Back to Article

  • bozilla - Sunday, October 24, 2004 - link


    I totally understand what you are talking about. I'm a graphic designer and do web development and I put heavy loads with multiple applications opened and Athlons just can't keep up. The fact is that when it comes to work environment like I have (Photoshop, Outlook, Dreamweaver, Flash) opened constantly and switching between them even P4 2.8C blows A64s @ 3000+ out of the water. It's an issue that AMD always had problems with.

    That article on infotech is right on the money.
    For basic computing with 1-2 apps opened A64s might perform better, but in the long run, what good is that when I start working seriously the machine slows down so much that I get frustrated.

  • AtaStrumf - Wednesday, October 20, 2004 - link

    I appreciate your willingness to help (BTW, I have VIA K8T800Pro chipset), but I still have a few things to try before I start bothering other people :-) Reply
  • justly - Tuesday, October 19, 2004 - link

    I doubt I can help you since I dont have a A64 or use bittorrent or nero, but someone else might be able to if you give them a chance. Also I have no way to contact you even if I did find out anything. Without knowing the details of your system I am also at a disadvantage, but just to take a wild guess at it, do you by chance have a Nforce 3 chipset, if you do is it possible to disable the firewall in the chipset to see if that has anything to do with some of your problems.
  • nottlv - Tuesday, October 19, 2004 - link

    Regarding the Java tests, you should disclose which JVM and version was used as there are some significant differences between them. Throwing some other JVMs into the mix would be an intersting comparison as well, though you would really need to run Linux to get the broadest spectrum. There are JVMs that do include optimization for the Opteron, including 64-bit support. The latest Sun JVM 1.5/5.0 does for both W2k3, Solaris and Linux (which is hardly surprising since Sun is an ardent supporting of Opteron on the low end), as does the Blackdown Project's JVM 1.4.2 for the 64-bit versions of SuSE and RHEL Linux. IBM also plans to release a 64-bit optimized JVM for AMD64/EM64T for both Windows and Linux shortly.

    There has been some discussion of some of these JVMs elsewhere:
  • RZaakir - Tuesday, October 19, 2004 - link

    #42, That's funny, you named 2 things that I constantly do on my A64. I use BitTorrent religiously on files large and small and I use Nero 6 Ultra to Burn all DVD+/-R discs as well. No problems here. I can't speak for Folding @ Home though. Reply
  • AtaStrumf - Tuesday, October 19, 2004 - link

    I have found AT forums to be mostly useless. I use other forums for my problems, that's why you haven't found any of my posts, but if you would like to help explain why I'm getting bittorrent DL corruption, while Folding@home is running and why suddenly NERO's identity checks are failing after burning a DVD-/+R after more that 50 successful burns on the same equipment with the obvious exception of the CPU and MOBO, you are very welcome to do so. Reply
  • sprockkets - Monday, October 18, 2004 - link

    nvm, it's mentioned in the graphs...

  • justly - Monday, October 18, 2004 - link

    The search function shows that in the last 3 months you have only posted in 1 thread, maybe...just maybe , someone could help you figure out those problems if you bothered to ask. BTW is your A64 3200+ still running at 2800+ speeds (that might have someting to do with how it compares to your old XP).

    While it might be true that SOME "AMD fanboys" have an extremly distorted opinion that HT has no benifit, I still believe the majority of people, AMD fanboys included, understand that HT does help with multitasking (the real question is how much and in what circumstances).
  • Jason Clark - Monday, October 18, 2004 - link

    #37, 2-2.5% isn't a lead it's nearly deviation... They are pretty much neck and neck, except for .NET where some optimized code gave intel a boost (as the article indicates). Reply
  • AtaStrumf - Monday, October 18, 2004 - link

    OMG AMD fanboys just can't take the fact that Opteron isn't the fastest thing out there no matter what the circumstances.

    The fact is that A64 sucks in high stress multitasking and P4 at high MHz (>3 GHz) excels at it. Get over it will you!!!

    You hyped up this A64 so much I bought a A64 3200+ Newcastle and I feel a big empty space where my money used to be. It's hardly any better than my old Athlon XP at 3200+ speeds. Certainly not worth the price difference, not to mention all sorts of troubles I'm having that I just can't figure out what's causing them. CPU, MOBO, RAM???

  • Saist - Monday, October 18, 2004 - link

    I just wanted to comment that as I read the graphs, the opteron lead all but .NET Reply
  • justly - Monday, October 18, 2004 - link

    22 There was a thread here that talked about the infoword article, I suggest you at least lokk at it before you claim there are no holes in its conclusion.

    Like any other thread it does drift of topic at times but there are a lot of conclusions made by the author of the article (rck01) that he either could not or would not elaborate on. Personally I wouldnt trust the results of that article untill some of the questions asked in that thread get answered.
  • Chuckles - Monday, October 18, 2004 - link

    No, lets hope that AMD responds by getting a compiler team and optimizing the binary daylights out of the various compilers in addition to boosting the clock. That way everybody wins.
  • dollar - Monday, October 18, 2004 - link

    - The Xeons and the Opterons have the same 1MB L2 cache, cached up Xeons? Huh?
    - There are no Windows Server 2003 64-bit edition but the betas, and people looking for servers most likely aren't using betas. Also there is little or no real software availible. Plus, the Xeons are also 64-bit capable (so that would't put the Opterons at any real advantage anyways.
    - The fact that software is optimized for Xeons turns the tide in their favour, but it's nothing wrong with that, the costumer still gets more performance. Unfortunatly for AMD there isn't likely to be any widespread Opteron optimization with a 5% markedshare. That's what it's like to be the little guy :(

    Xeon's came out victorious (for once), let's hope AMD responds with faster CPUs ;)
  • sprockkets - Monday, October 18, 2004 - link

    I guess my only question is what type of Xeon was used, the ones with huge cache, or what?

    I liked that Infoworld report, in a way. It's weird that Opterons are faster, but load up a Xeon with work and it is faster. Kinda makes sense, but if you are faster when under load, wouldn't you run faster without load? Does that mean Xeons waste most of the time without other programs to take advantage then of Hyper Threading?

    Then again, with a shared bus architecture it's been proven here until the Xenon went up to a 800mhz bus that Opterons scale much better.
  • Guspaz - Monday, October 18, 2004 - link

    Isn't it kind of an unfair test to compare a 64-bit processor in 32 bit mode to a 32 bit processor?

    If you're going to benchmark without taking advantage of one of the Opteron's biggest features (AMD64), why not disable something like Hyper-Threading to compensate? From what I understand both AMD64 and HyperThreading provide similar performance increases of something like 5 to 15 percent.
  • WooDaddy - Monday, October 18, 2004 - link

    I understand for the purpose of the review, it might be easier to order from the same vendor, but since the architecture of each one is different (AMD/Intel), most companies wouldn't sell conflicting yet equivalent servers. The server market caters less to fanboys/men/women than the fickle consumer market.

    My point is that if you are going to compare full blown pre-assembled systems, you should look at competing vendors since it isn't cost effective for the vendor to release self-competing products. But since you probably built your own (the test configuration info was rather sparce), make sure the component cost is the same. That's the comparision that would count.
  • Jason Clark - Monday, October 18, 2004 - link

    I plan on adding a cost comparison in our next article in this series. The trick is to make it as fair as possible where each system is outfitted in a similar fashion from the same vendor if possible.

  • Questar - Monday, October 18, 2004 - link

    Oh yeah, that's a really good idea. I should base business buying decisions based upon a review at a gaming site. There's a source I would quote in my research. Reply
  • mrdudesir - Monday, October 18, 2004 - link

    That review at info world was a joke. No Data, just assertions that they claim, would they care to back it up with evidence. If you want to see a real review check out this one over at GamePC that i found, which actually outlines all of the hardware and apps used.
  • Questar - Monday, October 18, 2004 - link

    RTFA, the numbers are all there. Now who's the joke?
  • Phiro - Monday, October 18, 2004 - link

    Good article - we currently exclusively use clustered dual-P4 cpu boxes w/hyperthreading enabled & Windows 2003 for our web clusters, and the .net side of it gets larger every day, so this quick review was right on the money. The one thing I would have added was a quick cost comparison for the like servers.

    People, you may all beg and cry for things like Linux testing, Windows 64 testing, etc. etc. but given the simple constraints on this article - basic web server comparison using hardware & OS's and software that's actually in production at most Fortune 500 companies - that's useful to some of us. I'm sorry they didn't benchmark this with Raptors, 42 sticks of ram and the latest beta nvidia drivers, but this wasn't a "how high can we max out web server performance" - they write those on odd-numbered days :)
  • PrinceXizor - Monday, October 18, 2004 - link

    That infoworld "review" was a joke. No benchmarking numbers, just the reviewers own subjective opinions. There may be some grain of truth in the multi-tasking vs. non multi-tasking strengths of the Xeons. But, its impossible to say from that "review". There was virtually no useful information for evaluating the platforms. Its no wonder that most useful reviews are from on-line hardware sites like AT, [H], TechReport, THG, etc.

  • WooDaddy - Monday, October 18, 2004 - link

    BIG problem with this review. HOW MUCH DO THEY COST!?!

    No self-respecting company would purchase a server without performing a cost/performance ratio.

    My assumption is that the Opteron system is less expensive.. that being said, then the review is moot. Equally priced systems should be used. My next assumption is that then the new Opteron system would spank the Intel...

    But unfortunately, I'm an AMD fanman.
  • Questar - Monday, October 18, 2004 - link

    That should say that testing of Opteron vs Xeon with workstation class loads has already been done by others Reply
  • Questar - Monday, October 18, 2004 - link

    Testing of Opteron vs Xeon has already been done by others:

    To quote:
    "What we found was eye-opening. The Opteron machine outperformed the Xeons when lightly loaded with minimal multitasking, but once the real work started, the Opteron stopped. It was effectively shut down by the same multitasking load that the two Xeons performed with ease. In the clean environment, it still performed at less than half the speed of the older and allegedly less-capable Xeons."
  • allnighter - Monday, October 18, 2004 - link

    I feel sorry for all my fellow AMD fans for getting so defensive over one test result. Especially when clearly stated that the application uses optimized code for Intel processors. What's the big deal? Anyone surprised? Reply
  • Jeff7181 - Monday, October 18, 2004 - link

    #19... since you obviously didn't read the other posts or the article and just looked at the graphs... the fact that the Intel solution was faster than the AMD solution in .NET is more likely due to the fact that .NET has been optimized for the P4. Reply
  • MightyB - Monday, October 18, 2004 - link

    I think it is nice to see Intel finally beat a opteron .. they only had to make a 3.6Ghz and beef up the cache before they could match it :-).. The only thing this review lacks like all others is to mention the prize difference.. how much more do u pay to get those 8% in .NET....??

    Best regards
  • Rohde - Monday, October 18, 2004 - link

    #10 - Since they only used a single pair of memory sticks, Numa would not have made a difference.

    If instead they attached 1GB of memory to each processor, we probably would have seen better performance in all benchmarks since one CPU would not be taking a memory latency hit with each access.
  • Jason Clark - Monday, October 18, 2004 - link

    To all those looking for windows 64 bit numbers, we've actually already been testing. Lets just say that the builds we had were a bit too early for benchmarking with. We are continually monitoring the 64 builds, as soon as we have something we can work with we'll do an article.
  • Jason Clark - Monday, October 18, 2004 - link

    #15, we're looking at doing workstation, just takes time to come up with real meaningful tests.

  • Regs - Monday, October 18, 2004 - link

    All these dual cores on Web Based Applications! Why not have a workstation section? Reply
  • Jason Clark - Monday, October 18, 2004 - link

    #7, since the I/O usage was barely 2% throughout the tests, why would you want a different drive? I/O should have no impact on most web applications unless in special cases the app is designed to use I/O for a purpose. Most any web application server out there is going to cache heavily. Anandtech has used IDE drives in our web servers for years, no issues and would perform no different than a Ultra 320 scsi drive.

  • compudog - Monday, October 18, 2004 - link

    Great work Jason. All you fanboys should READ the article. The big difference on the .Net platform is because of CPU optimizations, not as a result of CPU deficiencies. When/If MS writes optimized code for .NET on K8 the tests would likely be within the 2.5% deviation.

  • ajuez - Monday, October 18, 2004 - link

    Can you use the Windows 2003 Server 64 bit Edition on both plataforms?

    It could be interesting for future performance!

    Thanks and sorry about my english
  • mikidutzaa - Monday, October 18, 2004 - link

    Great article. I would LOVE to see the same benchmarks in Linux 32bit AND 64bit!

    If possible, maybe include some lower priced processors (say a 246 & 3.2).
  • Fluff - Monday, October 18, 2004 - link

    Hmm this version of Server 2003 is not NUMA aware. How would this affect the results? Reply
  • Tides - Monday, October 18, 2004 - link

    ah yes, another article that shows very little yet spreads a lot of opinion.why not just say, "we ran 3 programs, opteron won 2 of the 3 tests, but as you can see by our non biased views, the intel system owns the amd system." Reply
  • gimpsoft - Monday, October 18, 2004 - link

  • Beenthere - Monday, October 18, 2004 - link

    Why would you use a 40 GB 7200RPM 8MB Cache IDE Drive for a performance server??? Wouldn't you use a faster/larger drive or dual drives??? Reply
  • tyski34 - Monday, October 18, 2004 - link


    "The difference between the Opteron and Xeon here was approximately 3%, which isn't far off our deviation of 2.5%."

    = a draw statistically
  • gherald - Monday, October 18, 2004 - link

    Why yes #4, it is clear that the Opterons bested the Xeons in the ColdFusion and PHP tests by a slim margin. But tech writers call such things draws, since such small percentage points in performance are fairly negligeable. Reply
  • Boonesmi - Monday, October 18, 2004 - link

    "The results throughout much of these tests were a draw, right up until the Microsoft .NET tests"

    huh? the opteron was fastest in every benchmark except the .NET tests.... a draw would have been if each platform has won some and lost some.
  • bozilla - Monday, October 18, 2004 - link

    If someone would read this from anandtech and do a test between these 2 configuration for content creation and test these computers as workstations, with the design/video/3d applications. What I'm asking for I guess is comparison between the best AMD has to offer against the latest Intel offering. I think this is only fair, since as we all know these workstation can cost as low as $4k (if self-built) as oppose to single CPU machines from Falcon Northwest or Alienware that cost pretty much the same. I think that many people like me who are in creative profession would like to see who is the performance king in dual system for this field. Maybe you should definitely include gaming tests and compare these dual machines with single CPU machines (FX53, P4EE, P4 560)

  • Ardan - Monday, October 18, 2004 - link

    LOL thats a good summary :) Reply
  • Denial - Monday, October 18, 2004 - link

    To save everyone the 2 minutes it takes to read this...

    For the 32 bit apps which were tested, the difference is negligible.

    Move along now.

Log in

Don't have an account? Sign up now