Comments Locked

97 Comments

Back to Article

  • Visual - Thursday, July 7, 2005 - link

    the intel board that you used, you listed it as SE7620AF2. there is no such thing though, so is it a typoed SE7520AF2 or a yet unreleased board?
  • kaka - Saturday, February 19, 2005 - link

    ??,OPteron is better than xeon!!
  • Fluff - Thursday, February 17, 2005 - link

    But in future it would be handy to touch upon extra features such as differences in remote management, what happens if a cpu fails, if memory fails is there hotswop. As these probably affect a decision as well as performance.

    I believe that people benefit from the sort of technical analysis and simulated real world that Anandtech does but in addition the other factors such as up-time and manangement would be nice to know.

    If a cpu fan / stick of memory fails on a database at the weekend and no one is there to hear the alarm what do the various platforms do?

    If a cpu fails on a dual opteron does that mean it loses all the data attached to that cpu? Does the same happen on a xeon? Will a Xeon keep going with just one - chipkill?

    I'm not sure if this is outside the scope of Anandtech.
  • Jason Clark - Thursday, February 17, 2005 - link

    Hans, you are correct in that they wouldn't be using non supported memory. But, since the board was pre-production and at the time of testing there were no "recommended' memory modules, we had to go with what we had. Word is our issues were bios related and a new bios should address it.

    Cheers
  • Jason Clark - Thursday, February 17, 2005 - link

    Hans, fair enough on the next article we'll include it for those curious.
  • Jason Clark - Thursday, February 17, 2005 - link

    Viditor, we tested with 8GB of memory using PAE and AWE support in SQL. When 64bit versions of sql and windows 2003 are ready we'll be all over it.
  • Viditor - Thursday, February 17, 2005 - link

    BTW, for some Linux spec results, check these out...

    http://www.pathscale.com/pr_021505.html

    Sun Fire V20z server (2xAMD Opteron processor Model 252, SLES9) with PathScale EKOPath Compiler Suite: SPECfp2000 -- 2036, SPECint_rate2000 -- 40.4, SPECfp_rate2000 -- 46.5.

    The Sun Fire V40z server with PathScale EKOPath Compiler Suite (4xAMD Opteron processor Model 852, SLES9): SPECint_rate2000 76.7, SPECfp_rate2000 -- 87.1.

    The Sun Fire V20z server (2xAMD Opteron processor Model 250, SLES8): SPECfp_rate2000 37.2.

    IBM eServer OpenPower 710 (2x1.65 GHz Power5, Linux): SPECfp_rate -- 40.2.

    IBM eServer p5 510 (2x1.65 GHz Power5, AIX): SPECint_rate2000 -- 33, SPECfp_rate2000 -- 43.2
  • Viditor - Thursday, February 17, 2005 - link

    Jason...

    I see you are retesting the HT, but I haven't seen a comment from you about testing 64bit with large memory (>4GB). Is this something you just aren't prepared to do right now?

    Cheers...
  • Viditor - Thursday, February 17, 2005 - link

    "I read viditor comment that said as single"

    Yup...very sorry prd00...my bad!

    "Which is why we aren't going to provide information like that, as it isn't relevant to the target audience or the purpose of the article"

    Fair call Jason, but as this is a beta bios, it might be an important data point...

    sleepless - "Looking at the configuration you show Opteron 250 with a 252. Did you have a problem getting another 252 Opteron for the test?"

    They built 2 test platforms, 1 with dual 250s and 1 with dual 252s...or so I assume (after my last mistake I take nothing for granted)...:-)
  • sleepless1 - Wednesday, February 16, 2005 - link

    Looking at the configuration you show Opteron 250 with a 252. Did you have a problem getting another 252 Opteron for the test?
  • Hans Maulwurf - Wednesday, February 16, 2005 - link

    Yes, but IBM would not use memory that is not on the recommanded list of the mainboard, at lest I hope so.
    And it is possible that the boad sets very high latencies for the memory you used. So I think it is an important information especially when using memory that is not recommanded.
  • Jason Clark - Wednesday, February 16, 2005 - link

    Hans, let me ask you this. When someone in an IT dept. calls Compaq, Dell, HP or IBM for a server do you think they ask them what the memory timings are set at? The answer is no. Which is why we aren't going to provide information like that, as it isn't relevant to the target audience or the purpose of the article. We're trying to educate the IT folks on what platform does what on certain workloads and IT related tests.

    Cheers.
  • prd00 - Wednesday, February 16, 2005 - link

  • Hans Maulwurf - Wednesday, February 16, 2005 - link

    Jason,

    you do not have to play with the memory timings to report them.
  • dm - Tuesday, February 15, 2005 - link

    danidentity, i guess you're right when you mentioned about 5pages of reply ;)...
  • prd00 - Tuesday, February 15, 2005 - link

    Sorry, missed your comment Jason.. I read viditor comment that said as single. So, in Dual setup, Xeon is more powerful now ;). Then, Xeon must be faster in single.
    I am waiting for 64 bit one ;)
  • prd00 - Tuesday, February 15, 2005 - link

    Wow.. single??
    On single setup, I already knew that Xeon is powerful. Right now what we are lacking is a TRUE SERVER BENCHMARK. Not just single vs single. I can safely recommend Xeon since a few months ago on single setup, but right now, most of our customers are asking about DUAL SETUP. Some are looking in QUAD setup. Single is useless in server environment. For databse server, 9 out of 10 are looking for 2p setup
    So, what I am really looking are database benchmark on single, dual and quad setup, and also how does it scale. Which platform best suited for 2p and 4p, and which one has better upgrade future (i.e. by adding processors), and until what point.

    So, like, Xeon is good for 1p, but on 2p Opteron is better, while more than 8p we can consider Itanium instead for database server.

    Kind of conclusion like that.
  • Jason Clark - Tuesday, February 15, 2005 - link

    Zebo, because this is a server test. You don't play with memory timings/overclocking in servers. We used default memory timings that the Tyan board set for the memory. I linked to the manufacturer specs on the memory which identifies its SPD rating. The only thing we're investigating at this point is the 1GHz HT issue in the bios.
  • PrinceGaz - Tuesday, February 15, 2005 - link

    It's certainly a change from the usual Opteron beating Xeon in almost all server tests reviews, and all the more so because you say they were both dual CPU systems (I was under the impression while reading they were only single CPU servers being compared).

    It just goes to show how much difference the benchmarks that are run, how well the systems are set up, and any other things we never know about, can influence results.

    I'm glad Intel is coming out ahead in some tests on AT, maybe you should make them come out ahead on desktop stuff too as that might encourage AMD to drop the prices on the higher rated E0 revision Athlon 64 processors sooner rather than later :)
  • Zebo - Tuesday, February 15, 2005 - link

    Jason how comw you did'nt say mem timings nor speed or if 1T or not? I've never seen a review from AT without this.
  • Carfax - Tuesday, February 15, 2005 - link

    Sheesh, the workstation benches still aren't up? :(

    More people are interested in the workstation benchmarks than database I'd wager because it's a better showcase for the new enhancements.

    How long will we have to wait?
  • Jason Clark - Tuesday, February 15, 2005 - link

    snorre, proper? It is proper in terms of the Windows world since 64 bit DOES NOT EXIST :). If you want to see 64bit linux coverage as said in these comments and in the article view the linux section or Johans work in the IT section.

  • snorre - Tuesday, February 15, 2005 - link

    I'd like to see a proper Xeon DP 2M vs Opteron 252 review, since MS SQL 32-bit benchmarks are only of limited interest. When will we see this?

    Are there any proper Opteron 252 reviews out there?
  • semo - Tuesday, February 15, 2005 - link

    #70, you said it. it's the cost. cost is my killer.

    sure ddr2 costs more than ddr but i hate upgrading my whole setup just to get new momory. right now i'm running a pc133 setup and cannot upgrade even if i wanted to (and believe me... i want to). i know that low latency is what the hammer architecture wants but doesn't regitered memory increase latencies... and what is registered memory anyway?
  • Jason Clark - Tuesday, February 15, 2005 - link

    There was a few questions about single or dual in here, I had answered that but to clarify all testing was DUAL processor.
  • Jason Clark - Tuesday, February 15, 2005 - link

    One thing to remember with the Tyan bios is it is pre-production. We'll post info as soon as we have it.
  • Jason Clark - Tuesday, February 15, 2005 - link

    We're working with Tyan on the 1GHz HT issue, if we get a new bios that supports it we will re-test and post our results..

    Cheers.
  • Viditor - Tuesday, February 15, 2005 - link

    "i'm interested in number cruncing and games and rendering, i.e. a workstation not a server"

    Why would you not want registered memory then? Contrary to popular opinion, it does not affect the speed...only the cost.
    For gaming, dual systems are no help at all (unless you're running a game server) with todays software. For professional rendering, you absolutely WANT registered memory!
    DDR2 would actually be no speed increase at all for AMD64 systems, and none yet for Intel systems. Not until the memory speeds get much higher will we see any benefit from DDR2...
    XDR is also not a good match for the AMD chips because of the high latency. AMD chips are NOT bandwidth constrained but ARE latency sensitive (meaning that increasing memory speeds does very little, while increasing latency makes them much worse).

    The only real issue of registered memory is the cost, and if that is the problem I would suggest a high end A64 939 SLI board (e.g. Asus A8N-SLI), and upgrade to dual core in September or so...
  • semo - Tuesday, February 15, 2005 - link

    i'm interested in number cruncing and games and rendering, i.e. a workstation not a server. unforutnately the integrated memory controller of the amd hammers are both their strengths and weaknesses.

    it's only upto amd whether we can have unregistered, ddr2 or maybe even xdr memory i guess
  • Viditor - Tuesday, February 15, 2005 - link

    "is it possible to have a dual proc setup without using registered memory?"

    Technically yes...but registered memory is what's preferred for servers because it is more securely accurate. All Opterons use registered memory...
    Platforms for the Athlon MP use non-registered memory, and a very few of the Xeon platforms do as well...
  • semo - Tuesday, February 15, 2005 - link

    is it possible to have a dual proc setup without using registered memory?
  • Proton - Tuesday, February 15, 2005 - link

    "We did a revamp of the tool itself, which is more performant on high volume queries."

    Performant?
    Please read this article...
    http://msdn.microsoft.com/msdnmag/issues/05/03/Edi...

    "More recently, we've seen the word "performant" start its crawl into the everyday vocabulary of devspace. It is used to mean "highly performing." It's also not a word. When something provides information, it's informative. It's not "informant." The word "performant," if it existed, would be a noun—not an adjective. But it doesn't exist, so if you do see it in print, remember that it's not really there.'
  • ceefka - Tuesday, February 15, 2005 - link

    #15 Jason, let me rephrase that#10: "However compact"... That would do it more justice ;-)

    I didn't thank you for the effort you and Ross put into this, did I? Your article came out together with the announcements of AMD. Hot stuff! How much time/sleep did you really have?
  • Viditor - Tuesday, February 15, 2005 - link

    "What memory timings?"

    Good question...

    "is it dual vs Dual or single vs single"

    single vs single, 32bit
  • prd00 - Tuesday, February 15, 2005 - link

    Wait... I think I miss something here.. is it dual vs Dual or single vs single?
  • Zebo - Tuesday, February 15, 2005 - link

    What memory timings?
  • Viditor - Tuesday, February 15, 2005 - link

    "I don't know if it fixes the IOMMU issue or not"

    As far as we know, it doesn't. The Smithfield is a desktop part, so that is to be expected...large quantities of memory aren't yet necessary for the desktop.

    "Now this is interesting. Somewhere were Intel comes out on top by a big margin"

    (grin) Only the most diehard AMD fan would deny Xeon's capabilities...
    For a 1 or 2 CPU server that is used for low-end database serving or webserving, the new Xeon is excellent in 32bit (the CPU of choice)!
    As the next few months grind ahead, we will see quite a few scenarios on review sites. My own suppositions are that

    1. In a 1 or 2 single core Opteron system there is almost no bandwidth constraint. This is evidenced by the lack of change with the 25% HT increase to 1GHz. That said, we might see significant changes in 4 and 8 way systems, especially as dual cores come on-line.
    2. We still have no reviews of these two platforms in 64bit using >4GB of ram. I suspect that Opteron will be much more effective there...
    3. When Intel releases their mp Xeon Nocona, I suspect that 4 and 8 way Opteron systems will blow their doors off...my rationale is that the 1GHz HT links and AMD's MOESI cache protocol gives them a huge advantage in scaling processors.
  • Staples - Tuesday, February 15, 2005 - link

    Now this is interesting. Somewhere were Intel comes out on top by a big margin.
  • fitten - Monday, February 14, 2005 - link

    BTW... there is a new chipset (or some new chipsets) being released soon along with the Smithdale CPU. I don't know if it fixes the IOMMU issue or not, but it might be worth a look...
  • Viditor - Monday, February 14, 2005 - link

    "no mention in any of the access scenarios is described as 32bit..."

    Oops...yes it does.

    "Some devices, such as a large majority of PCI cards cannot directly access memory above the 4GB point"
  • Viditor - Monday, February 14, 2005 - link

    "DMA operations initiated by a peripheral device that does not directly support 64-bit addressing will have performance issues"

    I'm not sure you are correct in this...I believe the issue is

    "physical addresses above 4GB (32 bits) cannot reliably be the source or destination of DMA operations"

    I found another article that explains my concern quite well...
    http://www.spodesabode.com/content/article/nocona/...

    "Unlike the Itanium, which is solely a 64-Bit processor, these chips have the ability to run in both 32-Bit and 64-Bit mode. Some devices, such as a large majority of PCI cards cannot directly access memory above the 4GB point. To solve this, the software has to ensure the physical memory address is below the 4GB point. AMD solved this solution by using a hardware IOMMU, which is effectively a "bounce buffer" or look-up table of physically memory addresses corresponding to a virtual address that is given to the incompatible hardware, allowing it to use memory above the 4GB barrier.
    Intels solution isn't quite as elegant. If a device needs to access memory above the 4GB point, the data is just copied from wherever it is, to a fixed location below the 4GB point. This takes time and can reduce performance. In extreme cases we have heard there could be as much as 30-50% decrease in performance on the Nocona platform"

    This does not appear to be a 64bit driver issue to me as no mention in any of the access scenarios is described as 32bit...
  • Accord99 - Monday, February 14, 2005 - link

    It's an Intel thing I think, for why they don't have an IOMMU. Even their chipsets for the Itanium 2 don't have one while HP and SGI's chipsets do. Or perhaps Intel just wants (and has the power to force) peripheral manufacturer's to make proper 64-bit devices and drivers.
  • Viditor - Monday, February 14, 2005 - link

    OIC what you are saying...and yes, it's a problem with the chipset. Of course that is exactly what I said in the first place...

    "Because there is still no hardware IOMMU on Xeon chipsets"

    The big question is, why hasn't Intel fixed this?
    I can only assume that it is a design problem for them that is inherent to EM64T...
    I can't imagine that they would just let this slide on their chipset development.
    What that problem is, I have no idea...I would just like to see what effect it has on system function.
  • Accord99 - Monday, February 14, 2005 - link

    The linuxhardware article supports what I'm saying, DMA operations initiated by a peripheral device that does not directly support 64-bit addressing will have performance issues. Server-level peripherals typically support 64-bit addressing and it is not a problem with the CPU, or the EMT64 instruction set, it is a problem with the chipset. It does not affect the Xeon's ability to addres flatly >4GB of memory.
  • Viditor - Monday, February 14, 2005 - link

    I don't believe I do...
    I have read that post before, and I don't see your point.

    Try reading this article to understand what I'm saying:
    http://www.linuxhardware.org/article.pl?sid=04/10/...

    “Software IOTLB — Intel EM64T does not support an IOMMU in hardware while AMD64 processors do. This means that physical addresses above 4GB (32 bits) cannot reliably be the source or destination of DMA operations. Therefore, the Red Hat Enterprise Linux 3 Update 2 kernel "bounces" all DMA operations to or from physical addresses above 4GB to buffers that the kernel pre-allocated below 4GB at boot time. This is likely to result in lower performance for IO-intensive workloads for Intel EM64T as compared to AMD64 processors.”
    Although this shouldn't affect people that run with under 4GB of memory, this is an important point to note. If you do ever need the extra memory, you may take a performance hit. Unfortunately, we do not have over 4GB of DDR2 memory here today so we will not be able to test how much of a hit you would take if any"

    The bottom line is that many believe (including myself) the physical addressing will be a significant problem, and many (including you) don't.
    That's why I have requested that AT do an actual test...nothing like reality to settle a discussion...:-)

    BTW, thanks for correcting my typo...
  • Dubb - Monday, February 14, 2005 - link

    /taps fingers impatiently waiting on rendering benchmarks...

    which hopefully include (hint hint)

    mental ray
    brazil
    renderman
  • Accord99 - Monday, February 14, 2005 - link

    Your understanding of the IOMMU is wrong. Please refer to this thread:

    http://realworldtech.com/forums/index.cfm?action=d...

    Also, the Xeon supports 36-bits.
  • Viditor - Monday, February 14, 2005 - link

    Accord99 - "The IOMMU is only used for peripherals that don't support 64-bit addressing"

    The IOMMU is a memory mapping unit sitting between the I/O bus and physical memory. While the memory controller of the Xeon can address 64bit, it uses PAE to do so because current chipsets only address 32 bits. The on-die memory controller for AMD64 chips address 40 bits...
  • Accord99 - Monday, February 14, 2005 - link

    The hardware IOMMU has no impact on the Xeon's ability to flat address >4GB of memory. The IOMMU is only used for peripherals that don't support 64-bit addressing, ie USB 2.0 cards, EIDE controllers, soundcards, some network controllers and will reduce IO performance for these devices. High-end 64-bit SCSI controllers, gigabit network controllers and newer SATA controllers all support 64-bit addressing and run at full performance.
  • Viditor - Monday, February 14, 2005 - link

    One other request (if it's possible)...
    Just so we can get a well-rounded view on the results, is it possible for you to do a Solaris/Oracle and Linux/MySQL (or Linux/Postgres) test?
    I realise that I'm asking a lot, but if you have the time...:-)
  • Zan Lynx - Monday, February 14, 2005 - link

    I see Viditor explained what he really wanted. That was my first comment and by the time I'd filled out all the forms and received the email with my password he had already explained. Sorry. Please ignore me.
  • Zan Lynx - Monday, February 14, 2005 - link

    Viditor, the test hardware used 8GB RAM for both the Xeon and Opteron systems according to page 2.
  • Viditor - Monday, February 14, 2005 - link

    Jason - Let me expand on my request...

    Because there is still no hardware IOMMU on Xeon chipsets, I believe they must use PAE for 64bit addressing over 4GB, however Opteron doesn't have this problem and can address directly up to 128GB.
    I would very much like to see the results of a comparison on the same testbed you used for this article (8GB Ram) to compare and see how much this effects performance as this seems a very typical model to me.

    Cheers!
  • Viditor - Monday, February 14, 2005 - link

    Jason - Very well done test and article!

    I too would be very interested in a 64bit Linux (or even Windows Beta) test with that configuration...
    One of the things I am anxious to see is Xeons reaction to >4GB of ram on its performance. There are still NO results (that I have seen) with that configuration.

    Cheers, and thanks for the article.
  • sri2000 - Monday, February 14, 2005 - link

    Someone mentioned adding other database functions to provide different kind of stresses. How about using SQL Server Data Transfromation Services (DTS) to perform a variety of mass imports/exports from the test database?

    You could also perform some Full-Text searches mixed in with the regular queries on appropriately indexed tables - though those are really disk intensive rather than CPU-intensive (though the CPU usage does spike significantly when these queries are run).

    I also wonder if adding queries which hit Views in addition to regular tables would affect anything, the result being that you're essentially running nested queries (though this doesn't likely reflect the type of usage seen in your forums, which was the basis of this test).

    By the same token, having queries that use wildcards, user functions, sub-queries, etc (rather than just simple selects & inserts) will also add complexity to the searches & might affect the results.

  • Marlin1975 - Monday, February 14, 2005 - link

    Like someone else pointed out, when will you do some test to see what the SSE3 did for AMD.

    Also what were the temps on both of the NEW Cpus. Haveing hundreds of them in a server room can cost a arm and a leg to keep cool, so I think temps do matter here.
  • fitten - Monday, February 14, 2005 - link

    #39, we don't need to point out that 64-bit Intel P4 Xeons have been out and available for a while even though WindowsXP64 isn't available yet. You can run the RC WindowsXP64 on those and on Opterons/Athlon64s.
  • rgb - Monday, February 14, 2005 - link

    I don't think the BIOS of the test machine was adapted to Revision E Opterons.

    I adapted LinuxBIOS to the Rev E stepping last week and the 1 GHz support is really the easiest thing (was already present in revision D processors). Changing the HT speed while the operating system is running is _very_ difficult. It requires a reset or LDTSTOP on both CPUs for the new frequency to be effective, so this is normally done a boot time in the BIOS. I guess ntune does not really change the HT frequency.

    In addition Revision E has a number of errata fixed which result in improved performance (for example Errata 94).

    The most important point is the new memory controller mode that reduces the DRAM bank conflicts. It improves STREAM benchmarks scores around 30%. This modes has to be automatically enabled by the BIOS, so please rerun the benchmark on a mainboard that supports Rev E processors.

  • Quanticles - Monday, February 14, 2005 - link

    I'd really want to see tests run on Linux, even if it is 32-bit. There are too many Windows programs that are tailored to Intel processors.

    I dont need to point out that Microsoft is delaying the 64 bit version of Windows until Intel has their 64 bit processor come out. If they're going to delay like that then I wonder how well the Opteron will preform on it.
  • Phiro - Monday, February 14, 2005 - link

    Jason: Ignore all the 64-bit idiots. Please keep supplying 32-bit sql benchmarks for a LONG time - in the real world 99.5% of production dbs are running on 32-bit sql servers and that number will remain quite high for a long, long time no matter how fast 64-bit takes off.
  • Jason Clark - Monday, February 14, 2005 - link

    bthomas, read page 1 please. We focus on the window side of the house and there is no released 64bit OS or SQL server yet.

    Quanticles, the only measure we has was ntune which reported the HT bus running at 1GHz. Dual configuration for all tests.

  • Quanticles - Monday, February 14, 2005 - link

    Did you check to make sure the HT bus was actually running at 1 GHz with an o-scope?

    Where you running these systems as 1P or 2P? I got the impression that you were running the tests as 1P systems and then was making recommendations on 2P systems.
  • bthomas - Monday, February 14, 2005 - link

    Geez. Nobody is mentioning the fact that the Opteron is running on a 32-bit OS in these tests.

    Yeah, its basically a wash under these conditions, but so what..the real test would be under 64 bit. DB applications/servers are supposed to really thrive in the 64-bit realm. Why didnt you test under a 64 bit OS/DB software like Linux/Postgres|MySQL/etc ?!?

    =b.t.






















  • rivieracadman - Monday, February 14, 2005 - link

    I forgot to ask; Does the 152 offer SSOI or is it still SOI. From the power ratings I can guess it's still SOI. Just curious ...
  • chucky2 - Monday, February 14, 2005 - link

    I like how vendors cripple the AMD offerings...sometimes ever so slightly, other times largely. Take a look at the two HP offerings listed out at the end of the article and tell me which one you'd like to buy? For $900 extra, I'll give up whatever performance benefit I'd see for the managability any day.

    Not AMD's fault...it's the vendors... :(

    Chuck
  • Fluff - Monday, February 14, 2005 - link

    Was NUMA enabled on 2003 Enterprise Edition for the 252?

    Did it make any difference?

    This was not made clear in the article.

    Unless /PAE is the equivalent.
  • mlittl3 - Monday, February 14, 2005 - link

    For those of you who are interested in what opterons will be made using 90 nm and 1 GHz hypertransport, here is the link on amd's website.

    http://www2.amd.com/us-en/OPN_Printer/1,,,00.html?...

    Sorry it is so long but there is a lot of scripting for filtering results on the page.

    To summarize, Opterons 242 (1.6 GHz) to 852 (2.6 GHz) are being updated to the new die process and HT bus.

    I would like to recommend to the author of the article to include a reference section at the end of every review to relevant websites for more information. This would be similar to the reference section in the article from Johan. The above link should go there as well as any links to more indepth architecture info on both AMD's and Intel's websites. Just a thought.
  • skiboysteve - Monday, February 14, 2005 - link

    that extra period at the end of post #28 made what would have been a normal statement entirely creepy as hell...
  • snorre - Monday, February 14, 2005 - link

    It would be more interesting with an update to these articles:
    http://anandtech.com/IT/showdoc.aspx?i=1982
    http://www.anandtech.com/IT/showdoc.html?i=1935

    "The true test that remains, however, is a test comparing AMD’s Opteron to Intel’s Itanium 2. Intel was not very receptive to the idea of doing a head-to-head; not out of a fear of losing, but out of a desire not to lend AMD any credibility by showing that the Opteron is indeed a competitor to the Itanium 2. While we do believe that the Itanium 2 in its 128-way configurations is definitely out of the Opteron’s league, in the 2-way and 4-way configurations that we are interested in comparing, the two are absolutely competitors.

    Whether Intel is looking to supply us with an Itanium 2 system or not, we will make that comparison."

    We're still waiting...
  • SpaceRanger - Monday, February 14, 2005 - link

    I'd love to see it Jason..
  • Jason Clark - Monday, February 14, 2005 - link

    An article we are contemplating is desktop parts in a SQL test, and web. Lots of folks in smaller orgranizations and even medium to some extent build their own boxes.

    Interesting?
  • Regs - Monday, February 14, 2005 - link

    Thanks for Clarifying me #24. For some odd reason I'm thinking about the differences between the branch predicator of a A64 and Intel and I got in over my head.

    But you are right about the cache, spatial and temporal locality.
  • rivieracadman - Monday, February 14, 2005 - link

    I would suspect that the raw speed of the Xeon coupled with the larger cash to reduce latency would make the Xeon perform well in any benchmark that was both threaded and delt with small data sets, such as reads, queries, and searches. On the other hand, the Opteron due to its lower memory access overhead, and shear bandwidth, would do better in areas with large data sets such as data transfers, data recovery, and large complex calculations. If this is correct, which you have pretty much confirmed, then I would suspect that the Opteron would do better in the web server tests as long as the pages served were larger then say 15K. Not that this is any magical number, but the Xeon would have to pull from memory more at this point.

    As for the HT bus. I wouldn't think you would use the entire 1Ghz bus on a database benchmark. You really need to perform some workstation benchmarks to fill the bus.

    Since everyone else here is adding to the wish list. I would like to see a real world combined query, read, change, write benchmark. I think the Xeon does better when searching and reading because of its shear speed, but the Opteron would do better when a record is altered and resubmitted to a database. This is more of a real world example in my opinion, and since both are architectually diffrent, it would allow for both CPUs to show their true colors in what would be considered every tasks.
  • blckgrffn - Monday, February 14, 2005 - link

    Having repetitive data is what having cache is all about, the long pipelined architecture of the P4 needs the large local cache to minimize time-expensive ram lookups to compensate for the time-expensive deep pipe operations that get tossed when mis-predicted. So, the 2meg cache could help the prescott in many places and is not limited only to SQL. I think that we can probably look at the the EE P4's and get a feeling for what the new prescotts will bring to the table, but we can hope that all of those additions that were made to the Prescott core are allowed to shine with more cache present.
  • fitten - Monday, February 14, 2005 - link

    #9, this was a server benchmark test. Servers are about stability and such. Anyone who overclocks a critical server (database, etc.) should be fired on the spot.

    They may do overclocking tests in the workstation review that was mentioned.
  • Ross Whitehead - Monday, February 14, 2005 - link

    #20 - I agree the AMDs instructions/clock count is high, but we were surprised that the 25% increase in HT did not provide any measurable difference.
  • Regs - Monday, February 14, 2005 - link

    *Their IPC counts are higher*

    Need more coffee
  • Regs - Monday, February 14, 2005 - link

    #11 - I doubt there will be a performance gain for games with just added cache. The problem with the prescott is it's low IPC core and leakage. Anyways, Apps on the desk top use a lot of repeatedly used data arrays with similar instruction sets. So why would the CPU core benefit a larger L2 cache for games when it's just going to be the similar type of code it just processed?

    #16 - AMD's are not bandwidth starved. Their high instructions per clock count are higher. So the pipeline is a lot shorter which means it does not run a risk of pipeline stalls if it was not fed enough data from the bus unlike the Intel.
  • Jason Clark - Monday, February 14, 2005 - link

    mickyb,
    Quad 3.6 Xeon systems don't exist as far as I know, correct me if I'm wrong. Quad Xeon systems are still the 400MHz FSB Xeons that are clocked at most 3GHz.
  • mickyb - Monday, February 14, 2005 - link

    The Intel XEON has always been competitive. You guys are thinking about gaming. I would like to see 4 way perforamnce and see a graph on benchmarks compared to number of CPUs. AMD has previously done well in this area.
  • bob661 - Monday, February 14, 2005 - link

    #14
    The difference is the 2xx can go up to 2 CPU's and the 8xx can go up to 8 CPU's. That's it.
  • Ross Whitehead - Monday, February 14, 2005 - link

    R3MF, we plan to discuss w/ AMD and Tyan the lack of benefit the 1 GHz HyperTransport provided.
  • Jason Clark - Monday, February 14, 2005 - link

    ceefka, meager? 3 of the most popular uses of a database? If there is something you think we are missing, please reveal ;).

    We'll work on a web article asap.
  • ksherman - Monday, February 14, 2005 - link

    is it just me, or did you take the best Xeon and put it against a mid range Opteron? what about the 8xx series? what is the difference between 2xx and 8xx?
  • blackbrrd - Monday, February 14, 2005 - link

    Seems Intel just turned the table again. What about webserver performance?
  • blckgrffn - Monday, February 14, 2005 - link

    I meant on the desktop, which is why the PM doesn't really count, sorry I wasn't more clear on that...
  • blckgrffn - Monday, February 14, 2005 - link

    I hope that the upcoming prescotts with 2meg L2 cache show similar improvements across the board - not because I am Intel fan, but really AMD hasn't had much in the way of direct competition from Intel lately (the PM doesn't count)

    Every benchmark has been: The 3000+ AMD64 is better than nearly any P4 for gaming performance, and if you really want to win all the benches but one or two, shell out for the fx-55... kind of boring, really :)
  • ceefka - Monday, February 14, 2005 - link

    However meager the benchies, it proofs my point that a company should mix and match according to their needs and not just stick with one or the other because their supplier says they shoud buy this or that.

    We have lots of financial data and scans, tables etc. going here, so a 4-way Opteron can be justified to sit between a few Xeon boxes for other apps. Unfortunately we're in the Intel comfort zone and browsing through accounts, scans and tables is therefore tedious.
  • R3MF - Monday, February 14, 2005 - link

    just because i'm awkward -

    i'd like to see a comparison between a:
    > FX55 (2.6GHz) & O252 (2.6GHz)
    > nF4 Ultra & nF4 Pro (abit wln8+)
    > 2x 512MB DDR500
    > 2x 300GB Max10 NCQ
    > 6800 Ultra

    in order to see whether the core enhancements in the new Opteron make a difference........?

    am i asking for too much? :p
  • gordon151 - Monday, February 14, 2005 - link

    Yeah, this article needs to be re-written because the Opteron doesn't crush Xeon. These numbers are dubious!
  • danidentity - Monday, February 14, 2005 - link

    Jason, I hope you're ready for about 5 pages of comments pointing out the flaws in your testing methodology and another 5 pages demanding you re-do all the tests because the Opteron didn't destroy the Xeon.

    Fair warning. ;)
  • Jason Clark - Monday, February 14, 2005 - link

    Tiamat, yep corrected. Thanks
  • Tiamat - Monday, February 14, 2005 - link

    "Dual core Opterons will be socket compatible with existing 950 pin sockets that support 90nm (95W/80A)."

    Correct me if I am incorrect, did you mean 940 pin? If not, I have not seen any 950 pin sockets on the market...
  • Jason Clark - Monday, February 14, 2005 - link

    Aileur, we'll get right on it.
  • Jason Clark - Monday, February 14, 2005 - link

    They are coming soon :) Derek Wilson is going to deliver those.
  • Aileur - Monday, February 14, 2005 - link

    Im afraid youre gonna have to redo this whole article since the opteron doesnt wipe the floor with the xeon, and this is unacceptable.
  • Carfax - Monday, February 14, 2005 - link

    Can you please do some Workstation benchmarks?

    It is rumored that AMD enhanced the SSE2 units aswell as added SSE3 support, and I want to see if it's true.

Log in

Don't have an account? Sign up now