Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 


Forgot your password?
Close
typodupeerror
×
AMD IT

Itanium Retreats To Multis, Opteron Presses Attack 61

Posted by timothy from the personification-personified dept.
vincecate writes " Back in 1997 Itanium was presented as a compatible extension of x86, and Intel had dreams of replacing high end x86 by 1999 (about min 16 in link). However, the original 2001 Itanium had the 32-bit performance of a much older Pentium so Itanium is viewed as non-compatible. Now with the rise of what Microsoft is calling the "x64" architecture (AMD64 and EM64T), Itanium has been repositioned to the multiprocessor server market."

However, Opterons are designed for multiprocessing. Each has its own memory and built in hypertransport links to make NUMA multiprocessors. So existing Opterons don't need large expensive caches like Xeon MP, nor any glue chips for up to 8-way multiprocessors. This has started the commoditization of multiprocessors. You can now buy a 4-way Opteron for $6000 or an 8-way for $10,000.

There is an interesting interview with Tyan CEO and his assistant that give some info about future Opteron plans. People are working on 8-way motherboards that will become 16-way when duel-core Opterons come out. They also say that the next Opteron core, the K9, will be able to 'go over 60 processors without adding any external crossbar chips.' Another fun plan mentioned is connecting the hypertransport links using fibers for really large systems."
This discussion has been archived. No new comments can be posted.

Itanium Retreats To Multis, Opteron Presses Attack More

Itanium Retreats To Multis, Opteron Presses Attack

Comments Filter:

  • x64 vs x86? (Score:3, Insightful)

    by Ianoo ( 711633 ) on Monday August 23, 2004 @07:18PM (#10051623) Journal
    Why have Microsoft decided to call AMD64/EMT64 "x64"? Surely this will just add to confusion rather than improve matters, since CLEARLY x86 is better than x64, because it's higher!

    A better name would just be x86-64 or some generic marketing term. Any suggestions?
    • Your average Joe Six Pack has likely never heard the term 'x86' therefore hearing 'x64' would probably result in little confusion as far as marketing goes. Your average systems administrator likely has heard both terms and would know the difference anyway. I think x64 has a nice ring to it myself. It sounds like an experimental aircraft project.
      • I'd never heard "x64" before today.

        My preference is "86-64" -- get rid of the "x" business all together.

        • Re:x64 vs x86? (Score:4, Informative)

          by obeythefist ( 719316 ) on Monday August 23, 2004 @11:47PM (#10053190) Journal
          But if you want to remove the x, you can't be vague about the 86 - you'd need to reference the full 8086-64, although the CPU's we use today are markedly different from 8086, more like 80586-64, but then the 586 was really the pentium(tm) brand, so to be correct and without using an "x", you have to call it the pentium-64, which is really inaccurate because AMD's K8 hammer family is very different to a pentium internally, much more powerful CPU's. So it just isn't going to work.
        • But "x" is good marketing!

    • Re:Sexium (Score:3, Funny)

      by Bastian ( 66383 )
      We've been on Pentium way too long. Since six comes after five, let's call it "Sexium."

  • future intel systems will have a server and consumer Front Side Bus

    that means that all the Xeon boards will accept Itanium and means large Itanium systems could accept Xeon's (x86_64) and so those huge clusters could also be x86_64 clusters or IA64 clusters...

    intel hedge bets

    plus I thought that hypertransport bandwidth was good but not great (why the memory controler was on chip) so that means accessing memory on another processor would be expensive...

    hmmm if all the processors are working on the same d
    • The Itanium already uses a modified GTL/GTL+ bus, the only difference is that it runs at a difference speed than the bus used by the current Xeon DP/MP processors. What will happen though is that Intel will use a common socket, bus and socket for both the Xeon and the Itanium.

      Intel and HP are already doing something like that with their dual-core PA-RISC workstation, as it uses the same socket and chipset as the Itanium... the only difference is that the firmware used was designed for the PA-RISC. That rig

  • x86 code size advantage over Itanium (Score:4, Informative)

    by vincecate ( 741268 ) on Monday August 23, 2004 @07:37PM (#10051775) Journal
    It is reported that IPF executable images are typically three times the size of equivalent Alpha executables [shannonknowshpc.com]. I used crosstool to make a gcc cross compiler [kegel.com], and found Itanic (IPF) code to be twice the size of AMD64 code. This is a significant architectural price/performance difference when it comes to either cache size or memory bandwidth, and no doubt part of why Itanics are so expensive.

  • The AMD multiprocessor plan seems like an Itanic killer. History will probably record Itanium [wikipedia.org] as Intel's VLIW attempt to break away from x86. Very similar to their failed IAPX_432 object oriented attempt [wikipedia.org] and their i860 RISC attempt [wikipedia.org] to move customers away from x86. Each time Intel seemed to use the architectural fad of the day to try to move people off x86 but without good backward compatibility. Each time seems to have failed badly.

    • Re:Intel attempts to move away from x86 (Score:5, Interesting)

      by questionlp ( 58365 ) on Monday August 23, 2004 @07:59PM (#10051957) Homepage
      Although AMD is not directly aiming the Opteron at the Itanium (instead it's aimed more towards the Xeon DP and Xeon MP), the Opteron can be very competitive against the Itanium in a fair number of scenarios. There are some places where the Itanium will beat the AMD in performance, but it also costs more. For instance, the Itanium (with a bit of help from SGI) can scale into the hundreads of processors and still be able to run a single kernel image. Right now, that isn't exactly doable with the Opteron.

      Intel is aiming their Xeon with EM64T at the Opteron while pinning the Itanium against Sun's UltraSPARC, IBM's POWER, etc. Unfortunately, the Itanium is also used as a replacement for the PA-RISC and the Alpha :\

      I favor the Opteron over the Itanium because of backwards compatibility without performance problems, lower cost, lower power consumption and better I/O and memory throughput.

      I have bashed the Itanium in the past... but I still think it is a bit too early to sent it crashing towards an iceberg and sinking it soon. It does have it's good qualities, but also a fair amount of downsides.
      • For instance, the Itanium (with a bit of help from SGI) can scale into the hundreads of processors and still be able to run a single kernel image. Right now, that isn't exactly doable with the Opteron.

        This (SGI Altixes) is not a feature of Itanium, but rather of the proprietary S-HUB chips and NUMAlink. Opteron can scale easily as well, provided that you accompany it with a right chipset (as opposed to 1-4 CPU Opteron boxes which can live without an external northbridge).

        Just take alook at Cray XD-1 -

        • Nonetheless, Itanium2 still has a FP performance superior to Opteron.
          Only in FP-Performance/CPU, and not by that much. By most other measures Opteron wins. If you look at FPP/$, FPP/watt, FP/motherboard, FP/cubic-foot Opteron wins. Opteron has 4-way on a motherboard, and moving to 8 and 16-way on a motherboard while Itanic is looking at 2 to 4-way. In the end price/performance is far more important that absolute performance per CPU.
          • The Itanium can scale up to 8, 16, 32 or even 64 processor modules (where each module can contain one or two processors, a la HP's mx2) whereas the Opteron is only available in four-processor configurations. 8-way servers are still in the work and aren't available in volume yet.
            • It looks like someone is releasing an 8-way Opteron pretty soon [hpcsystems.com]. From the specifications, it's nice to see that they are providing each processor with enough memory slots to allow for full 128-bit memory connection and Infiniband connectivity.

            • The Itanium can scale up to 8, 16, 32 or even 64 processor modules ...

              A new chipset for 32-way opterons [eweek.com] should be out by the end of the year. So yes, at the moment Itanium has retreated to multiprocessors where the only comperable Opteron system is the Cray XD1 [cray.com]. But it won't be safe for long.

      • Since the Itanium seems to be falling behind I have wonder if the Alpha might rise from the grave. Probably not but it is a nice idea.
        • The Alpha as we knew it probably won't be rising from the graves... but parts of it will get merged into the Itanium (at least that is what Intel has been showing in their pretty presentations).

          I hope they do make very, very good use of the Alpha engineers that they got.
          • I just wonder if the Itanium is just a bad idea all around. Intel tried the "put the smarts in the compiler" idea with the i860 and it was a total failure. RISC chips like the PowerPC, Power4, Xscale/ARM family, and the Alpha seem to be better bets than the Itaniums ISA. Yes Intel and AMD have done wonders making pigs fly but this decoupleing of ISA from logic seems to be a bad plan in the long run. How much of P4 and AMD64 chip is wasted on nasty decodeing logic just to run 8086 instructions? The Alpha, M
    • The iAPX 432 was a complete and utter failure; by comparison, ia64 has been a success. Ia64 *is* seeing design wins, and does have market niches where it's a good choice. The iAPX 432 was just a dog.

      • The iAPX 432 was a complete and utter failure; by comparison, ia64 has been a success. Ia64 *is* seeing design wins, and does have market niches where it's a good choice. The iAPX 432 was just a dog.

        Intel is said to have spent $5 billion on Itanic. They sold 100,000 chips in 2003. If you say $3,000/chip that is $300 mil. I think it is safe to say that Intel has lost more money on ia64 than they did on iAPX 432. And the percentage of x86 that moved to ia64 is also about 0.

        Intel admitted the iAPX 432

        • Intel admitted the iAPX 432 was a failure and killed it. However, they have not yet admitted the ia64 is, so the blood will keep draining for awhile yet. Sometimes a clear failure hurts less than a not so clear failure.

          Another thing is they seem to have reduced development of the x86 since they thought Itanic was working. They put their best guys on the Itanic and just sort of tweeked the P4 for years. This let AMD pass them. Intel could loose many billions because of this. Intel's stock is already d

      • It really is too bad that Intel often seemed to bet on the wrong cpu. The 960 which was a development of the iAPX432 was a very good chip. Much better than the i860 but Intel removed the mmu and pushed it into the embeded market.

  • Ready... FIGHT! (Score:5, Funny)

    by Mr. Flibble ( 12943 ) on Monday August 23, 2004 @08:02PM (#10051981) Homepage
    People are working on 8-way motherboards that will become 16-way when duel-core Opterons come out.

    That will be soo cool when we have duel core opeterons. Can you imagine 16 opetrons dueling it out in your case?

    Cool! Wicked Awesome!!!

    What? A typo. Oh. Err... I knew that...

  • Itanium, Opteron related news... (Score:5, Funny)

    by hoggoth ( 414195 ) on Monday August 23, 2004 @08:03PM (#10051986) Journal
    Itanium Retreats To Multis, Opteron Presses Attack.
    In related news, Megatron Retreats to Cybertron, Optimus Prime Presses Attack.

  • US$6000/1000 for 4/8 CPUs (Score:4, Interesting)

    by hbackert ( 45117 ) on Monday August 23, 2004 @09:09PM (#10052367) Homepage

    Those offerings from Rocketcalc are dual Operon boards with orginary clustering. The only difference is, they put them in one case. A 4 CPU or 8 CPU Opteron box is far more expensive. of course a 8 CPU Itanium2 is expensive too. But comparing a bunch of (commodity) dual CPU boards with one 8 CPU box is not fair. It's the often found apple-and-oranges-comparison [improb.com] comparison.

    • Those offerings from Rocketcalc are dual Operon boards with orginary clustering. The only difference is, they put them in one case.

      Ouch. I did not realize that. Sun's 4-way has different cards that are connected together with hypertransport links and I thought these guys were doing the same thing in the backplane.

      I have seen a 4-way Opteron motherboard (I think it was Tyan) for about $1,000. Getting this, CPUs, etc would not be all that expensive. So the $6,000 price seemed plausible.

      • Last I checked, Tyan's 4way Opteron boards start at $1500 and change. And then you have to get the 8xx series processors. Not exactly cheap - $1250 for the Opteron 848, $855 for the 846 (or if you really have cash to blow, $1549 for the 850). And then you need some good registered ECC DDR400 RAM - $120 per 512 meg stick of Kingston, and I'd want to put several gigs in a machine like that... Plus incidentals like a huge case, really big fans and an even bigger power supply, and you're getting into some serio
    • Also noted, the prices quoted on the Rocketcalc site are "starts at" prices someone wanna give a stab at what an actual usable config would cost?
  • "[...]Intel had dreams of replacing high end x86 [...]Itanium has been repositioned to the multiprocessor server market."

    What else is and has been the domain of high end x86, if not the multiprocessor server market?

  • I wonder if this is a reaction to IBM's dual core G5 [theregister.co.uk] chips that will likely be appearing in Apple Xserve boxes early next year? (oh and motorola are doing dual core G4s too).

    I can't help thinking IBM will have the edge here, since Apple's business oriented G5 range is already all dual processor, and the current G5 acritecture is (to cut a long story short) a cut down version of the quad processor Power chip set to start with.

  • 10) Compatibility mode is so slow people say it is non-compatible
    9) Sales can generously be described as "flat"
    8) Alpha development halted for years before Itanic caught up
    7) Microsoft calls AMD64 by the name x64
    6) Code-size is twice x64, so needs 2x cache and 2x memory bandwidth
    5) Fewer software tool vendors support it now than a year ago
    4) Even before Win-x64 is released, MS supports more products on x64
    3) Don't know anyone buying one, just someone who got one for free
    2) Marketing keeps telling pe
  • Here are some interesting numbers on Itanic and Opteron sales [theregister.co.uk]. Total Itanic system revenue was $319 mil in Q2, up from $287 in Q1 for 11% increase. Total servers at 5,665 in Q2 compared to 2,717 in 2003-Q2. Opteron servers total 60,000 and generated $191m in revenue, according to Gartner. Previously reported that Opteron increased by 81% from Q1 to Q2. This 60,000 compares to just 2,735 shipments and $8m in revenue in the same quarter last year. At this rate the dollars should be about equal in Q3, though

Slashdot Top Deals

"I've finally learned what `upward compatible' means. It means we get to keep all our old mistakes." -- Dennie van Tassel

Close