Slashdot Mirror


World's Most Powerful x86 Supercomputer Boots Up in Germany

Nerval's Lobster writes "Europe's most powerful supercomputer — and the fourth most powerful in the world — has been officially inaugurated. The SuperMUC, ranked fourth in the June TOP500 supercomputing listing, contains 147,456 cores using Intel Xeon 2.7-GHz, 8-core E5-2680 chips. IBM, which built the supercomputer, stated in a recent press release that the supercomputer actually includes more than 155,000 processor cores. It is located at the Leibniz-Rechenzentrum (Leibniz Supercomputing Centre) in Garching, Germany, near Munich. According to the TOP500 list, the SuperMUC is the world's most powerful X86-based supercomputer. The Department of Energy's 'Sequoia' supercomputer at the Lawrence Livermore National Laboratory in Livermore, Calif., the world's [overall] most powerful, relies on 16-core, 1.6-GHz POWER BQC chips."

151 comments

  1. DID SOMEONE SAY BBQ? by Rinikusu · · Score: 4, Funny

    My fatass almost got excited for a second.. a supercomputer fueled by BBQ... :(

    --
    If you were me, you'd be good lookin'. - six string samurai
    1. Re:DID SOMEONE SAY BBQ? by Thundaaa+Struk · · Score: 1

      I thought the same thing.......turns out it was just a bunch of supermuc.

    2. Re:DID SOMEONE SAY BBQ? by Megahard · · Score: 2, Funny

      No, it just runs hot enough to also work as a BBQ.

      --
      I eat only the real part of complex carbohydrates.
    3. Re:DID SOMEONE SAY BBQ? by ackthpt · · Score: 1, Offtopic

      No, it just runs hot enough to also work as a BBQ.

      Silly you. Everyone knows everything is better with bacon, so it needs to be hot enough to fry BACON!

      --

      A feeling of having made the same mistake before: Deja Foobar
    4. Re:DID SOMEONE SAY BBQ? by Thundaaa+Struk · · Score: 0

      I'll have one SuperMuc w/Bacon please!!!

    5. Re:DID SOMEONE SAY BBQ? by Anonymous Coward · · Score: 0

      Stock in BBQ companies fluctuated today as the masses of nerds who read slashdot were subconsciously influenced to eat BBQ for lunch.

  2. Re:I need that... by Anonymous Coward · · Score: 3, Funny

    Or check tpyos.

  3. Re:I need that... by Qubit · · Score: 5, Funny

    ...so I can first post mote quickly!

    let's fix you're spelling frist, then work on the spead of you're posting.

    --

    coding is life /* the rest is */
  4. power to x86 by SlashDev · · Score: 4, Interesting

    powerful and x86 are oxymorons. Try the i860 architecture now THAT's a processor, it's ancient I know.

    --

    TOP DSLR Cameras Reviews of the top DSLRs
    1. Re:power to x86 by Joce640k · · Score: 3, Insightful

      I'm pretty sure they'll be running them in x64 mode, not x86.

      I'm sure modern Intel CPUs with multiple instruction dispatch and SSE for math instead of x87 will give the i860 a run for its money.

      But yeah ... some of those old chips were cool (even if they didn't have a proper divide or sqrt instruction :-)

      --
      No sig today...
    2. Re:power to x86 by rgbrenner · · Score: 4, Informative

      wow.. you're right. The i860 had 1 whole core and ran at up to 50mhz.

      Imagine if they built this supercomputer out of those. Instead of 155,000, it would only need 8,370,000.

      Now THAT's a super computer.

      On a serious note, wikipedia says:

      On paper, performance was impressive for a single-chip solution; however, real-world performance was anything but. One problem, perhaps unrecognized at the time, was that runtime code paths are difficult to predict, meaning that it becomes exceedingly difficult to order instructions properly at compile time.

      Sounds like an earlier version of Itanium

    3. Re:power to x86 by 0123456 · · Score: 2

      I worked with i860s years ago. They weren't bad for graphics, but the guys who had to do general-purpose work on the i860 workstations hated them.

      Except the one who was promoted to i860 from the Clipper machine. I don't know why he always got the worst jobs.

    4. Re:power to x86 by ackthpt · · Score: 1

      I'm pretty sure they'll be running them in x64 mode, not x86.

      I'm sure modern Intel CPUs with multiple instruction dispatch and SSE for math instead of x87 will give the i860 a run for its money.

      But yeah ... some of those old chips were cool (even if they didn't have a proper divide or sqrt instruction :-)

      A big thank you to AMD for proving Intel wrong, the we really do need 64 bit processors. =)

      --

      A feeling of having made the same mistake before: Deja Foobar
    5. Re:power to x86 by Anonymous Coward · · Score: 0

      Behold, an article from 1999 hailing the Post RISC era: http://arstechnica.com/features/1999/10/rvc/

      To sum up: x86 (since the P4) are not x86 anymore, but have a x86 front end to a modern RISC core. They were even more "RISC" than official "RISC" chips of the era. (probably even more true now)

    6. Re:power to x86 by Score+Whore · · Score: 1

      You do realize that RISC has nothing to do with the internals of the processor. It's about the instruction set. And the point was that you could be faster by having simple, fast instructions as opposed to complex, slow instructions. Turns out that Intel has been able to be faster with complex, fast instructions. How that happens inside the chip is irrelevant to the principle in question.

    7. Re:power to x86 by KingMotley · · Score: 1

      To be fair, Intel was right. We didn't need it at that time for most desktop apps. They never said we will never need 64-bit processors, just there were other more pressing issues they were tackling first. Seems it paid off pretty well for them. How is AMD fairing these days? When was the last time they were competitive, or turned a profit?

    8. Re:power to x86 by Anonymous Coward · · Score: 0

      IIRC there were x86 chips that drew ~70 Watts. That's a lot of power.

    9. Re:power to x86 by MikShapi · · Score: 1

      Oxymorons.
      You keep using that word. I do not think it means what you think it means.

      --
      -
    10. Re:power to x86 by cheesybagel · · Score: 1

      They were wrong. Try to find their original timetable for 64-bits on the desktop. You were supposed to wait for Itanium (which at the time was called either IA-64 or EPIC) to filter down.

    11. Re:power to x86 by cheesybagel · · Score: 2

      Modern RISC processors are not that simple anymore. It used to be that they had no multiply or divide instruction but all modern RISC processors have those. It also used to be that their memory addressing was simpler but several modern RISC processors like POWER have complex memory addressing schemes. So boh.

    12. Re:power to x86 by gshegosh · · Score: 1

      i860? Wow, you must be from the far future, we only have i7 here.

    13. Re:power to x86 by Anonymous Coward · · Score: 0

      You think? Even TODAY, how many things do YOU have running 64-bit on your desktop that doesn't have a 32-bit version that you couldn't tell if it was swapped out?

      What they were wrong about was the perceived importance of a feature that noone really needed because of technical ignorance. Even many techies bought into the whole 64-bit hype when the only thing they really cared about was a larger addressable memory space, and that was already available through PAE.

    14. Re:power to x86 by Tamerlin · · Score: 1

      "Even many techies bought into the whole 64-bit hype when the only thing they really cared about was a larger addressable memory space, and that was already available through PAE." Most of them still don't need the larger addressable memory space. To top it off, even on natively 64-bit platforms, most of the software available is 32-bit. Now there is quite a bit of 64-bit software for x86, but it's still not because of memory requirements, it's because of the extra registers and SIMD instructions that aren't available in legacy x86 mode. These require 64-bit mode on x86, so we accept the memory overhead and associated bandwidth overhead because the additional registers, flat floating point register model, and new SIMD instructions far more than make up the difference, and the margin increases with every new processor generation.

    15. Re:power to x86 by drsmithy · · Score: 1

      To sum up: x86 (since the P4) are not x86 anymore, but have a x86 front end to a modern RISC core.

      Actually, the Pentium Pro (1995) was the first Intel chip to use this design. AMD's K5 (1996) was another early CPU that used the same model.

    16. Re:power to x86 by Anonymous Coward · · Score: 0

      This explains why HP discontinued the 25SFF DL380p Gen 8 I ordered with the E5-2680 -- all available chips were sent to .de

  5. Power BBQ Chips by j.+andrew+rogers · · Score: 3, Funny

    I need to find myself some of these Power BBQ Chips mentioned in the summary. Fast and tangy without the downside of Cheetoh fingers.

    1. Re:Power BBQ Chips by Anonymous Coward · · Score: 0

      *bump*

  6. And still... by santax · · Score: 1

    crysis won't run on highest settings. Sjeez.

    1. Re:And still... by gman003 · · Score: 1

      Update your jokes. I have literally maxed out Crysis on a laptop. All settings on ultra, 1920x1080, 16x MSAA, 16x anisotropic filtering. Doesn't dip below 60fps.

    2. Re:And still... by santax · · Score: 1

      Ok, next time I will say Crysis 2. Must be a nice laptop btw! Haven't tried Crysis here in years though, but referring to the game is a bit of a meme here. Just as, you insensitive clod ;)

    3. Re:And still... by KingMotley · · Score: 1

      Yes, but can it run Cysis on my matrix of 3x3 (9 for those that can't multiply) monitors, and then real-time compress it to x.264 for streaming live all at full resolution (5760x3600 @ 60FPS) under wine so it can run on linux?

    4. Re:And still... by gman003 · · Score: 1

      No, because it only has three video outputs.

      It might be able to do 2x2, but I actually don't have three more monitors to try it with.

    5. Re:And still... by KDR_11k · · Score: 1

      Crysis 2 is less demanding, it was designed for consoles first and foremost.

      --
      Justice is the sheep getting arrested while an impartial judge declares the vote void.
    6. Re:And still... by gman003 · · Score: 1

      Until you install that patch, whose purpose seems to be to make the game run worse, not look better. It's almost deliberately unoptimized. For instance, with the patch installed, if there is water anywhere on the map, the water is rendered across the full map, even when completely invisible. And certain objects have had their polycount bumped into orbit - I suspect they simply took the high-res meshes they used to bake normal maps, and used them as render meshes.

  7. Re:I need that... by Thundaaa+Struk · · Score: 1

    A few fries short of a happy meal eh?

  8. the real question by slashmydots · · Score: 4, Funny

    But the real question is, can it run bitcoin mining software? See, you thought I was going to say Linux or Crysis, didn't you? lol.

    P.S. most miners are run on Linux btw ;-)

    1. Re:the real question by Anonymous Coward · · Score: 0

      I have access to a decent sized cluster. For giggles, I tried, and was able to do around 11.5 GHash/second.

      Based on this, the cluster in the article would probably push between 400 and 500 GH/s, or about 650 high end video cards. :)

    2. Re:the real question by Anonymous Coward · · Score: 0

      Most REAL miners use FPGA's not CPU/GPUs

    3. Re:the real question by jpapon · · Score: 2

      Most REAL miners use dynamite, pickaxes, shovels, and heavy machinery.

      --
      -- Let us endeavor so to live that when we pass even the undertaker shall be sorry. -- M. Twain
    4. Re:the real question by WhoBeDaPlaya · · Score: 1

      Actually, I was going to say "Could you imagine a Beowulf cluster of those?", although I suppose that would be kind of a "Yo Dawg, I herd you like clusters of clusters" type of comment.

    5. Re:the real question by Anonymous Coward · · Score: 0

      But the real question is, can it run bitcoin mining software? See, you thought I was going to say Linux or Crysis, didn't you? lol.

      P.S. most miners are run on Linux btw ;-)

      No because I assumed you had a functional brain and know that crysis isnt very powerful and doesnt require a big pc. It never has and never will.

      See the problem with crysis is it ran like shit on powerful pcs so everyone thought it was from the future and uber powerful. Fact is it just wasnt optimized very well because crytek are shitty coders (there is a reason why only a few no name games have licensed their engines and those games sucked). If crysis is so super powerful then why did like the 3rd patch improve performance like 25%? Or why did a home made .ini tweak improve the game like 40%? Because the engine isnt optimized and it runs like shit.

    6. Re:the real question by Chris+Mattern · · Score: 1

      Really? I've been playing Minecraft for a while now, and I can make dynamite, pickaxes and shovels...but how do I make heavy machinery?

    7. Re:the real question by WhoBeDaPlaya · · Score: 1

      Have you looked at the backorders for those lately? It took me 3 months to finally receive my order of 6 BFlabs Singles.

    8. Re:the real question by flimflammer · · Score: 1

      Through the technic/tekkit pack of course.

    9. Re:the real question by AngryDill · · Score: 1

      Using a Beowulf cluster of sticky pistons, if you can imagine it.

      -ad-

      --


      I'm Erwin Schrodinger and I approve of this message, and I do not approve of this message!
  9. Livermore Power BQI ? by damn_registrars · · Score: 1

    If it was instead running Itanium (yes, I know that nobody uses Itanium any more) it would have been well suited to be called "Power BBQ" just by the heat output.

    --
    Damn_registrars has no butt-hole. Damn_registrars has no use for a butt-hole.
    1. Re:Livermore Power BQI ? by acidfast7 · · Score: 0

      it's actually BBQ season in Deutschland ... I just got in from one :D

  10. Just in time... by Anonymous Coward · · Score: 0, Informative

    Windows 8 is a hog.

  11. Crappy story title by Anonymous Coward · · Score: 0

    Its Europe's most powerful x64 supercomputer, not the world's.

    1. Re:Crappy story title by Anonymous Coward · · Score: 0

      It's the most powerful x86 supercomputer in the world the same way the world series is a world series.

    2. Re:Crappy story title by Anonymous Coward · · Score: 0

      You misunderstood. It's the x86 supercomputer boots which are the world's most powerful. :-)

  12. Re:I need that... by damn_registrars · · Score: 3, Funny

    ...so I can first post mote quickly!

    let's fix you're spelling frist, then work on the spead of you're posting.

    You head two many correctly sppeled wurds you must be a bot.

    --
    Damn_registrars has no butt-hole. Damn_registrars has no use for a butt-hole.
  13. Re:Herzlichen Glückwunsch und by Anonymous Coward · · Score: 0

    dam u str8 babygurl

  14. Financial Modeling by Anonymous Coward · · Score: 1

    Now if the Fed can just loan them our financial modeling software,
    maybe we can save Spain.

    On 2nd thought Goldman-Sachs might be a better place to shop for software.

  15. what's it going to run? by ThorGod · · Score: 1

    I skimmed the article and couldn't find mention of what it's going to be calculating.

    --
    PS: I don't reply to ACs.
    1. Re:what's it going to run? by gstoddart · · Score: 1

      I skimmed the article and couldn't find mention of what it's going to be calculating.

      Well, it's a center for supercomputing -- so likely many different things.

      It doesn't sound like it's built for a specific purpose, but the many things people use supercomputers for -- fancy physics simulations and the like seem popular. I'm sure some grad student will use it for something goofy now and then. No doubt industry will pay to get some time on it to solve some specific problems.

      --
      Lost at C:>. Found at C.
    2. Re:what's it going to run? by ackthpt · · Score: 1

      I skimmed the article and couldn't find mention of what it's going to be calculating.

      It's for figuring out how long it will take for Greece to pay back their Euro loans.

      and at the rate Spain is going they'll need to add a few more CPUs.

      --

      A feeling of having made the same mistake before: Deja Foobar
    3. Re:what's it going to run? by KingMotley · · Score: 2

      Greece's deficit.

  16. My computer is way faster by Anonymous Coward · · Score: 0

    2.7-GHz, 8-core E5-2680 chips

    My computer is way faster than that!!!

    and contains 155,000 processor cores

    Oops, Never mind!

  17. Obligatory... by HerculesMO · · Score: 0

    Can it play Crysis?

    --
    The price is always right if someone else is paying.
  18. Europe suddenly got bigger... by mholve · · Score: 1

    It's EUROPE's fastest supercomputer - but the topic title says "World." Last time I checked, Europe wasn't quite THAT big...

    1. Re:Europe suddenly got bigger... by mholve · · Score: 0

      It's EUROPE's fastest supercomputer - but the topic title says "World." Last time I checked, Europe wasn't quite THAT big...

      Ahh, x86. D'ohh! :p

    2. Re:Europe suddenly got bigger... by rgbrenner · · Score: 2

      You might want to read the article again. It says it is Europe's fastest supercomputer AND the worlds fastest x86 supercomputer.

      It's #4 on the top500, and the other 3 are not x86 (POWER BQC for #1 and #2, and SPARC VIIIfx for #3).

  19. Re:Herzlichen Glückwunsch und by Anonymous Coward · · Score: 1

    It's believe "mir". To believe (glauben) needs the dative case, not accusative (that would be "mich").
    Now go and brush up on your German. Jeeeez.

  20. ~1800 kilowatts (100 watt per CPU) by cpu6502 · · Score: 1

    That's quite a heater! Mine only goes up to 1.5 kilowatts.
    So is Xeon a faster CPU than the i7?

    --
    My AC stalker: " I personally agree with your posts most of the time, but that won't keep me from modding you troll"
  21. Too much powah? by Anonymous Coward · · Score: 0

    ... and in an instant, what was left of Germany's economy is vacuumed up by utility companies.

  22. Re:I need that... by Thundaaa+Struk · · Score: 1

    Did anyone else read this in a Fu Manchu voice? *giggle*

  23. Slashdot Grab Bag by Roachie · · Score: 3, Funny

    1) Does it run Linux?
    2) I for one, would like to welcome our new register constrained overlord.
    3) Can you imagine a Beowulf cluster of these?
    4) In Soviet Russia supercomputer run YOU!
    5) There is no God, I reject your fairytales.

    --
    This sig is not paradoxical or ironic.
    1. Re:Slashdot Grab Bag by damien_kane · · Score: 3, Informative

      1) Does it run Linux?

      Yes, SUSE

      2) I for one, would like to welcome our new register constrained overlord.

      Then you had better get started on its AI routines

      3) Can you imagine a Beowulf cluster of these?

      Why yes, yes I can (and it would be huge, power hungry, and require it be run at the bottom of the ocean for heat-dissipation)
      BTW, from TFA this system is cooled "by dumping water directly on the microprocessors", after which the warmed water is used to heat the rest of the building in winter

      4) In Soviet Russia supercomputer run YOU!

      Only if you get around to finishing Point 2

      5) There is no God, I reject your fairytales.

      You mean you won't buy them any more?
      Damnit, what am I going to do with this gross of tails I tore off of faeries last week? Not cool, man...

    2. Re:Slashdot Grab Bag by Discopete · · Score: 1

      BTW, from TFA this system is cooled "by dumping water directly on the microprocessors", after which the warmed water is used to heat the rest of the building in winter

      Um, the article actually says "Aquasar system pumps water directly over the microprocessors" not "dumping water directly on"

    3. Re:Slashdot Grab Bag by slew · · Score: 1, Funny

      1) Does it run Linux?
      2) I for one, would like to welcome our new register constrained overlord.
      3) Can you imagine a Beowulf cluster of these?
      4) In Soviet Russia supercomputer run YOU!
      5) There is no God, I reject your fairytales.

      6) ???
      7) Profit!

    4. Re:Slashdot Grab Bag by Tarlus · · Score: 1

      Bravo. =)

      --
      /* No Comment */
    5. Re:Slashdot Grab Bag by Roachie · · Score: 1

      Ah! yes I overlooked the lovable, ubiquitous /. pedantry, good catch my man.

      Al least you have a sense of humor, fuck.

      --
      This sig is not paradoxical or ironic.
    6. Re:Slashdot Grab Bag by L4t3r4lu5 · · Score: 1

      To answer the absent "6)", Crysis is rendered at 40FPS.

      In software.

      --
      Finally had enough. Come see us over at https://soylentnews.org/
    7. Re:Slashdot Grab Bag by Anonymous Coward · · Score: 0

      I've also heard that god is dead. But did Netcraft confirm it?

    8. Re:Slashdot Grab Bag by tom17 · · Score: 1

      I heard you like memes so I added a meme to your meme so you can meme while you meme.

  24. It would had been the worlds fastest. by jellomizer · · Score: 1, Troll

    But they couldn't get the money out of Greese fast enough.

    --
    If something is so important that you feel the need to post it on the internet... It probably isn't that important.
  25. free delivery? by Anonymous Coward · · Score: 0

    $31.8 million in processors....if they bought them from newegg.

  26. What about CE? by Impy+the+Impiuos+Imp · · Score: 5, Funny

    > actually includes more than 155,000 processor cores

    Scientists and engineers toyed with putting Windows 8 on it, but Windows 8 with 150,000-200,000 core support was over $73 trillion.

    --
    (-1: Post disagrees with my already-settled worldview) is not a valid mod option.
    1. Re:What about CE? by PRMan · · Score: 2

      And Vista was still too slow on it...

      --
      Peter predicted that you would "deliberately forget" creation 2000 years ago...
  27. Too bad they didn't name it... by swamp+boy · · Score: 0

    Das Packard Bell -- ist nicht jus fur Walmart anymur

  28. I can hear the chants ... by jxander · · Score: 4, Funny

    We're number four!!
    We're number four!!
    We're number four!!

    --
    This signature is false.
    1. Re:I can hear the chants ... by Anonymous Coward · · Score: 0

      It's Germany so shouldn't it be

      We want number two!
      We want number two!
      We want number two!

    2. Re:I can hear the chants ... by Kjella · · Score: 2

      Looks like Hollywood has got prior art.

      --
      Live today, because you never know what tomorrow brings
  29. My understanding by killmenow · · Score: 1

    I think it's designed to run complex calculations on how the price of tea in china is related to everything.

  30. Shall we . . . by Traciatim · · Score: 1

    play a game?

  31. Unrelated, but I am curious by Kaptain+Kruton · · Score: 1

    Has anyone created a 'super computer' out of raspberry pi's yet?

    1. Re:Unrelated, but I am curious by luis_a_espinal · · Score: 1

      Has anyone created a 'super computer' out of raspberry pi's yet?

      With what supplies? There are not enough of them for single-unit buyers, let alone to buy the bulk necessary to build a super-computer. Yes, people could use the schematics and build tens (if not hundreds) of thousands to build a super-computer, cluster whatever. But the economics would simply not scale (compared to buying already stuff by the truckload.)

      Now, a better question would be "has anyone created a Beowulf cluster" with a bunch of rasberry pi's? That is a more reasonable enterprise, me thinks.

    2. Re:Unrelated, but I am curious by oodaloop · · Score: 1

      The proper phraseology around these parts is, "Imagine a beowulf cluster of raspberry pi's". Alternatively, you also allowed to imagine beowulf clusters of supercomputers, iPad 3's, and Jeri Ryan.

      --
      Tic-Tac-Toe, Global Thermonuclear War, and relationships all have the same winning move.
  32. Re:Herzlichen Glückwunsch und by Anonymous Coward · · Score: 0

    It's believe "mir". To believe (glauben) needs the dative case, not accusative (that would be "mich").
    Now go and brush up on your German. Jeeeez.

    Ich glaube bist du ein Luder. (captcha: stupidity)

  33. Can you send a screencast?

    At those settings, it must be better than real life.

    1. Re:Wow by gman003 · · Score: 1

      I'll take some screencaps next time I play, but yeah, it does look "better" than real life, in the same way that a big-budget movie looks better than real life.

      Of course, it all falls apart if you can see anyone's face clearly (especially if they're talking). Or if there's fire. Or something breaking. Or rotor wash. Or a million other things that look almost, but not entirely, right.

      The game looks awesome, especially for its age (it's about on par with Skyrim, which came out about three years later). In some limited situations, I would even say it is photorealistic. But I'll also say that in most cases, it's only *mostly* photorealistic, and that in some cases, it's just downright bad (Crytek cannot for the life of them figure out facial animation).

    2. Re:Wow by Anonymous Coward · · Score: 0

      On par with Skyrim?
      Skyrim has about the worst graphics to system requirements ratio of every game I ever played. I don't find it hard to believe that there are three year old games that look better.

  34. .stl torrent plz by Anonymous Coward · · Score: 0

    for my 3d printer

  35. Q: Why are we still on x86 and 64bit and not 128? by Anonymous Coward · · Score: 1

    Every year I keep reading that there are these new technologies that allow processors to go up to 128, 256, 512 and 1024bit computing (and beyond) or at least should be seen in the next year or two but that never happens. I've been hearing about this since the turn of the century. So could somebody be kind enough to explain this to me please and whether or not this has a use for anyone?

  36. at first glance by Anonymous Coward · · Score: 0

    "...1.6-GHz POWER BBQ chips."

  37. That Clock Speed Sucks by barlevg · · Score: 2, Insightful

    I really hate how the focus these days is on more cores, not faster cores.

    Not every task is trivially parallelizable, and even with those that are, the speedup you get from running on N cores is always going to be less than Nx.

    I'd be much more impressed by a supercomputer running, say, 1/4 as many 4.0 GHz+ processors.

    Also: if what you're going for is massively parallelizable tasks, x86 is so last century--GPGPUs are where it's at.

    1. Re:That Clock Speed Sucks by ThorGod · · Score: 1

      I think we're going to be stuck in the same ghz range until we're past silicon.

      That's what I remember being told, anyway...

      --
      PS: I don't reply to ACs.
    2. Re:That Clock Speed Sucks by afidel · · Score: 1

      Max turbo on the E5-2680 is 3.5Ghz and with a higher IPC than any previous processor it's going to get more done per core per wall time than anything but the E5-2687W (150W TDP) or the E5-2690 which is significantly more expensive (almost 20% more).

      --
      There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
    3. Re:That Clock Speed Sucks by Anonymous Coward · · Score: 1

      You are incorrect. You can get superlinear speedups, for example when you parallelize a problem across multiple machines and each machine needs to hold less data. If you cross the threshold from out-of-cache to in-cache, the resulting system can run at more than Nx throughput.

    4. Re:That Clock Speed Sucks by AReilly · · Score: 2

      Limiting factor these days is how much power you can get in and out of the box. They will have optimized for that. And these processors probably do have GPUs on them.

      --
      -- Andrew
    5. Re:That Clock Speed Sucks by slew · · Score: 4, Informative

      I think we're going to be stuck in the same ghz range until we're past silicon.

      That's what I remember being told, anyway...

      Even when we get past "silicon", there are some fundamental issues that will likely constrain clock-speeds things until we solve them.

      First, the design of small low power devices (e.g, switching transistors) is currently problematic. Minimum sized geometries tend to "leak" more power, and potential subsitutes for silicon that are faster also tend to have leakier transistors (like graphene). We can make the devices bigger to minimize this, but then they switch slower, and there is more distance to traverse between devices. This is problematic in that the perf per watt tradeoff isn't great if you are doubling the watts to get 50% more perf (as an example), sometimes it doesn't make sense to go so fast.

      Second, we are reaching manufacturability limits. Today, one of the biggest problems with silicon is parametric yield loss. This is basically device-to-device variation of circuit parameters due to manufacturing variation. This requires quite a bit of over-engineering of margin which reduces the ability to use any of the intrinsic speed advances. We are now using nearly every trick in the book to get small devices that lay down stuff where you can count the dimensions of some features in atoms on your fingers and toes, so parametric yield loss due to + or - one atom dimension average change causing a 5-10% variation isn't likely to go way very soon.

      Third, re-syncronization uncertainty is now a big problem and getting worse. If a re-synchronizer circuit (say one that harmonizes two sides of an asynchronous fifo across 2 clock domains running at the same nominal frequency) is designed so that it would only fail 1-in-a-million times, you could have a reasonable failure-rate by cascading a few of them. If you are running 10 or 100 times faster, that's not a scalable strategy. Nowdays, even the jitter from a phase-locked and delay-locked loops or from two slightly mismatched clock-trees on different parts of a chip can be several clock periods long so what used to be a fairly simple syncrhonization problem now would likely be 10-100 times harder if it was 10-100 times faster (jitter isn't improving as fast as the potential clock rate).

      Of course if we stop using electrons in lattices for computational circuits (e.g., use photons in crystals), and developed new structured circuit realization technologies that allowed reducing some of the engineering margins required to yield devices, some of these limitations might be solved in different ways, but those types of advances are probably quite far off... I'm willing to wager, that we will start to leverage alternate computation technologies (e.g., like ubiquitous parallel operation, or even quantum) before we get there, so maybe going so fast won't seem as critical as it does today...

    6. Re:That Clock Speed Sucks by Anonymous Coward · · Score: 1

      So your complaint is that " Not every task is trivially parallelizable " and then suggest "GPGPUs" as a solution ? You realize that GPUs are only efficient at problems that can be split into millions of tiny, independent problems that execute the same function on different data, which makes it nearly impossible for some programs to even run or have any kind of speedup on GPUs. The next problem with GPUs is their lack of ram, while you can easily cram 128 GB per CPU on a regular motherboard, even the tesla K10 (which only support single precision at good speed, yet another block for most scientific programs) only has 4 GB per gpu ( 8 in total ). This making it nearly impossible to run very large computations on the GPU. Processing parts of the problem on the GPU, unloading, processing on the CPU to find the next part and merge results possibly more computations, reloading .... would just waste so many cycles and would most likely such a complex task that there is no speed gain in it. GPUs work really well with Linear algebra, which is why they give so many Gflops in linpack, sadly most Programs are not only linear algebra like linpack is... that would be too easy.

      Also serious scientific programs are all massively parallel and the CPUs clock often is not the bottleneck. In my experience, most of the time its IO, the interconnect or the memory bandwidth that are the bottlenecks. In fact the best results in terms of efficiency I had for some Programs were with x86 cpus clocked at 1.8 Ghz.

      Lastly, these machines are no toys, power usage and processor lifetime and reliability are a huge concern, with thousands of CPUs there are failures all the time. 4 Ghz CPUs don't have either if you have to overclock them that far. I don't think with current technology it would be possible to have a reliable cluster with such a high clock.

      In conclusion: GPU are no silver bullet, high cpu clocks are usually not needed and/or technically unfeasible .

    7. Re:That Clock Speed Sucks by Anonymous Coward · · Score: 0

      Not every task is trivially parallelizable

      Does this seem like the kind of machine that one would use for "every task"? Or any "trivial" ones at all?

    8. Re:That Clock Speed Sucks by barlevg · · Score: 1

      So your complaint is that " Not every task is trivially parallelizable " and then suggest "GPGPUs" as a solution ?

      Actually, what I said is that, if it's not massively parallelizable, I'd prefer greater clock speed on fewer cores, and if it is, then I'd prefer GPGPUs.

      The Xeon chips used for this machine occupy a very uninteresting "middle ground" in my view.

      The rest of your points are very interesting: I hadn't really thought about the RAM limitations (I use a GPGPU for my own research occasionally but have only once or twice come up against the RAM limits), and non-clockspeed bottlenecks are honestly not something I've come up against, but I do understand that other people have.

    9. Re:That Clock Speed Sucks by pla · · Score: 1

      I really hate how the focus these days is on more cores, not faster cores.

      TFA refers to a supercomputer, not a high-end gaming rig.

      Yes, some problems have a "hard" sequential component, and nothing but "faster" will make a dent in it. We don't really have any options in that realm, however - For a near infinite amount of money, you could conceivably build something 100x faster than the current best commercially available chip - Though in a decade (of which the building of this superchip might take a significant portion to produce), the best commercially available chips will have caught up to that level of performance.

      OTOH, we have no shortage of trivially parallelizable problems of great interest to us today, that we can efficiently tackly by throwing more cheap low-power cores at the problem. Weather, fluid dynamics, protein folding, cortical column simulation - We could realistically keep every von Neumann type CPU humanity produces in the next century busy just on a handful of interesting problems like those.

  38. Re:I need that... by mcgrew · · Score: 0

    let's fix you're spelling frist, then work on the spead of you're posting

    Mod parent funny, I got a chuckle out of that!

  39. it must have a *really* fast boot time by goffster · · Score: 1

    with all those cpus. :)

  40. Finally... by Anonymous Coward · · Score: 1

    Something that can boot Windows 8 in a reasonable amout of time...

  41. More core by Sycraft-fu · · Score: 1

    Xeons are available in 8 and 10 core models (this computer uses the 8 core version) whereas i7s are only 4 and 6 core.

    1. Re:More core by afidel · · Score: 1

      This is a SB Xeon, the ten core models are Westmere based and so get significantly fewer MIPS/Watt (though they have larger cache and more QPI links so they're great for DB work).

      --
      There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
  42. Re:Herzlichen Glückwunsch und by Anonymous Coward · · Score: 0

    Hehe, way to go with Google translate. Nobody would say a sentence like this in german, it sounds pretty weird. The common term for "bitch" is "Schlampe".

  43. Someone had to say it... by cephus440 · · Score: 0

    ... Can you play Doom on it?

    1. Re:Someone had to say it... by cephus440 · · Score: 3, Funny

      I'm glad they didn't use Cyrix CPUs.

    2. Re:Someone had to say it... by zeroryoko1974 · · Score: 0

      No, the video drivers cause the game to crash. Still waiting for a patch

  44. Re:Q: Why are we still on x86 and 64bit and not 12 by Jaywu · · Score: 2

    The 16, 32, 64, 128-bit computing refers to the standard register size for integers and pointers in a processor. Specifically, a 32-bit computer can generally access 2^32 locations of memory, which is 4GB. A "true" 64-bit processor would be able to address 2^64 (18 quintrillian) bytes of memory. However, x86-64 only use 40 bytes for addressing, which will handle 1 TB of RAM. Additionally, doubling the data size makes every operation take significantly longer, so clock speeds have to suffer. Since very few applications actually need 64-bit or higher math functions, its more efficient to implement higher order stuff in software, and have a faster executing processor.

  45. Re:Q: Why are we still on x86 and 64bit and not 12 by Anonymous Coward · · Score: 1

    64 bits are enough to perform any kind of needed computation. More bits would imply larger instructions, larger memory pointers, less usable cache space; basically a waste.

    Just think that now there's a proposal of switching many applications to use 32 bits pointers (on Linux) even if using 64 bits registers, so that more space is available for L1, L2 and L3 cache.

    Hope this helps, cheers

  46. Re:Q: Why are we still on x86 and 64bit and not 12 by six · · Score: 4, Informative

    Don't mix up addressing and computing.

    The whole internet would fit in a 64 bit address space, there is really absolutely no need at all for more than 64 bit for addresses in CPUs, that's why x86_64 and other 64 bit archs are here to stay, and you'll probably never see "128 bit" processors at all.

    On the other side, today's x86_64 CPUs are capable of 128 bit (SSE) and 256 bit (AVX) computing. The width of the compute units is also bound to increase for some time, with Intel already planning to go 1024 bit in the not-so-far future.

  47. I'm Hungry by BetaDays · · Score: 1

    I want a to get a Super Mac.

    --
    Paul: Father... father, the sleeper has awakened! - Dune
  48. Re:All that power... by afidel · · Score: 1

    x86 hasn't been limited to 4GB of ram since the Pentium Pro!

    --
    There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
  49. Re:Q: Why are we still on x86 and 64bit and not 12 by nogginthenog · · Score: 1

    Not always true. The 68000 has 8 x 32bit address and 8 x 32bit data registers, with a 24bit address bus. Nearly all operations can be performed as 32bit. Yet it's reguarded as a 16bit cpu.

  50. Anti-Virus Protection by Dr.Who · · Score: 1

    will consume 50% of the CPU. If they run windows, 80% of the rest will be consumed by DPCs. That leaves 10% for the intended function.

    1. Re:Anti-Virus Protection by MacBurn11 · · Score: 1

      is this supposed to be some kind of trap?

  51. Well? by StripedCow · · Score: 2

    World's Most Powerful x86 Supercomputer Boots Up in Germany

    So, how fast does it boot?

    --
    If Pandora's box is destined to be opened, *I* want to be the one to open it.
  52. Re:Q: Why are we still on x86 and 64bit and not 12 by alexo · · Score: 1

    Not always true. The 68000 has 8 x 32bit address and 8 x 32bit data registers, with a 24bit address bus. Nearly all operations can be performed as 32bit.
    Yet it's reguarded as a 16bit cpu.

    The 68000 had a 16-bit external bus and 32-bit internal architecture.
    It was regarded as a 16/32-bit processor.

  53. Imagine by x181 · · Score: 1

    Imagine a beowulf cluster of SuperMUCs, or a cluster of clusters which would be semantically reduced to just 'cluster'....so just imagine a beowulf cluster.

  54. But.... by ignavus · · Score: 1

    But what sort of video card has it got?

    --
    I am anarch of all I survey.
  55. Why IDataPlex? PureFlex is already out by stenWolf · · Score: 1

    Sure, it takes a while to manufacture the physical components, but they should have switched to a Flex configuration even midway in the installation process - would have saved money in the long run.

  56. No by Anonymous Coward · · Score: 0

    but then neither can any other system, since it requires windows and we all know that it sux badly.

  57. Re:The Super Computer Race is a Sad Scam by Anonymous Coward · · Score: 0

    And yet, everything that you have pointed out, has actually IMPROVED magnitudes due to these large supercomputers. Weather is improving all the time. When I was a kid, getting the weather right just 12 hours ahead was difficult. Back in mid 90's, it was about 2-3 days out. Now, it is roughly 4-5 days out that are pretty decent for the bulk of America and certainly almost all of Europe (not sure of other areas). And I am referring to Colorado front range, which is one of America's worst places to forecast at. Anybody that can do better than 60% here will do better than 90% elsewhere.

  58. Re:x86? good luck with that... by cheesybagel · · Score: 1

    The CPU core is Sandy Bridge so the processor is 64-bit i.e. X86-64. I guess that since you would be hard pressed to find a non 64-bit X86 system today they skipped that bit. This is what used to happen in the past as well. We have had X86-16, X86-32, X86-64 up to now. Besides the addressing space is not of the utmost importance since this is most likely a cluster with message-passing.

  59. Re:I need that... by Anonymous Coward · · Score: 0

    You are easily amused.

  60. Re:Q: Why are we still on x86 and 64bit and not 12 by Anonymous Coward · · Score: 0

    When did "n bit processor" change its meaning from "n bit data" to "n bit address"?

    The 8080 was an 8 bit processor, despite the fact that it had a 16 bit address bus (all addresses were given in 16 bits, unconditionally; you needed two registers to hold an address).

    The 8086 was a 16 bit processor, despite the fact that its addresses were 20 bit (although they were split up into 16 bit chunks by segmentation, so a complete address needed a 16 bit segment and a 16 bit offset to be combined to a 20 bit address).

  61. Re:Q: Why are we still on x86 and 64bit and not 12 by Junta · · Score: 1

    However, x86-64 only use 40 bytes for addressing, which will handle 1 TB of RAM.

    40 *bytes* would be overkill and more than a TB, and 40 bits is outdated information:

    "Current implementations of the AMD64 architecture (starting from AMD 10h microarchitecture) extend this to 48-bit physical addresses[9] and therefore can address up to 256 TB of RAM. The architecture permits extending this to 52 bits in the future"

    So without a new architecture, can hit a petabyte of ram. There are systems with multiple terabytes of ram on a system already (see IBM x3850 x5 for example)

    --
    XML is like violence. If it doesn't solve the problem, use more.
  62. all wrong by Anonymous Coward · · Score: 0

    All comments analysed, you are all wrong.

    SuperMUC

    - this message took less than 1 yoctosecond -

  63. Re:x86? good luck with that... by Anonymous Coward · · Score: 0

    With 155.000 cores and 8 cores per CPU, you'll have 19375 CPUs. Even if every CPU supported only 4GB, that would be a total of about 77 Terabytes. However I'm pretty sure the E5-2680 supports more than 4GB (even when run in 32 bit mode, with PAE, you could address a total of 32 GB per node if every core runs a separate thread (which is very likely since your program will likely run on more than 8 cores [else, why bother to use that supercomputer anyway] and thus cannot be completely mutlithreaded; adding separate multithreading and multiprocessing layers would only add needless complexity).

  64. Re:The Super Computer Race is a Sad Scam by Anonymous Coward · · Score: 0

    So far, computer simulations have not helped us understand or find dark matter

    Here's a map.

    So what is going on? Why haven’t the computer gods delivered? This state of affairs has persisted in the face of colossal increases in available computational power.

    Math is hard!

  65. Power barbecue by Kurast · · Score: 1

    My first reading of the article:
    "1.6-GHz POWER BBQ chips."

    Well, that is some fast barbecue.

  66. Vertical MIPS by servant · · Score: 1

    What is the most powerful 1 processor machine?

    There are problems that many processors can't handle as well as single processors, so I was wondering what is the KingKong of processors.

    Some problems are inherently best handled by many processors (weather, seismic analysis, 3D processing, keeping websites up when having DOS attacks, come to mind) so the many little processors are great. Still I admire the large processor that can crunch more than anything else.

    --
    ... "When you pry the source from my cold dead hands."
  67. More cores is the only way forward. by tempest69 · · Score: 1

    The traces in the chips are 2.5 atoms thick, the distance between traces is 22nm for the most modern production technique, there is some room for squeezing it down a bit more, but there aren't many more significant drops in size that can be made.
    GPGPU has a long way to go to be flexible enough for general purpose work.
    Besides the real push needs to be the push for less power per op, at 1GF/watt, exaflops are a problem.

  68. Re:Q: Why are we still on x86 and 64bit and not 12 by Anonymous Coward · · Score: 0

    Did someone really just make another "this is all the power we will ever need" claim?

  69. Re:x86? good luck with that... by Kaenneth · · Score: 1

    Somebody didn't get the joke.