Nice to see that it's not just 3D performance now -- Linux is becoming more mainstream among the h/w enthusiast crowd." This is a cool followup to see to AnandTech's October comparison of video cards under Linux.
This discussion has been archived. No new comments can be posted.

Linux Intel Chipset Comparison More

Linux Intel Chipset Comparison

Comments Filter:
  • I've been running a dual boot system for the last week. Working between the two on the same system has proven to me that Linux runs better on the setup that I have. Far more stable. The processing seems to happen much faster. I have a piii 500 with a 7200 rpm 27 gig drive (fat32/win98 single partition), and a 5400 rpm 3.2 gig(3 partition, 100mb swap). I had been running on an ATA66 but that's been removed for the Red Hat 7 Install. So I think it might be at 33 onboard.

    To make this long, not very technical, story short, Linux has proven it's speed and stability with the same hardware. What I find interesting i that Linux is running on the slower drive but it still runs faster.
  • It was my understanding that the "big" benchmark Spec (the one that supposedly everyone relies on) is platform-independent. That it doesn't really use a "OS" to run, per se.

  • Re:P3 800 vs K6s 500 (Score:1)

    by Anonymous Coward
    You wann know why????

    Read:
    "Why Aren't Operating Systems Getting Faster As Fast As Hardware?"
    by: John Ousterhout

    Don't worry you open source zombies it's available online and free.

    Oh and don't forget to click a banner or two.
  • Ok, improbably way off topic on this one, but why dont people like RAMBUS? Is the technology flawed? Or was Intel's inplementation flawed? Had the technology been Free, would there such an issue?

    --
  • It seems older distributions have trouble booting on the P4. I doubt win2k is really any better optimized for p4, but It seems you will likely have fewer headaches with win2k, than linux on a p4 (for at least a month or two anyway)
  • Probobly because when you build your system, you bought parts that you wanted.

    You said you bought Dell, well a lot of people recomend that brand. But I found them sleeping in bed with Intel. No matter how slow/expensive Intel chips are, they still buy them.

    A lot of things can determine the speed of the system not just CPU. For instance you could get RAID with 2HD, this will double your HD performace(if you use striping 0, or 0+1) HD performance is where you gonna see the difference(you always buy the fastes HD available) because it's the slowest link in the system, Memory is also important I found 128 is not enought if you use more then one application.
  • An AGP port or slot is where you plug in an expansion card which utilises the AGP bus. Just as with PCI slots/bus, and ISA slots/bus. If you want more technical info on what a bus is and isn't, email me or reply, but this post is already rather offtopic.

    JJ

  • ...it supports PC100 & PC133 SDRAM only. Intel had to eat it words and finally produce a chipset that actually supports PC133 SDRAM. The 815 is very stable & reliable and a good alternative. I currently use an 815e motherboard and have been quite pleased. The only downside that I can think of is it's 512MB RAM limitation.
  • A big 'thankyou' to the guys at Anandtech [anandtech.com] for this one. This has always been my major bone with Linux - hardware vendors rarely even know if what they sell will work with Linux, let alone how well!

    How about a new symbol to go alongside the ubiquitous 'Designed for Windows {95/98/ME/NT}' and 'plug & pray' ones on new hardware? Something like 'Designed for Linux - designed to work', or even just a pretty picture so you know it's tested and includes Linux drivers.

    Then I might actually be able to tell if my new kit works on a decent OS before forking out the hardearned or waiting for someone else to try it first!

    JJ

  • Yep, it would be nice. I'll get around to it in due time. The i840 and other "server" chipsets would not have fit properly in this comparison. We'll save those for later. There are plenty of chipsets to compare, and this article was meant to just get my feet wet in chipset benchmarking with the standard consumer Pentium III chipsets. I've learned a lot from writing this article, and it'll help when I get to writing about more chipsets in the future.

    Jeff Brubaker
    Linux Tech Writer
    AnandTech
  • Of course, cutting edge technologies (re: Video Cards) are not going to work under Linux especially if hardware vendors are not writing out the Linux drivers right out the gate.

    I have setup a zillion Linux servers/workstations for every type of hardware ranging from a 386 to a quad Intel Pentium III Xeon with very little trouble (CD-R drives, certain funky NIC's I have never heard of before, etc.)

    The only thing I can recommend to my friends when buying equipment for Linux workstations/servers is don't buy the latest video card, get a nic you know and love, a real modem will be nice (not win- ), basic sound card and everything is great.

  • I find it quite curious that there is no explaniation of why the BX chipset gave the best results in the real-world test (kernel compile) while it lagged behind (albeit only slightly) in every feature-specific test.
  • I'll field all those questions. People don't like Rambus because it is insanely expensive ($500 to $800 for a stick of 128MB). Furthermore, it comes in paired banks, much like 72-pin SIMMs did; that means that you either have to buy two RIMMs or one RIMM and a "blank" RIMM (which is just as expensive; probably over $100). Also, a new RAM standard means new motherboards, and the boards are about twice as expensive as an Athlon chipset, or even the 440BX.

    Both the Rambus technology and Intel's implementation are flawed; recently, it was discovered that Rambus introduces MORE latency into the system (probably due to its packet structure), and not less (as was implied/marketed by Rambus, who touted the high clock speed of the RAM).

    Intel's smear campaign to introduce Rambus to the world ultimately failed due to the astronomical costs of the RIMMs; people didn't want to spend $2300 on a Pentium III 733 with Rambus when they could have bought an Athlon 900 for $1600.

    If the Rambus technology had been free, then maybe Rambus Technologies, Inc. LLP LLC, CRAP, etc. wouldn't have been the lawfirm that it seems to be right now. Maybe Rambus would've had its stint in the computer industry - only to be ousted by DDR when it was found that DDR was inherently better.

  • Ah yes - but I want the performance offered by top-range kit. Which is my problem. When I first got into Linux, a few years back, I was broke and therefore Linux liked my (old, reliable, well-known) kit. Now, I have a bit more cash and I've had to go back to Windoze to make my (new, fast) stuff work...

    Great. A step backwards in the name of progress.

    JJ

  • It looks as though You have Ported to run properly, under the most Anal of Conditions. Have a nice day.

    From: The Troglodyte
  • Actually, that's not correct. Look at the memory benchmarks again. The Nbench results show the BX as falling in second place (but only by a slight amount) while the Unixbench results show it actually beating out both the 815 and the VIA chipsets. Memory bandwidth is one of the larger chipset limiting factors in kernel compilation, so the BX winning the kernel compilation only reflects the scores in memory performance.

    Note that the BX didn't beat the 815 by much in the kernel compilation tests, while the VIA performed notably worse than the other two chipsets. This is similar to other benchmarks involving memory performance (in the same article) in which the VIA lost every one.

    Jeff Brubaker
    Linux Tech Writer
    AnandTech
  • If you want an accurate benchmark, you have to test under the OS you are going to use. As much as I would like to see some good, honest Linux benchmarks, how a chip will run in the environment it will be used in is what really matters.

  • my curiosity has... (Score:1)

    by Anonymous Coward
    ... piqued.

  • Re:More accurate? (Score:3)

    by evanbd ( 210358 ) on Sunday December 17, 2000 @07:37PM (#552781)
    In a very fundamental sense, they can't be. Period

    By definition, what a benchmark is is just a measurement of the speed of a particular piece of hardware at running a particular piece of software. That includes the OS. It makes sense to compare different pieces of software on the same hardware to compare how fast they are at solving a particular problem, or the same software on different hardware to see how fast the hardware is at a particular task, or even different pieces of hardware and software performing a similar task. The win98 benchmarks are (barring bad benchmarking techniques, etc) as accurate at measuring the win98 solution to a problem as the linux ones are at measuring the linux solution to the same problem. They may be slower, or faster, but they fundamentaly are no more accurate. They both tell how fast the hardware/software configuration is at a task.

    What really matters is what task you care about, and I'm guessing you care about linux doing something, so linux benchmarks would have more meaning to you. For various reasons, I run windows (and can't switch easily enough to linux, but that's a different discussion), so the windows ones matter more to me. However, I am quite glad to see both being run.

  • i'm running an Athlon 700 w/ and AMD Irongate 750 chipset (MSI K7 Pro) w/512 Megs ram. Built it in march, and i run linux on it, and it performs wonderfully, i have not had a single issue with hardware compatability. I'm running a celeron based system right next to it, and neither have given me problems.
  • They would certainly be more accurate at how the hardware will perform under Linux!

    Though the writeup above seems to vaguely indicate CPU speed was what was being measured, video card performance was a big part of these benchmarks. These days, with the complexity of all types of add-on cards, and especially video cards, drivers play a fairly large role in the overall measured speed, and since Windows and Linux drivers will clearly be different, you could side hugely different numbers on each platform. Even under Windows itself, a card like the GeForce 2 will perform nearly 10% faster or slower depending upon the version of Nvidia's drivers you have installed.

    This is true also for other components, like disks, where the underlying code in the OS and device driver level comes into play.

  • Not only that, but all the JavaScript locked up my browser.
  • I hearby proclaim this story as BANNER BAIT!

  • But what about recoil?

    Oh, it's self-coiling.

    Take your buzzword bullshit elsewhere, troll.

    --Joe
    --
    Program Intellivision! [schells.com]
  • I don't understand how posting a story about Linux benchmarks is considered to be "banner bait." The same number of people are going to http on over to www.slashdot.org whether there is an article about CmdrTaco's underwear or an article about AnandTech wanting to benchbark with Linux.

    Only if the story is somehow broadcast into the minds of non-slashdot readers could your theory be even remotely true.

    It may generate a few more hits due to subsequent trolling and flamewars, but how many of the trolls and flamers actually click (or even notice) banner ads at all?
  • They completely ignored the higher-end chipsets like Intel's 840 and the ServerWorks ServerSet III; it would have been nice to see those mentioned.
  • There's really only one chipset worth having at the moment and that's the VIA KT133. Although the performance isn't fantastic, it's better than any of the alternatives until we start seeing DDR mobos hit the shelves (any time now, hopefully). The standard 2.2 series kernels are quite happy with them, and applying the IDE patches [linux-ide.org] to the kernel will give you reasonable performance. The 2.4-test series have this built in. Of course, if you want 3D to work, that's a whole different kettle of fish :) .
  • It might be a good idea to get yourself a dictionary and look up "sarcasm" and "irony". Perhaps "humor" first so that you can understand the others.
  • i wonder how linux would do with the pentium 4 code..
    i heard that win2k was better optimized for the p4 .
    i can't wait for a comparison between p4 code handling on linux and on windows..
    anybody got any idea where it'll be up soon ?

    "The world is coming to an end. Please log orff."
  • I just purchased 2 Dell P3 800s with 128 megs of ram for my business, and I gotta tell ya, I have not seen any improvements over my older home built K62 500 with 96 megs of ram. Running Win ME or Linux either, the processing power just doesn't seem to be there.

  • ...the 82443BX is still the best one that Intel has released so far. The 820, 815, and 840 are all so plagued with problems due to the Rambus incident (the entire existence of Rambus can be classified as an incident; when Rambus dies, progress continues). Not until Intel releases their DDR chipset will another viable Intel offering be seen.
  • I'm sure Jeff @ Anandtech will get around to it; he has enough on his hands already (um, yes I know him). :-)

    On that note I'm glad to see reviewers (Tom's, Anandtech, DukeOfURL, etc.) beginning to slant toward Linux and *BSD in their hardware and software reviews. This sort of information would have made my life _much_ easier in choosing compatible hardware earlier.
  • Last year I read a review in one of the better UK magazines. They were doing a comparative test of a number of SCSI and EIDE add-on boards, including a number that did RAID.

    The benchmark results varied significantly, particularly for one RAID conroller which gave utterly appalling results. It then dawned on me why this was the case. The magazine had performed all their benchmarks under Windows95, yet the RAID controller had no Windows95 drivers available. For this controller they had run their benchmarks using the 16-bit emulation mode.

    This is not the first time I've seen such benchmarks run. I've lost count of the number of IDE based systems I've seen not running in optimum UDMA mode.

  • Would benchmarks under Linux be more accurate than those under Windows? It probalby makes no difference, but my curiousity has peaked..

  • Accurate benchmarks? Do such things exist ;)
  • So far, about the only thing I've seen come from benchmark tests is a ton of flame wars. People see these and they immediately say one of two things.

    1) this proves MY system/OS/chip/HD/etc.. is best.
    or
    2) This beenchmark is screwed.

    I mean a linux benchmark on Pentiums? Yea here comes a linux Vs. Winblows or Intel Vs. AMD flame war.

    Besides did anyone really NEED a benchmark to see that the best computer is a AMD chip with Linux running on it?

  • Coincidence ... but I was just hunting for this when the article came up. I am looking to build a new computer with with an AMD athlon chip but all the reviews about motherboards on Toms Hardware [tomshardware.com] and Anandtech [anandtech.com] seem to have a MS Windows centric view.

    I hope they do come out with a review for linux but that just might take time. SO what have your experiences been under linux ? Anything people like me should be keeping an eye out for ? Or something you would definitely recommend ?
  • That Linux is becoming more mainstream at all? When you can buy various distributions at Wal-Mart or Best Buy, it gets people who normally would not have access interested in it. Plus, you're guarenteed to get a good copy with the manuals...

    But when it becomes available in chain stores like those, of course hardware makers are going to do things like this. They see where the cash lies, and what with the supposedly imminent M$ break-up (not to mention their lackluster earnings in the second quarter), they're hedging their bets.

    Just my 2 shekels.

    Kierthos

Slashdot Top Deals

If it wasn't for Newton, we wouldn't have to eat bruised apples.

Close