Slashdot Mirror


Windows Cluster Hits a Petaflop, But Linux Retains Top-5 Spot

Twice a year, Top500.org publishes a list of supercomputing benchmarks from sites around the world; the new results are in. Reader jbrodkin writes "Microsoft says a Windows-based supercomputer has broken the petaflop speed barrier, but the achievement is not being recognized by the group that tracks the world's fastest supercomputers, because the same machine was able to achieve higher speeds using Linux. The Tokyo-based Tsubame 2.0 computer, which uses both Windows and Linux, was ranked fourth in the world in the latest Top 500 supercomputers list. While the computer broke a petaflop with both operating systems, it achieved a faster score with Linux, denying Microsoft its first official petaflop ranking." Also in Top-500 news, reader symbolset writes with word that "the Chinese Tianhe-1A system at the National Supercomputer Center in Tianjin takes the top spot with 2.57 petaflops. Although the US has long held a dominant position in the list things now seem to be shifting, with two of the top spots held by China, one by Japan, and one by the US. In the Operating System Family category Linux continues to consolidate its supercomputing near-monopoly with 91.8% of the systems — up from 91%. High Performance Computing has come a long way quickly. When the list started as a top-10 list in June of 1993 the least powerful system on the list was a Cray Y-MP C916/16526 with 16 cores driving 13.7 RMAX GFLOP/s. This is roughly the performance of a single midrange laptop today."

229 comments

  1. Petaflops per second? by mattventura · · Score: 5, Interesting

    2.57 petaflops per second

    floating point operations per second per second?

    1. Re:Petaflops per second? by Shikaku · · Score: 4, Funny

      I'd say Google datacenters accelerate at about that rate.

    2. Re:Petaflops per second? by DarkKnightRadick · · Score: 0

      Is this an acceleration or computing speed measurement?

      --
      "There is a way that seems right to a man, but its end is the way of death." Proverbs 16:25 (NKJV)
    3. Re:Petaflops per second? by K.+S.+Kyosuke · · Score: 4, Funny

      One petaflop, two petaflops... (Anyway, I didn't know that MS has already shipped so many flops...)

      --
      Ezekiel 23:20
    4. Re:Petaflops per second? by History's+Coming+To · · Score: 3, Interesting

      I can only presume this is a manifestation of Moore's Law, the curve is now so steep the computers are accelerating as they're running. Or maybe a typo ;)

      I'm willing to bet that the top end is going to become less and less relevant and we're going to be judging processors more and more by the "flops-per-watt" and "flops-per-dollar" rating. We're already in a position where clusters of commercial games machines make more sense than a traditional supercomputer for many applications, and I dread to think how much energy could be harvested from these using some efficient heat exchangers.

      --
      Please consider this account deleted, I just can't be bothered with the spam anymore.
    5. Re:Petaflops per second? by Barefoot+Monkey · · Score: 5, Funny

      2.57 petaflops per second

      floating point operations per second per second?

      Well-spotted. It appears that this particular supercomputer gets faster the longer it is left running. Clearly the reason that it ran faster with Linux than with Windows was because in the latter case it needed to be restarted after every Patch Tuesday, thus limiting the potential speed increase to 6.88 zettaflops.

    6. Re:Petaflops per second? by K.+S.+Kyosuke · · Score: 1

      Check the flop in your pants. It's never shipped anything.

      I know for sure that it hasn't, I don't have to check. Given my seasickness, I would immediately notice any attempt at getting into maritime cargo transport business on my flop's part.

      --
      Ezekiel 23:20
    7. Re:Petaflops per second? by zach_the_lizard · · Score: 1

      The Kin and, so far, WP7 have been flops.

      --
      SSC
    8. Re:Petaflops per second? by JAlexoi · · Score: 1

      Yeah! Don't you get it? It's accelerating at that petafloppage!

    9. Re:Petaflops per second? by Anonymous Coward · · Score: 0

      I like this one too:

      Windows Cluster Hits a Petaflop

      rofl

    10. Re:Petaflops per second? by Flytrap · · Score: 1

      I'm not sure that Google's data centres could qualify as a single super computer with each node solving a different part of the same problem...

    11. Re:Petaflops per second? by jimrthy · · Score: 1

      That sig's awesome.

    12. Re:Petaflops per second? by shogun · · Score: 3, Funny

      I'm not sure that Google's data centres could qualify as a single super computer with each node solving a different part of the same problem...

      World domination isn't a single problem?

    13. Re:Petaflops per second? by cheater512 · · Score: 1

      Erm...yes thats how clusters work. Its not possible to build a single machine fast enough to solve many problems.

    14. Re:Petaflops per second? by Mitchell314 · · Score: 1

      No, there are many, many, many aspects to trying to take over the world. Trust me, 80% of it is middle management work (henchman pay-scale management alone is 20%. They kept on bugging me about wanting a better retirement plan).

      --
      I read TFA and all I got was this lousy cookie
    15. Re:Petaflops per second? by mug+funky · · Score: 1

      retirement?

      that's not how it works with henchmen.

    16. Re:Petaflops per second? by Anonymous Coward · · Score: 0

      I wouldn't consider my world domination as a problem, no.

    17. Re:Petaflops per second? by Kjella · · Score: 1

      thus limiting the potential speed increase to 6.88 zettaflops.

      If it could become a million times faster by installing Windows, there's something very very wrong with the world.

      --
      Live today, because you never know what tomorrow brings
    18. Re:Petaflops per second? by oliverthered · · Score: 1

      it's a solitary pursuit,
      you'll know when I'm done.

      --
      thank God the internet isn't a human right.
    19. Re:Petaflops per second? by ozmanjusri · · Score: 1
      I don't think they've ever shipped a flop based on their sales.

      Not the sales they're reporting at least.

      http://www.informationweek.com/news/software/operatingsystems/showArticle.jhtml;jsessionid=4XPMLS5U3OEIRQE1GHRSKH4ATMY32JVN?articleID=228200850&pgno=2&queryText=&isPrev=

      Microsoft's most recent Windows sales totals got a boost from the fact the company quietly added revenues it previously assigned to other groups to its operating systems unit, a bit of accounting legerdemain that, along with other bookkeeping moves, helped the Windows group post big gains in the past quarter,

      Windows sales from the OEM channel, which account for 75% of all Windows sales, increased just 11% year-over-year when the deferral program is considered. Not bad, but it's pretty much in line with most estimates for overall PC market growth during the period, including Microsoft's own.

      To boot, data from market watcher Net Applications shows Windows has actually lost more than 1% of market share since last December, though it still commands more than 91% of the PC OS market.

      Microsoft is running scared and cooking their books. Ballmer knows - he's dumping 30% of his Microsoft shares.

      They're heading for an Enron for sure...

      --
      "I've got more toys than Teruhisa Kitahara."
    20. Re:Petaflops per second? by evilviper · · Score: 1

      2.57 petaflops per second

      floating point operations per second per second?

      "What is: the speed of a supercomputer falling off a cliff?"

      Trebeck: "That's correct. You select next."

      "I'll take: 'Bad jokes' for 1,000, Alex."

      --
      Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
    21. Re:Petaflops per second? by Datamonstar · · Score: 1

      Well just about anything is better than a swift knife in the back.

      --
      The eternal struggle of good vs. evil begins within one's self.
    22. Re:Petaflops per second? by RocketRabbit · · Score: 1

      Typos are accidental, this is just the result of ignorance.

    23. Re:Petaflops per second? by aiht · · Score: 1

      I second that!

    24. Re:Petaflops per second? by Burpmaster · · Score: 1
    25. Re:Petaflops per second? by PseudonymousBraveguy · · Score: 1

      Even though that acceleration seems increddibly fast, Moores Law proposes an exponential acceleration* that will outgrow that acceleration by far. (That's also the reason why Moores law will fail at some point.)

      *Actually he never talked about speed but number of transistors, but that's sufficiently correlated ;-)

    26. Re:Petaflops per second? by ultranova · · Score: 1

      It appears that this particular supercomputer gets faster the longer it is left running.

      You got modded funny, but isn't this a property of many JIT systems: they can profile and recompile parts of programs on the fly? And, for that matter, a cluster could set aside some computing power to analyze itself and optimize (by changing message priorities, moving subtasks from one node to another, etc) for the task at hand.

      --

      Forget magic. Any technology distinguishable from divine power is insufficiently advanced.

    27. Re:Petaflops per second? by Chrisq · · Score: 1

      2.57 petaflops per second

      floating point operations per second per second?

      If that's the ramp-up speed I'm impressed

    28. Re:Petaflops per second? by tehcyder · · Score: 1

      To boot, data from market watcher Net Applications shows Windows has actually lost more than 1% of market share since last December, though it still commands more than 91% of the PC OS market.

      They're heading for an Enron for sure...

      I don't think a company with more than 91% market share is about to go tits up any time soon.

      --
      To have a right to do a thing is not at all the same as to be right in doing it
    29. Re:Petaflops per second? by uninformedLuddite · · Score: 1

      and then they built the super collider

      --
      The new right fascists are bilingual. They speak English and Bullshit.
    30. Re:Petaflops per second? by nashv · · Score: 1

      And since its Google, its not by increasing the numerator of that fraction either. Relativity comes in handy eh?

      --
      Entia non sunt multiplicanda praeter necessitatem.
  2. Nevertheless I am impressed by Anonymous Coward · · Score: 1, Interesting

    I am impressed that Windows can actually scale to that type of hardware. However, my questions are:

      - What kind of performance can an actual program achieve on Windows on that hardware?
      - Are context switches from godawful slow memory allocation calls as painfully slow on this supercomputer as they are on the typical desktop?
      - How badly does the ever-essential anti-malware suite drag down the supercomputer?

    1. Re:Nevertheless I am impressed by bmo · · Score: 2, Interesting

      - What kind of performance can an actual program achieve on Windows on that hardware?

      Less than on Linux, and that's what counts in the end, isn't it?

      Coupled with the fact that licenses eat into the budget a significant amount, Windows TCO is not the bargain that Microsoft would like you to believe.

      --
      BMO

    2. Re:Nevertheless I am impressed by gmack · · Score: 2, Informative

      I am impressed that Windows can actually scale to that type of hardware. However, my questions are:

        - What kind of performance can an actual program achieve on Windows on that hardware?

      Fairly good if the programmer is skilled at writing super computer applications.

      - Are context switches from godawful slow memory allocation calls as painfully slow on this supercomputer as they are on the typical desktop?

      It shouldn't matter too much since they would (mostly) avoid context switches by only running 1 copy of the software per core and half of windows is disabled in Super Computing edition.

      - How badly does the ever-essential anti-malware suite drag down the supercomputer?

      Shouldn't be needed since it should be extremely hard for malware to get into such a controlled environment to begin with.

      There are other reasons Microsoft's idea is a bad one such as the higher licensing costs, no possible reason to want to write custom, non GUI software from scratch on Windows etc.

    3. Re:Nevertheless I am impressed by Noughmad · · Score: 2, Funny

      - How badly does the ever-essential anti-malware suite drag down the supercomputer?

      Shouldn't be needed since it should be extremely hard for malware to get into such a controlled environment to begin with.

      Digital Fortress?

      --
      PlusFive Slashdot reader for Android. Can post comments.
    4. Re:Nevertheless I am impressed by ozmanjusri · · Score: 1
      What kind of performance can an actual program achieve on Windows on that hardware?

      Not much, but Vista is reasonably snappy.

      --
      "I've got more toys than Teruhisa Kitahara."
    5. Re:Nevertheless I am impressed by bertok · · Score: 2, Insightful

      no possible reason to want to write custom, non GUI software from scratch on Windows

      That's a bit excessive! It does have some nice things going for it, including a fairly nice API that's been binary and source compatible for decades. There's end-to-end Unicode support in all APIs, a nice event logging and tracing system, a nice performance monitoring system (WMI), various asynchronous file and socket APIs, including advanced copy-less APIs that can tie TCP streams to specific CPU cores, etc...

      Unlike Linux, Windows has a built-in volume snapshot system that supports application quiescing (not just cache flushing), exportable snapshots, advanced access-list support that is standard and consistent, etc...

      Really, the biggest issue with Windows is that the source is closed, so if you need something special for a cluster, you're out of luck. "patch tuesday" is only an issue on networks which are not controlled, and a supercomputer would use a dedicated, isolated network.

    6. Re:Nevertheless I am impressed by gmack · · Score: 1

      - How badly does the ever-essential anti-malware suite drag down the supercomputer?

      Shouldn't be needed since it should be extremely hard for malware to get into such a controlled environment to begin with.

      Digital Fortress?

      Machines only connect to their internal network and only run either Microsoft or in house apps?
      To top it off the cluster edition of windows has pretty much all services not even installed in the first place lat alone running so few open ports even if something did make it into the network.

    7. Re:Nevertheless I am impressed by macshit · · Score: 1

      There are other reasons Microsoft's idea is a bad one such as the higher licensing costs, no possible reason to want to write custom, non GUI software from scratch on Windows etc.

      From Microsoft's point of view, it's good, as it allows them to test/prove their algorithms, etc; presumably scalability will be useful for future consumer-level hardware.

      For the supercomputer user/developer though, there seems to be utterly no point to running windows -- pretty much all of window's strengths (consumer familiarity, driver availability, availability of mainstream apps, widespread support) are irrelevant for that class of hardware/application -- and there are many negatives to doing so (licensing/legal restrictions, cost, excessive GUI dependency, difficulty of customization, lack of commonality with other supercomputer-relevant apps/libraries/users, etc).

      I suppose the actual reason is that MS is throwing buckets of money at them... boot windows a few times, and pay half your staffs' salaries for a year...

      --
      We live, as we dream -- alone....
    8. Re:Nevertheless I am impressed by imakemusic · · Score: 1

      - Can it run Crysis?

      --
      Brain surgery - it's not rocket science!
    9. Re:Nevertheless I am impressed by ookaze · · Score: 1

      That's a bit excessive! It does have some nice things going for it, including a fairly nice API that's been binary and source compatible for decades.

      This is no advantage in this case as there are decades old API which are nicer, standard, and as a bonus have open implementation (like MPI).

      There's end-to-end Unicode support in all APIs, a nice event logging and tracing system, a nice performance monitoring system (WMI), various asynchronous file and socket APIs, including advanced copy-less APIs that can tie TCP streams to specific CPU cores, etc...

      All of which are pretty much useless in HPC, and when they are useful, they're already there in better form on Linux. A nice event logging and tracing system, really? When people want maximum computing efficiency, they don't want all that.

      Unlike Linux, Windows has a built-in volume snapshot system that supports application quiescing (not just cache flushing), exportable snapshots, advanced access-list support that is standard and consistent, etc...

      All of which are useless in a cluster. If Windows snapshots are exportable to Linux LVM, this is a good thing. The same if Windows ACL support is standard with the POSIX ones, or at least the one in Linux.
      I didn't know that, but at the same time who cares?

      Really, the biggest issue with Windows is that the source is closed, so if you need something special for a cluster, you're out of luck. "patch tuesday" is only an issue on networks which are not controlled, and a supercomputer would use a dedicated, isolated network.

      Which is nonsense because a FS like Lustre is still updated constantly, and often need tweaking to a particular hardware.
      And no, the biggest issue with Windows is its efficiency. It's one of the worst ones in the Tsubame 2.0 system at Rmax being 52 % of the Rpeak. In part due to the use of GPU, but still. Even the first on the top 500, that also uses GPU, is at 54 %. Linux can go in efficiency to as high as 87 % and more.

    10. Re:Nevertheless I am impressed by Anonymous Coward · · Score: 0

      As someone who has written things to run in the nodes of big boxen; I had trouble figuring out when those nicities would have been useful. Uicode -- no -- GCTA fit in nibbles or bits just fine w/o Unicode; go fast doesn't give you much time for a monstrous even logger, it's easy to lose a lot of performance in performance monitoring, would prefer TCP to be offloaded into hardware -- besides real men don't use tcpip inside a cluster for tightly coupled questions, not sure why I want my nodes to be doing things with a file system other than read the executable and start running. I guess the point is that you suggest overhead which is not necessary as a good thing.

    11. Re:Nevertheless I am impressed by jd · · Score: 1

      Depends on which Windows. It will boot up Vista, though, and I believe they got a copy of Notepad fired up.

      --
      It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
    12. Re:Nevertheless I am impressed by Yfrwlf · · Score: 1

      This is what I don't understand about any of this. If they deny Windows from being recognized on this specific supercomputer due to the fact Linux is faster on it, Windows most likely needs to be removed from ALL of the supercomputers on the list due to the same reason that Linux would most likely be faster if it were installed. The moral of the story: you can remove Windows from being recognized at all by having them simply "try out" Linux. Everyone, mail live Linux for Supercomputers CDs/thumbdrives to the locations of the remaining Windows supercomputers!!!

      --
      Promote true freedom - support standards and interoperability.
  3. US becoming less superpowery by Oxford_Comma_Lover · · Score: 1

    > Although the US has long held a dominant position in the list things now seem to be shifting, with two of the top spots held by China, one by Japan, and one by the US.

    Damn, I feel like Britain after WW2.

    Hey, does this mean US accents are going to seem sexy soon?

    --
    -- IANAL, this isn't legal advice, and definitely isn't legal advice for you. Also, Squee!
    1. Re:US becoming less superpowery by bsDaemon · · Score: 2, Informative

      Yeah, but on the downside, it means that asian chicks are going to start gaining weight and wanting to be "liberated" and stuff, so your sexy accent isn't really going to pay off.

    2. Re:US becoming less superpowery by hedwards · · Score: 1

      This was bound to happen eventually. But the process was accelerated by the right wing and the American exceptionalists who are completely unable to acknowledge when we need a course correction.

    3. Re:US becoming less superpowery by Anonymous Coward · · Score: 0

      Still the superpower in Lardarse-ery and Parochialism. No contest there.

    4. Re:US becoming less superpowery by zach_the_lizard · · Score: 1

      Way to bring politics into a thread about supercomputers!

      Now, to politics.... Being a fan of neither large party, I can smugly sit here and point out both of the sides' failings while you and the inevitable others argue which of the two sides is unfit to rule. Sadly, both sides have me convinced the other side sucks.

      --
      SSC
    5. Re:US becoming less superpowery by jellomizer · · Score: 1

      Really I thought it was accelerated by the left wing and those environmentalists who say that all new technology is bad and evil, and unwilling to see that life is about balance.

      Or...

      It could be that China is a country that has the highest population and its new free(er) market economy allows to better utilize its human capital and brain power. As well they are in a culture where when they are competing they will try to win at all costs even in spite of them selfs. While in the US we try hard to win but on a longer term.

      --
      If something is so important that you feel the need to post it on the internet... It probably isn't that important.
    6. Re:US becoming less superpowery by kramulous · · Score: 1

      Don't worry, the Americans are working on the next one: 10 petaflops

      Here's hoping I get to work on it :)

      --
      .
    7. Re:US becoming less superpowery by tehcyder · · Score: 1

      Damn, I feel like Britain after WW2.

      Considering their diets and eating habits, I'm not sure they know the war is over.

      It's always good to be lectured about diet by a three hundred pound American (taking a wild guess) and as for eating habits, at least in the UK we can use a fucking knife and fork simultaneously.

      --
      To have a right to do a thing is not at all the same as to be right in doing it
  4. About hardware, not operating systems by noidentity · · Score: 1

    Isn't this about hardware, not operating systems (other than the OS being able to support the hardware)? And isn't the hardware simply about how much money you have to throw at it?

    1. Re:About hardware, not operating systems by rrossman2 · · Score: 1

      Well, it says the hardware ran linux at X speed, and windows at less than X speed...

    2. Re:About hardware, not operating systems by gmuslera · · Score: 1

      That in the same hardware Linux was faster than Windows is about operating systems.

    3. Re:About hardware, not operating systems by betterunixthanunix · · Score: 1

      Isn't this about hardware, not operating systems (other than the OS being able to support the hardware)?

      No, it is about two operating systems on the same hardware, one of which (GNU/Linux) outperforming the other (Windows).

      And isn't the hardware simply about how much money you have to throw at it?

      No, it is also about the architectural choices.

      --
      Palm trees and 8
    4. Re:About hardware, not operating systems by hey! · · Score: 3, Insightful

      Well, it says the hardware ran linux at X speed, and windows at less than X speed...

      Actually the article doesn't say that. The hardware was different: the Linux configuration had more nodes than the Windows configuration. This *might* have been for some technical reason, or it might have been for some extraneous reason (e.g., they have better things to do with this beast than run benchmarks on it).

      In any case, the difference between the Windows and Linux scores was for practical purposes insignificant. It was a *benchmark*, not a real computation. Even if the benchmark is pretty good, the mix of resources used by a real program won't match it exactly (e.g. an app that uses less floating point calculations but more memory allocations might see a very different result).

      Microsoft's aim is not to run on research clusters, but to make inroads into businesses that have in-house Windows system administration and programming capabilities and might have use for high performance computing. If so, the linpack benchmark is probably close to irrelevant for many applications.

      --
      Post may contain irony: discontinue use if experiencing mood swings, nausea or elevated blood pressure.
    5. Re:About hardware, not operating systems by jedidiah · · Score: 2, Insightful

      Well... "being able to run more nodes" is also a function of software. It's called scalability.

      Being able to throw more nodes at a problem would certainly be a "feature" for HPC.

      --
      A Pirate and a Puritan look the same on a balance sheet.
    6. Re:About hardware, not operating systems by LurkerXXX · · Score: 2, Insightful

      From TFA: "I'm not sure why the tests were run on a different number of nodes".

      No one anywhere, except in your imagination, said Windows wasn't *able* to run on the extra nodes.

    7. Re:About hardware, not operating systems by KarmaMB84 · · Score: 2, Insightful

      They didn't run the Windows benchmark with all available nodes. I'd assume they didn't have licenses for every node but the researchers made it sound like they had some sort of nerdgasm because the machine could benchmark running Windows on par with Linux (only a 5% margin on a smaller cluster).

    8. Re:About hardware, not operating systems by spisska · · Score: 2, Funny

      No one anywhere, except in your imagination, said Windows wasn't *able* to run on the extra nodes.

      I figure it was because the testers couldn't afford the licensing fees.

    9. Re:About hardware, not operating systems by f3rret · · Score: 2, Interesting

      Isn't this about hardware, not operating systems (other than the OS being able to support the hardware)?

      No, it is about two operating systems on the same hardware, one of which (GNU/Linux) outperforming the other (Windows).

      And isn't the hardware simply about how much money you have to throw at it?

      No, it is also about the architectural choices.

      Architectural choices are irrelevant if you don't have the funding to realize them.

      If you can't afford the hardware to your fancy supercomputer, you can make the best possible choices in the word, but you're still not getting a supercomputer.

      --
      Admit nothing. Deny Everything. Make Counter-accusations.
    10. Re:About hardware, not operating systems by gmack · · Score: 1

      Microsoft's aim is not to run on research clusters, but to make inroads into businesses that have in-house Windows system administration and programming capabilities and might have use for high performance computing. If so, the linpack benchmark is probably close to irrelevant for many applications.

      It's not a smart aim. Programmers who make clustered apps are a different skill set from the programmers who make most of the software out there and if your average programmer attempts it the result will not scale no matter what resources you throw at the project and this is on top of the fact that only a subset of software problems are suited to clustering to begin with.

      I'm going to go out on a limb and suggest that even in the Linux case the benchmark scales better than most software that will run on a cluster.

      Once you have the rare sort of programmer who can do this and the rare sort of software problem that needs it there is nothing at all that will make windows at all familiar since the rest of the supercomputing market runs on Unix/Linux.

    11. Re:About hardware, not operating systems by betterunixthanunix · · Score: 1

      However, if you have the money, architectural choices make a big difference. There is a reason why you do not see many shared memory machines these days, why Ethernet is usually not the network of course for clusters, etc.

      --
      Palm trees and 8
    12. Re:About hardware, not operating systems by Vanders · · Score: 1

      Ethernet is usually not the network of course for clusters

      Come again?

      I don't disagree that Ethernet is not the *best performing* interconnect, but on a price/performance basis it clearly isn't losing the battle.

    13. Re:About hardware, not operating systems by marcello_dl · · Score: 1

      >The hardware was different: the Linux configuration had more nodes than the Windows configuration.

        I RTFA but that claim is not confirmed.
      Anyway if they wanted to test linux vs windows they would have run on the same n. of nodes disabling linux ones. Pretty strange they did not, maybe some NDA or some phb which needs a case for
        win deployment?

      --
      ---- MISSING MISCELLANEOUS DATA SEGMENT --- [sigdash] trolololol
    14. Re:About hardware, not operating systems by LurkerXXX · · Score: 2, Insightful

      And you know for a fact that they hadn't added nodes to the cluster between when they ran it on windows and on linux, or that some nodes weren't down for service or other maintenance, moving, or a million other potential reasons?

      I don't pretend to know why when I don't. You pretend to know why when you don't.

    15. Re:About hardware, not operating systems by Anonymous Coward · · Score: 0

      The hardware was different: the Linux configuration had more nodes than the Windows configuration. This *might* have been for some technical reason

      That's because Windows is limited to 640 nodes. Nobody will ever need more.

    16. Re:About hardware, not operating systems by jedidiah · · Score: 1

      No. You just like engaging in self-serving wishful thinking.

      --
      A Pirate and a Puritan look the same on a balance sheet.
    17. Re:About hardware, not operating systems by LurkerXXX · · Score: 1

      Wishful thinking? What am I wishing, other than that other posters wouldn't make information?

    18. Re:About hardware, not operating systems by LurkerXXX · · Score: 1

      Make *up* information. Sigh, I hate it when I miss the preview button.

  5. Dual boots? by backslashdot · · Score: 3, Funny

    So it dual boots? press the option key or something to get into Windows and play Crysis?

    1. Re:Dual boots? by zlogic · · Score: 1

      This machine is probable capable of playing Crysis with a framerate higher that 20fps

    2. Re:Dual boots? by Nidi62 · · Score: 1

      You assume even this computer is powerful enough to play Crisis on anything other than low settings.

      --
      The only thing necessary for evil to triumph is for it to be pitted against a slightly greater evil
  6. Trying too hard to be pedantic by symbolset · · Score: 0, Troll

    FLoating point OPerationS per second. Now if you'll excuse me I need to go to the ATM machine if I can remember my PIN number.

    --
    Help stamp out iliturcy.
    1. Re:Trying too hard to be pedantic by X0563511 · · Score: 0

      The unit is "flop" - the s indicates plurality - you don't say 1.2 petaflops, you say 1.2 petaflop (vs 2.2 petaflops).

      It works the same way as a hertz.

      --
      For large sets, this will be our guide even unto death, for the LORD will work for each type of data it is applied to...
    2. Re:Trying too hard to be pedantic by Anonymous Coward · · Score: 1, Funny

      Ooooh, that hertz!

    3. Re:Trying too hard to be pedantic by Kilrah_il · · Score: 2, Informative

      Actually, flops means exactly what the OP said: Floating point operations per second.

      --
      Whenever in an argument, remember this.
    4. Re:Trying too hard to be pedantic by Anonymous Coward · · Score: 0

      No, the s indicates seconds...

    5. Re:Trying too hard to be pedantic by FrootLoops · · Score: 1

      Both flop and flops are acronyms, meaning either "FLoating-point OPeration" or "FLoating point OPerations per Second". The summary uses the former.

      Since ignoring the words "per second" is unambiguous, I'd say it's mildly incorrect. Since this whole discussion takes the focus off the content (...a near record-breaking Windows cluster...), I'd say it's quite incorrect.

    6. Re:Trying too hard to be pedantic by nashv · · Score: 1

      Fail. S= second in FlOPS

      --
      Entia non sunt multiplicanda praeter necessitatem.
  7. Re:Won't somebody please think of the licensing co by Peach+Rings · · Score: 1

    Linux isn't exactly an ultrascalable high-performance OS either. If you were building a supercomputer operating system from the start you'd make very different design decisions than Linus did.

  8. Interesting by quo_vadis · · Score: 2, Insightful

    It is interesting that there are 6 new entrants in the top 10. Even more interesting is the fact that GPGPU accelerated supercomputers are clearly outclassing classical supercomputers such as Cray. I suspect we might be seeing something like a paradigm shift, such as when people moved from custom interconnect to GbE and infiniband. Or when custom processors began to be replaced by Commercial Off The Shelf processors.

    --
    Legally obligatory sig : My opinions are my own... etc etc
    1. Re:Interesting by alexhs · · Score: 3, Informative

      Even more interesting is the fact that GPGPU accelerated supercomputers are clearly outclassing classical supercomputers such as Cray

      Funny that you mention Cray, as the Cray-1 was the first supercomputer with vector processors, what GPGPUs actually are.

      --
      I have discovered a truly marvelous proof of killer sig, which this margin is too narrow to contain.
    2. Re:Interesting by vlm · · Score: 1

      Funny that you mention Cray, as the Cray-1 was the first supercomputer with vector processors, what GPGPUs actually are.

      Cray-1 date of birth 1976

      CDC Star-100 date of birth 1974 (not a stellar business/economic/PR success, but it technically worked)

      ILLIAC IV design was completed in 1966. Implementation, however, had some problems. Debatable, but sort of true to say it was first booted up in 1972 but wasn't completely debugged for a couple years. As if there has ever been a completely debugged system.

      Thats the problem with "first", theres so many of them.

      --
      "Science flies us to the moon. Religion flies us into buildings." - Victor Stenger
    3. Re:Interesting by Sycraft-fu · · Score: 1

      Well part of the problem is that the definition of supercomptuer has become a little blurred, in particular with regards to the top500. Many things people are calling supercomputers really aren't, they are clusters. Now big clusters are fine, there are plenty of uses for them. However there are problems that they are not good at solving. In clusters, processors don't have access to memory on other nodes, they have to send over the data. So long as things are pretty independent, you can break down the problem and work on small sets without a ton of communication they work great. However for some things, like particle simulations, that doesn't work. There is so much interdependency that processors really have to be able to access memory not on their node to be able to keep things working fast.

      Then there's just the problem of what you choose to test with. GPUs are good at certain kinds of problems. Things that are 32-bit floating point (64-bit with the very latest GPUs), that can be divided down in to very small slices, that don't branch a lot and when a branch does happen, everything branches the same way, and where you can fit the problem set (or at least the part you are working on) in to the GPU's memory which is generally 1-4GB. That's fine, lot of problems are like that and they fly on GPUs. However others aren't, and they are much slower than CPUs. So GPGPU systems will appear powerful given some benchmarks, not as powerful given others.

      At any rate we just should be more careful with what we call a supercomputer because we are kind diluting the term. 2000 servers connected with GigE is a hell of a lot of processing power and a great cluster, but isn't really a super computer. There are reasons why some people need to pay more for special systems with high speed NUMA interconnects. Just because a cluster performs well on Linpack (what the top500 likes) doesn't mean it is good at everything.

    4. Re:Interesting by antifoidulus · · Score: 1

      Vector processors in supercomputing are like bellbottoms, they constantly go in and out of style. Like you said the first supercomputers were vector machines, but then with the rise of cots vector processors fell out of style for a while, came back briefly with the earth simulator, and now is back with the gpu. Unlike previous vector processors gpus have a lot more restrictions(ESP when it comes to memory bandwidth and latency), but also unlike previous vector processors gpus are dirt cheap an d developmen can essentially be outsourced to the gpu manufacturers.

    5. Re:Interesting by symbolset · · Score: 1

      It doesn't explicitly say, because the interconnect is proprietary. But with Infiniband the nodes can address the RAM on the other nodes. I would assume this to be the case here also.

      --
      Help stamp out iliturcy.
    6. Re:Interesting by alexhs · · Score: 1

      I went by "The vector technique was first fully exploited in the famous Cray-1" from the wikipedia :)

      Apparently the difference between the CDC Star-100 and the Cray-1 is the adressing mode : Star-100 fetched and stored data in main memory while the Cray-1 had 64 64-bit registers.

      On the account of ILLIAC IV, Wikipedia says it "was finally ready for operation in 1976". It booted in 1972, but wasn't reliable enough to run applications at that time. It was usable in 1975, operating only Monday to Friday and having up to 40 hours of planned maintenance a week.

      --
      I have discovered a truly marvelous proof of killer sig, which this margin is too narrow to contain.
    7. Re:Interesting by evilviper · · Score: 1

      Even more interesting is the fact that GPGPU accelerated supercomputers are clearly outclassing classical supercomputers such as Cray. I suspect we might be seeing something like a paradigm shift, such as when people moved from custom interconnect to GbE and infiniband. Or when custom processors began to be replaced by Commercial Off The Shelf processors.

      Nope. GPUs are just today's version of the FPUs in the 90s. Right now, they're a feature omitted in most systems, with software emulation taking up the slack but at a performance penalty. In newer and higher-end system, they're available as an add-on that can be coupled with the CPU, though the system can run fine without it for those who wish to omit it. And soon, all systems will come with it integrated right into the CPU silicon, just another footnote as to why your CPU die has to be so large...

      This doesn't bode well for embedded CPUs, of course. They weren't taken seriously in the high-end due to missing FPUs for over a decade, while all non-embedded processors had them. And with GPUs, AMD is quite far down the road of integration. Intel has enough money to play catch-up without anyone really noticing they missed a beat. But embedded CPU designers like ARM aren't even in the ballpark, and could well fall behind and stay behind for the next decade just as soon as the benefits of a CPU-GPU are realized by mainstream software. It looks a whole lot like history repeating.

      --
      Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
    8. Re:Interesting by Jeremy+Erwin · · Score: 1

      Your nostalgia is showing. The latest Crays don't immerse their boards in flouronert. They aren't hand connected by teams of unusually small weavers. They don't use chips clocked ten times faster than anyone else's. They aren't physically small. They do, however, have nifty interconnects-- which probably explains why Jaguar is 75% efficient, and Tianhe-1A is 54% efficient.

    9. Re:Interesting by walshy007 · · Score: 1

      You will NOT be seeing a gtx480 equivalent in your cpu die any time soon.

      From a thermal and 'oh dear god so many transistors' perspective it's pretty much impossible since as process improvements occur the gpu's just use more transistors to suit.

      Fpu's were a drop in the bucket compare to modern decent gpu's

    10. Re:Interesting by Anonymous Coward · · Score: 0

      Furthermore, the CDC-6600 was touted as the first "supercomputer." And predated the Cray-1 by a good decade.

    11. Re:Interesting by evilviper · · Score: 1

      You will NOT be seeing a gtx480 equivalent in your cpu die any time soon.

      No you won't. AMD's original idea was to have an SMP motherboard, with an Opteron in one socket, and a GPU in another. This would be eminently doable with a GTX 480, and anything else you can name. FPUs had their own sockets to start with, too.

      These days, having a GPU as a seperate core on a chip would be the expected way to go, and there's no reason that couldn't happen. Sure, it's a lot of transistors, but with entirely separate dies glued together, it really doesn't matter. Power consumption would be more of a problem, so your 480 will have to get a die shrink or two first.

      In the end, after several years, it'll end up in the die, though. Yes, the transistor count on CPUs will grow faster than GPUs, until it won't be so big of a leap. We're obviously not there yet, but we're headed that direction.

      --
      Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
    12. Re:Interesting by walshy007 · · Score: 1

      Yes, the transistor count on CPUs will grow faster than GPUs, until it won't be so big of a leap. We're obviously not there yet, but we're headed that direction.

      You're kidding right, all process shrinks will due is enable gpu makers to use MORE transistors to themselves, and gpu's have been growing in transistor count relative to cpu's for quite some time.

      but with entirely separate dies glued together, it really doesn't matter.

      so, assuming you're going to stick a modern six core die to a 480 die, would you care to explain how you are going to dissipate enough heat before they fry eachother from being in such close proximity?

      There is enough trouble cooling the gpu alone in the high end, what with their up to 200 watt thermal dissipation these days. Adding a second heavy heat creating part right next to it is begging for trouble.

      Your mistake is you think advances in process won't be used to make better gpu's, they will.

    13. Re:Interesting by Anonymous Coward · · Score: 0

      GPUs aren't vector processors, not by far. Similarly to vector processors they are rather more throughput than latency oriented, but their speedup comes from massive parallelism, not from massive pipelining like for vector processors (pipelining is of course a form of parallelism as well, but it is inside a single instruction).
      Also vector processors (usually) also have scalar units to provide low-latency operations, a GPU doesn't provide _any_ low-latency operation at all, which is one if the reasons you will never want to use it without an general-purpose CPU in addition.

    14. Re:Interesting by Anonymous Coward · · Score: 0

      > These days, having a GPU as a seperate core on a chip would be the expected way to go, and there's no reason that couldn't happen.

      Yes there is (for high-performance use-cases): You can't have a memory connection that is both very low latency and very high bandwidth.
      CPUs need low latency, GPUs need high bandwidth.
      If you put both on one die, you're already compromising on performance.
      Both on one die may be convenient, for some corner-case uses it may even provide better performance, but it will cost a lot for those cases where GPUs are currently _massively_ faster.

    15. Re:Interesting by David+Greene · · Score: 1

      such as when people moved from custom interconnect to GbE and infiniband.

      We haven't. The top two machines use custom interconnect. Big machines that run non-embarrassingly-parallel codes (i.e. not the one measuring for TOP500) still use custom interconnect.

      But you're right, we are seeing a paradigm shift. It's called hybrid computing and has been on the radar for several years. We used to do this stuff back when Burroughs and others were still in business. A GPU is "just" a vector processor, after all. What's old is new again.

      --

    16. Re:Interesting by David+Greene · · Score: 1

      The massive parallelism comes from SIMD programming, so it is a vector machine. NVidea made up the "SIMT" term so people would think it's something new. It isn't. In fact the programming model would be much less confusing if CUDA didn't try to present the vector processor as a collection of scalar threads. Then all the silliness around "divergence" would go away.

      If it looks like a vector machine and is programmed like a vector machine, it is a vector machine.

      --

    17. Re:Interesting by David+Greene · · Score: 1

      You can't have a memory connection that is both very low latency and very high bandwidth.

      Why not? Bandwidth is simply data / latency + some pipelining effects. Drop the latency and the bandwidth goes up, generally. To put it another way, bandwidth is simply data / time between packets. Latency determines the depth of the pipeline.

      Both on one die may be convenient, for some corner-case uses it may even provide better performance

      All things being equal, an on-die GPU/coprocessor has huge advantages in bandwidth between the host and device. That covers a lot more than corner cases. CPU designers are running out of ways to use more transistors. Bigger caches only buy you so much until you hit diminishing returns. Specialized processor cores are the obvious next thing to do.

      --

    18. Re:Interesting by David+Greene · · Score: 1

      You will NOT be seeing a gtx480 equivalent in your cpu die any time soon.

      Don't be so sure. I'm just speculating, but cramming more threads into a GPU will only go so far. Right now one of the biggest bottlenecks is the PCIe bus. Moving the GPU on die gets rid of that entirely. I could certainly see an on-die gtx480-like coprocessor happening relatively soon. I'll bet the NVidea people sweat about this every day. It will be interesting to see how they maintain market share as more stuff gets integrated on-die.

      --

    19. Re:Interesting by walshy007 · · Score: 1

      Don't be so sure. I'm just speculating, but cramming more threads into a GPU will only go so far

      gpu's are far more parallel than cpus. While I'm sure diminishing returns could be reached, they are orders of magnitude more threads than what we have now. GPU dies are already significantly larger in size and transistor count than most cpus.

      Right now one of the biggest bottlenecks is the PCIe bus.

      The moment you have enough graphic card memory to store all texures/fragment programs/geometry you significantly lower the amount of traffic going over the pcie bus.

      I'll bet the nVidia people sweat about this every day.

      The only threat integrated graphics are to them is the low end of the low end. Which while is one of the largest markets, intel has had that market down pat for ages with it's crappy integrated chipsets. So no real loss.

      I could certainly see an on-die gtx480-like coprocessor happening relatively soon.

      Sure lets just triple the cpu transistor count (not that that is going to make the die so large latency suffers) and completely ignore all thermal properties so the chips fry themselves.. oh and manufacturing costs go through the roof. Smart.

      You cannot put a top of the line gpu in a cpu, you sacrifice too much of both and wind up making both a crappy cpu and gpu.

    20. Re:Interesting by David+Greene · · Score: 1

      gpu's are far more parallel than cpus.

      The hardware isn't the issue, it's the software. It becomes very difficult to use so many threads on most workloads. For graphics, sure, but one of the trends with these things is to use them as general accelerators.

      The moment you have enough graphic card memory to store all texures/fragment programs/geometry you significantly lower the amount of traffic going over the pcie bus.

      I don't think you'll ever have enough memory. We've demonstrated that repeatedly. And again, for general processing it's not feasible to preload everything into device memory.

      You cannot put a top of the line gpu in a cpu, you sacrifice too much of both and wind up making both a crappy cpu and gpu.

      You know this with absolute certainty? You are absolutely sure we'll never have the technology to do it? I'll take that bet against you in a heartbeat.

      --

    21. Re:Interesting by evilviper · · Score: 1

      gpu's have been growing in transistor count relative to cpu's for quite some time.

      Cause and effect. Because they aren't integrated, more and more tasks are being fully offloaded to the GPUs, requiring more power. Also, do you really not think there's an upper limit, where the GPU can render more polygons at a higher resolution than anyone is going to care about? It happens. It's the natural progression of high technology.

      so, assuming you're going to stick a modern six core die to a 480 die, would you care to explain how you are going to dissipate enough heat before they fry eachother from being in such close proximity?

      I can't imagine what I wrote that would lead you to believe that. Of course there's too much heat. With a couple process shrinks, or maybe just one shrink and a CPU redesign, it'll be fine. The simple option for the high-end right now is to give the GPU it's own CPU socket, which AMD has discussed repeatedly.

      Your mistake is you think advances in process won't be used to make better gpu's, they will.

      Point me to a 200 watt FPU.

      --
      Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
    22. Re:Interesting by walshy007 · · Score: 1

      The hardware isn't the issue, it's the software. It becomes very difficult to use so many threads on most workloads. For graphics, sure,

      We are talking about graphics cards, primarily used for graphics, general computing is nice but not their primary concern.

      You know this with absolute certainty? You are absolutely sure we'll never have the technology to do it? I'll take that bet against you in a heartbeat.

      For it to be possible we would have to have a certain point where we conclude that having a certain functionality gpu is 'enough' saying such a thing is like saying we'll ever have a cpu that is 'enough' it won't exist because people will always want better.

      Any technology advances will be used to make better cpus/gpus at the high end. Therefore you can't use that advance to try and combine the high end of both.

    23. Re:Interesting by David+Greene · · Score: 1

      Any technology advances will be used to make better cpus/gpus at the high end.

      A gtx480 is not going to be high end for longer than about a year.

      --

    24. Re:Interesting by walshy007 · · Score: 1

      Yes, but by that time we'll be comparing it to the gtx 6xx, which will be the new high end and what w want 'included' with the cpu, which is the whole damn point. That advances get used to make better gpus.

  9. Linux seems to be working out in HPC so far by symbolset · · Score: 1

    It'll do until something better comes along.

    --
    Help stamp out iliturcy.
  10. Rate of processing power increase by zyzko · · Score: 1

    The last two sentences on the summary are the most interesting ones. If you thought that the rate of growth of memory and processing power on standard home/office computers is out of hand just look at the supercomputers. These things are basicly old when delivered and their life is practically max. 3-5 years, after that nobody cares. And that is a pity considering how much these beasts cost and they are mostly funded with public (tax) money because running a business selling processor time from these things with their small lifetime would never be profitable.

    1. Re:Rate of processing power increase by Teun · · Score: 1

      But being ahead of the herd has never been cheap and the rewards (or losses for being late) have made it a necessity.

      --
      "The likes of Facebook and WhatsApp are free to those whose privacy is of zero value."
    2. Re:Rate of processing power increase by gmack · · Score: 1

      Pretty sure Render Farms have the same obsolescence problem and there are businesses that depend on them.

    3. Re:Rate of processing power increase by Junta · · Score: 2, Insightful

      Not really. Yes, there is something of an arms race for the top500, but even after the top500 no longer lists a system it will almost certainly still be in use by someone for practical purposes other than benchmarking.

      --
      XML is like violence. If it doesn't solve the problem, use more.
    4. Re:Rate of processing power increase by bbn · · Score: 1

      The weather institute had the most powerful supercomputer in this (small) country. It was not that old, but it was time to upgrade. The new supercomputer was now the fastest supercomputer and the old one became the second fastest.

      What happened to the second fastest supercomputer in the country? It was scraped. They could not afford to keep running it due to cost of powering it. They could not sell or give it away, because the economics of it did not add up. Anyone needing such computing power were better off getting new equipment that would do more for the amount of electricity needed.

    5. Re:Rate of processing power increase by wisty · · Score: 1

      I'm going to guess that the old supercomputer used Pentium 4s. An old Core2 system is probably still OK, but P4 systems are only good if your heaters need upgrading.

    6. Re:Rate of processing power increase by Anonymous Coward · · Score: 0

      Most people do not know the speed of the support units of super computers of yesterday,
      Although the Cray_YMP C916/16526 with 16 cores driving 13.7 RMAX GFLOP/s
      ( It was originally called the YMP C90, then called the Cray C90 model C916...)

      http://en.wikipedia.org/wiki/Cray_C90#External_links

      http://www.spikynorman.dsl.pipex.com/CrayWWWStuff/Cfaqp5.html#c90

      is equivalent to a mid-range laptop(wtfbbq?):

      It could boot in less than 1 second.
      It could load a 128MW-64bit ram image in about 4 seconds, process it for 30 seconds, and pump the whole data cache back to
      the online storage pool in another 4 seconds. I have never seen a Laptop or desktop have that kind of speed of IO. ( the Cray C90 also had up to 8 EIO processors ).

      Super computers are more than just RMAX Gflops, they have a couple million dollars of peripherals,
      as well as a support staff, and GREAT technical support. Ever call Cray? You would NEVER EVER get a voice mail box.
      There was some issue with the OS image, that we thought we had nailed down to a bug, so next we called up cray.
      We didn't have a bug, but there was already a well documented solution to the problem, that was both elegant and painless.
      Sheer brilliance. With a multi-million dollar system, you do get good support.

      Supercomputers, even 22 year old ones are a different breed.

  11. Time To Hump It! by b4upoo · · Score: 1

    The US had best take the processor speed race very seriously. Who knows what kind of either military or economic domination might get a leg up with super computers? And once on top it can take a century or two to dislodge a leader in technology.

    1. Re: Time To Hump It! by MidoriKid · · Score: 1

      Mr. President, we must not allow a super computing gap!

    2. Re: Time To Hump It! by badran · · Score: 1

      The army better be using P1 or older for their feild deployments as those are more rugged and survive EMP.

  12. Re:Won't somebody please think of the licensing co by Anonymous Coward · · Score: 0

    because the same machine was able to achieve higher speeds using Linux

    Well, duh.

    Frankly I don't see how you can "supercompute" on Windows at all, with UAC and clippy popping up every other hour and whatnot.

    Heh.

    Looks like your trying to simulate the Higgs Boson. Would you like a tutorial?

  13. Re:Won't somebody please think of the licensing co by bmo · · Score: 5, Insightful

    Wait, what?

    Have you ever paid attention to the OS trends in the Top500? All the proprietary OSes are disappearing. It used to be nearly all proprietary Unix and BSD. Now it's 91 percent Linux.

    Here's a graph showing the demise of Unix in the Top500
    http://www.top500.org/overtime/list/36/osfam

    Linux doesn't scale? It fits in toasters and supercomputers. I think that's pretty good scaling if you ask me.

    You could probably make the argument in 1991 when Linus smote the ground and came up with the kernel, but not anymore. You could probably even make that argument before kernel 2.0. But since then? Claiming that Linux doesn't scale well just makes you look like a Microsoft fanboy whistling while walking past the graveyard at best.

    --
    BMO

  14. Re:Won't somebody please think of the licensing co by zach_the_lizard · · Score: 3, Insightful

    Yet it powers most of the top 500 supercomputers and can run on embedded platforms. If that's poor scalability, I want to know what's good scalability.

    --
    SSC
  15. With or without? by Teun · · Score: 0, Troll

    Was that achieved with or without a reliable virus scanner and firewall?

    --
    "The likes of Facebook and WhatsApp are free to those whose privacy is of zero value."
  16. Long Term Trends by Anonymous Coward · · Score: 1, Insightful

    Over the next 10 years I think we will see China, India, and other growing economies surpass the US in technology and science research, just as the US surged ahead of the "old world" countries in Europe post World War 2. More Phds, more papers, more discoveries.

    As life gets more comfortable and stable for a country, in terms of things like health, energy, and infrastructure, the focus always moves away from this kind of technology advancement and onto the arts, literature, and social concerns.

    Try asking someone in Europe how important they think it is for Germany, or France or the UK to have a leading position in terms of supercomputing capability. It just doesn't feature on the radar for them.

    The same will become true for the US over the next decade.

    1. Re:Long Term Trends by Anonymous Coward · · Score: 1, Insightful

      > surged ahead of the "old world" countries in Europe post World War 2
      Sure. Europe was a pile of rubble.

      > More Phds, more papers
      Doesn't mean anything

      > more discoveries.
      by European immigrants escaping from the war

      > As life gets more comfortable and stable for a country
      You don't travel much. The most unstable countries are the worst in science. Also, CINC.

      US technology has been leading in only one area: IT. As it was the area with the biggest growth during the last decades, the economical benefits were great.
      The earth's past decades have been shaped by the US not because of technological superiority, but because of their marketing and entertainment.

    2. Re:Long Term Trends by walshy007 · · Score: 1

      mod parent up

    3. Re:Long Term Trends by turbidostato · · Score: 1

      "Try asking someone in Europe how important they think it is for Germany, or France or the UK to have a leading position in terms of supercomputing capability. It just doesn't feature on the radar for them."

      Well, being Germany the 2nd world's biggest exporter (surpassed only by China some few months ago) maybe they are not all at arts and literature only.

  17. Wow! by sunspot42 · · Score: 1

    Finally a Windows box capable of running Duke Nukem Forever!

  18. Re:Won't somebody please think of the licensing co by Anonymous Coward · · Score: 1, Informative

    > Linux isn't exactly an ultrascalable high-performance OS either.

    Actually it is, it has a whole mess of features that don't become relevant until high-end stuff that the typical "haha lunix sux0rs" sad windoze weenie couldn't comprehend. It's retrogressed slightly lately out-of-box under neverrending low-end "schedule better for the desktop" pressure (hint: if you have 32768 cores, O(1) scheduling is *really handy*. Fortunately you can switch schedulers).

    Coupled with the vendor-specific addons like SGI ProPack, it really is the least worst OS out there for HPC today.

  19. I need one by florescent_beige · · Score: 2, Interesting

    I need one so I can recalculate my budget spreadsheet in a femtosecond. These nanosecond pauses are getting old.

    On a lighter note, so, why isn't this stuff changing our lives? I remember in the late 90's I read a story about how gigaflop computing would revolutionize aeronautics, allowing the full simulation of weird new configurations of aircraft that would be quantum leaps over what we had. Er, have.

    Can I answer my own question? I mean, can I answer two of my questions? No, make that three now. Anyway, my perspective is that the kinds of engineers who have the knowledge required to write this kind of software aren't software engineers. In fact, aeronautics is rife with some of the most horrifying software imaginable. Much of it being Excel macros. Seriously. I wrote some of it.

    --
    Equine Mammals Are Considerably Smaller
    1. Re:I need one by Anonymous Coward · · Score: 0

      After all the great advances with modelling and simulation, we go from being information-limited to physics-limited again. You can design an amazing wing structure, but it needs materials with 3x the tensile strength of existing alloys. Research indicates you should switch to fiber composites, but the manufacturing lead in, tooling and maintenance work is a completely different game.

      You may have seen giant low-noise flying wing designs out of engineering colleges, looks like progess. Fabricating a working design within the constraints of current infrastructure becomes more time consuming, because you can't simulate that so well.

    2. Re:I need one by Anonymous Coward · · Score: 0

      How do you think Airbus build the A380 and Boeing built the Dreamliner? Hint: it wasn't guys with pocket protectors and slide rules.

    3. Re:I need one by florescent_beige · · Score: 1

      I agree with you. In fact, you could say we have been making the same airliner over and over since the 707. A tube with swept wings and either two or four engines on the wing. "Revolutionary" means 2% faster or 10% lighter. There is a whole global infrastructure dedicated to making these tubes and wings.

      However, I stand by my belief that engineering software is trapped in a time bubble. In 1985 I learned Patran and Nastran. These days I use...Patran and Nastran. Maybe the big shift has been from sol 101 to 106. Patran has the same bugs it did in 1996. And when we do a full scale static test we are just as nervous when the needle gets to 140% as we were back in the day.

      And the bible is still Bruhn. Written in the mid '60's.

      --
      Equine Mammals Are Considerably Smaller
    4. Re:I need one by Jeremy+Erwin · · Score: 3, Funny

      n fact, aeronautics is rife with some of the most horrifying software imaginable. Much of it being Excel macros.

      This is why Windows HPC is going to change everything

    5. Re:I need one by florescent_beige · · Score: 1

      The 380 is a triumph of industrial synthesis, not aerodynamics. The 787 is similar, though not so triumphant.

      Computer aided design (read: CATIA) increases productivity an order of magnitude more than performance. Case in point, instead of physically mocking up all the harnesses for an airplane like the 380, we now do that digitally. But that is just geometric modeling (and kinematic, but not dynamic). And we still get it wrong. The 380's wiring was laid out wrong and that was never caught until someone tried to connect two harnesses that ended a foot apart. Oops. Cost millions to fix.

      --
      Equine Mammals Are Considerably Smaller
    6. Re:I need one by LordOfTheNoobs · · Score: 1

      So, I guess our planes suck because you suck. Thanks a lot, guy.

      --
      They're there affecting their effect.
    7. Re:I need one by florescent_beige · · Score: 1

      If it was up to me we'd be flying around in a 2,000-passenger supersonic oblique flying wing with a pool bar and docking ports for the shuttles that take us up from the airport. But nobody listens.

      --
      Equine Mammals Are Considerably Smaller
    8. Re:I need one by PitaBred · · Score: 1

      Flown in an airplane lately? You no longer have to circle to land. You basically just fly right in. More computing power and better software have enabled that. We've got new jet engines in the pipeline that are more efficient and make less noise, too.

  20. So why would anyone want to do this? by Entropius · · Score: 5, Informative

    I do scientific high-performance computing, and there is simply no reason anyone would want to run Windows on a supercomputer.

    Linux has native, simple support for compiling the most common HPC languages (C and Fortran). It is open source and extensively customizable, so it's easy to make whatever changes need to be made to optimize the OS on the compute nodes, or optimize the communication latency between nodes. Adding support for exotic filesystems (like Lustre) is simple, especially since these file systems are usually developed *for* Linux. It has a simple, robust, scriptable mechanism for transferring large amounts of data around (scp/rsync) and a simple, unified mechanism for working remotely (ssh). Linux (the whole OS) can be compiled separately from source to optimize for a particular architecture (think Gentoo).

    What advantage does Windows bring to a HPC project?

    1. Re:So why would anyone want to do this? by BigFootApe · · Score: 1

      The only "advantage" is when you're defaulted to Windows because an ISV has a required shrink wrap application available only for Windows.

    2. Re:So why would anyone want to do this? by devent · · Score: 1

      Maybe Exchange, Outlook and ActiveDirectory?

      --
      http://www.mueller-public.de - My site http://www.anr-institute.com/ - Advanced Natural Research Institute
    3. Re:So why would anyone want to do this? by rolfwind · · Score: 1

      Duh. Obviously to run Crysis.

    4. Re:So why would anyone want to do this? by Anonymous Coward · · Score: 0

      yeah that. what the fuck is wrong with the ssh devs that they refuse to give us encryptionless binary transfers. i don't need encryption to move my gigabytes from one computer to another on my network, and it sounds like you have the same problem several orders of magnitude bigger.

      there is no good way to move files. windows you need to use a gui and linux the ssh people force encryption on you.

    5. Re:So why would anyone want to do this? by Anonymous Coward · · Score: 0

      Duh, Minesweeper. What are the researchers supposed to do while Gentoo compiles?

    6. Re:So why would anyone want to do this? by Anonymous Coward · · Score: 0

      > What advantage does Windows bring to a HPC project?
      As usual, they have marketing experts that can convince people to buy an inferior product.

    7. Re:So why would anyone want to do this? by Pinehill.net · · Score: 1

      MS has some clear advantages over linux. The unix authentication and authorization model is antiquated and very coarse compared to windows. Also, MS produces a much better integrated and more functional development environment that anything available in the FOSS world.

      They're nowhere near the level of depth in the HPC world that linux has, but if they can do for parallel programming what VB did for programming generally (make is accesible to non-programmer domain experts) then it could be a compelling alternative.

    8. Re:So why would anyone want to do this? by Deviant · · Score: 3, Interesting

      One of the big developments of late has been in data mining of the data from your ERP system / data warehouse to answer questions about your clients/business and to find interesting patterns in your data. Couple this with the fact that buisinesses are trying to retain more and more data in a live database to make this data mining more deep/interesting and the needs for massive database servers with the power to run some crazy complex queries/reports is on the rise.

      The popular example of this sort of thing in Wal-Mart who retain everything in an electronic form and can do scary things like see pictures of you based on correlating their digital security footage with your credit card purchase at a point in time at a particular register or track the differences in sales of individual products during unusual events like Hurricanes etc.
      http://developers.slashdot.org/article.pl?sid=04/11/14/2057228

      Many businesses run Microsoft SQL Server as the backend for their ERP system and/or as their primary database. This would allow them to build a nice little HPC system to do the sorts of scary things with massive amounts of data that they have been wanting to do. I end with this funny cartoon on the subject.
      http://onefte.com/2010/09/21/target-markets/
       

    9. Re:So why would anyone want to do this? by LordOfTheNoobs · · Score: 1

      Fucking shrink wrapped supercomputer apps.

      --
      They're there affecting their effect.
    10. Re:So why would anyone want to do this? by Coryoth · · Score: 1

      Also, MS produces a much better integrated and more functional development environment that anything available in the FOSS world.

      They're nowhere near the level of depth in the HPC world that linux has, but if they can do for parallel programming what VB did for programming generally (make is accesible to non-programmer domain experts) then it could be a compelling alternative.

      If you want that, then you're probably looking for either X10 or Chapel which offer a huge leap forward in making massive scale parallel programming simpler and easier. Of course X10 is from IBM and has Eclipse and plugins as the dev environment, and the closest they offer to a Windows version of the compiler is one compiled against cygwin. Chapel is from Cray, and has practically no Windows support, save for a claim that you can get it working with cygwin. Both languages are excellently supported on Linux (which is, of course, what Cray and IBM supercomputers run these days). So it woudl seem the future of parallel programming is firmly in the linux camp.

    11. Re:So why would anyone want to do this? by h4rr4r · · Score: 1

      If you don't want encryption do not use SSH, there are other ways to move files.

    12. Re:So why would anyone want to do this? by ratboy666 · · Score: 2, Insightful

      For HPC clusters, wouldn't you want something simple like a NIS domain? What advantage does Windows offer here? Further, what parallel programming support does Microsoft offer?

      And, since the nodes in the cluster are headless anyway, and the code is going to be written to POSIX and MP standards anyway, what advantage does Microsoft offer AT ALL compared to Linux or BSD?

      Linux, of course, offers early adopter support in this area. It tends to prevail simply because of the other clusters. You know it can work, and can cross-share experience. Windows? Not so much. And, if the Windows API doesn't help, the tools don't help (sure, they may not hinder, either), there is no compelling reason to build such a thing.

      Unless Microsoft funds it (I would like to see the OS bill for Windows on a 10,000+ processor node cluster).

      Strangely, I would have expected Microsoft to fund at least one cluster in the top 5, just for name. Now, I haven't looked in a few months, but the last time I did look (Jaguar was still #1), a Windows based cluster didn't even break into the top 10.

      --
      Just another "Cubible(sic) Joe" 2 17 3061
    13. Re:So why would anyone want to do this? by Anonymous Coward · · Score: 0

      Dude, have you run Office lately ?

    14. Re:So why would anyone want to do this? by swillden · · Score: 1

      It's not clear to me how running Windows on the HPC machine would help.

      --
      Note to ACs: I usually delete AC replies without reading them. If you want to talk to me, log in.
    15. Re:So why would anyone want to do this? by Anonymous Coward · · Score: 0

      ssh people force encryption on you.

      It's called Secure SHell for a reason and you have the source. So if you want to remove encryption from scp, go right ahead. Also, you should probably into netcat/nc. A little netcat and bash I/O redirection and you have a peer to peer file transfer protocol with no fuss.

    16. Re:So why would anyone want to do this? by Deviant · · Score: 1

      Because that organisation may not have much in the way of Linux knowledgefor the setup/management/programming of the HPC cluster in-house while they have a wealth of MS experience. Microsoft has created a number of programming APIs for their HPC product that can just be called in .NET to extend existing software or to create new tools where staff members are already familiar with Microsoft programming tools/methodologies.

      http://msdn.microsoft.com/en-us/library/cc853440(VS.85).aspx

      In short it is a Microsoft solution to the problem written for organisations that use their platform for everything else and that makes it compelling for a variety of reasons - not the least of which being interoperability with the existing infrastrucutre and managability by the existing staff.

    17. Re:So why would anyone want to do this? by hawkingradiation · · Score: 1

      The Tsubame 2.0 came loaded with Windows, naturally. They decided to try it out for a few compute cycles but found they needed better applications than Office in order to complete their super computing projects. They then promptly wiped the whole thing and installed Linux. I wonder if they have ever gone back since? I have heard that Office has not been optimized to run on GPU's and because of Windows limitations, the thousands of users that would be using the super computer could not be fully supported using Windows.

      --
      Society use your Sciences
    18. Re:So why would anyone want to do this? by SigmundFloyd · · Score: 1

      I do scientific high-performance computing, and there is simply no reason anyone would want to run Windows on a supercomputer.

      Right: or anything else with a GUI, for that matter. Those machines should mostly be crunching numbers and doing the least possible I/O.

      Cycles wasted checking for mouse movement, or drawing silly menus and icons, are wasted money, since one could build a smaller machine and offload the frivolous GUI stuff to a graphic terminal.

      --
      Knowledge is power; knowledge shared is power lost.
    19. Re:So why would anyone want to do this? by swillden · · Score: 1

      Because that organisation may not have much in the way of Linux knowledgefor the setup/management/programming of the HPC cluster in-house while they have a wealth of MS experience.

      Haven't worked for many big retailers, I see. Their infrastructure tends quite heterogeneous. You mentioned Wal-mart, for example. They have Linux all over the place.

      I grant that your scenario isn't impossible, but it's at least quite rare.

      --
      Note to ACs: I usually delete AC replies without reading them. If you want to talk to me, log in.
    20. Re:So why would anyone want to do this? by Entropius · · Score: 1

      The computers involved in the ssh transfers can do the encryption in their sleep. The login nodes involved here are seriously beefy.

      The computational burden is small enough that nobody cares, really.

    21. Re:So why would anyone want to do this? by Entropius · · Score: 1

      Oh, of course.

      The way these things tend to work is that you have internet-facing "login nodes" (with ssh servers but no GUI) that people can ssh into. They're typically pretty beefy machines (8- or 16-core with tons of ram). One of the things you can ask them to do is to submit the serious HPC jobs to a queue.

      There's another machine whose sole purpose is to coordinate transfers from some parallel high-performance filesystem(s).

      Finally, there are the thousands of actual compute nodes, which are not internet-facing, and which one communicates with using the "queue submit" feature. You send stuff to their stdin, you get stuff from their stdout, just like an ordinary linux program.

    22. Re:So why would anyone want to do this? by Anonymous Coward · · Score: 0

      Maybe Exchange, Outlook and ActiveDirectory?

      And you're running this on a supercomputer, why exactly?

    23. Re:So why would anyone want to do this? by Anonymous Coward · · Score: 0

      Exchange and Office. Oh, and DX11 games.

    24. Re:So why would anyone want to do this? by Anonymous Coward · · Score: 0

      You're asking in the wrong place. According to Slashdot, you don't need Windows for anything and the answer for everything is Ubuntu.

      Go Wayland!

    25. Re:So why would anyone want to do this? by Anonymous Coward · · Score: 0

      Let me bite.

      Apples and oranges - what you talk about is not HPC.
      HPC is typically about scientific computing and not data mining. For fast data mining you need great I/O and you don't need to top the floating point performance. For scientific stuff you need to be able to crunch some numbers.

      So, GP's question stays completely unanswered. I consider it to be in essence, a rhetorical question.

    26. Re:So why would anyone want to do this? by qchan · · Score: 1

      What the Entroplus is saying is that super computer operators have more room to customize the OS to get the max benefits from it. This will allow the super computer to run more efficiently. Linux also allows for scalability that simply isn't present in Windows; or at least, as simple and readily available. On another note: When I speak about scalability, I also refer to different architectures. A good example would be Sparc.

    27. Re:So why would anyone want to do this? by badran · · Score: 1

      ftp?

  21. Anti-American Bias? by l0ungeb0y · · Score: 1

    The summary clearly states "Linux retains a spot in the top-5", then goes on to say that China has 2 "top spots", with America and Japan only having one spot a piece. And while that may be true if you limit it to a "top-4", America is tied with China if you count the number 5 position. So why does the OP pull this slight of hand, only counting the top 4 as the "top spots" after making reference to the "top-5" as the measure of top positions? Looks like bias to me.

    1. Re:Anti-American Bias? by Chrisq · · Score: 1

      if you count the number 5 position. So why does the OP pull this slight of hand, only counting the top 4 as the "top spots" after making reference to the "top-5" as the measure of top positions? Looks like bias to me.

      Their supercomputer had rounding errors

  22. Re:Won't somebody please think of the licensing co by Anonymous Coward · · Score: 0

    Give me the money to design an OS from the start.

    I suspect a few hundred billion will do it.

  23. Re:Won't somebody please think of the licensing co by eugene2k · · Score: 1

    You can only switch I/O schedulers and O(1) is a task scheduler.

    --
    Apple has "Mac vs PC", Microsoft has "Laptop Hunters", Linux has recession
  24. So some kid on wiki got it wrong. by symbolset · · Score: 1

    Probably got confused with MIPS. Hopefully somebody here will wander over and fix it. I don't have time to get involved in a wikipedia edit war today.

    BTW: if you were looking for funny mods you could have gone down the SI Pebiflops fork, or the onion-belt milliflops fork. This line isn't going to get you there.

    --
    Help stamp out iliturcy.
    1. Re:So some kid on wiki got it wrong. by TheRaven64 · · Score: 1

      MIPS also mean Millions of Instructions Per Second, so MIPS per second would be similar nonsense. Unless MIPS means Microprocessor without Interlocked Pipeline Stages, in which case MIPS per second would... also be nonsense, but an entirely more confusing kind of nonsense.

      --
      I am TheRaven on Soylent News
    2. Re:So some kid on wiki got it wrong. by Kilrah_il · · Score: 1

      Actually he meant that the wiki page is wrong and, unlike MIPS, the 's' in FLOPS does not mean "second".
      I don't know enough about the subject. A quick Google search for "FLOPS floating" found both interpretations, although it seems there are more "per second" pages than those without it. I don't know...

      --
      Whenever in an argument, remember this.
  25. This is all good and fine... by Beelzebud · · Score: 2, Funny

    But will it play Flash Video smoothly at full screen?

  26. Re:Won't somebody please think of the licensing co by Kell+Bengal · · Score: 2, Funny

    What the hell kind of toaster runs Linux? There's hardly any justification for a mass-produced toaster to have any logic more complex than a relay. If there's an actual consumer toaster out there on the market that has linux controlling it, I'd like to see it (and buy it)!

    --
    Scientists point out problems, engineers fix them
    altslashdot.org: The future of slashdot.
  27. Re:Won't somebody please think of the licensing co by Sarten-X · · Score: 1

    You can get the full source easily. You can switch everything, if you want.

    --
    You do not have a moral or legal right to do absolutely anything you want.
  28. Re:Won't somebody please think of the licensing co by Guy+Harris · · Score: 1

    What the hell kind of toaster runs Linux? There's hardly any justification for a mass-produced toaster to have any logic more complex than a relay. If there's an actual consumer toaster out there on the market that has linux controlling it, I'd like to see it (and buy it)!

    No, you need NetBSD for that.

  29. Re:Won't somebody please think of the licensing co by bmo · · Score: 1

    Linux is and always has been designed with extreme outward AND upward scaling in mind

    >always

    You conveniently snipped "you could have made that argument..."

    Your argument is not only existentially fallacious, but you put words in my mouth.

    Cunt.

    --
    BMO

  30. Re:Won't somebody please think of the licensing co by Kjella · · Score: 1

    If you were building a supercomputer operating system from the start you'd make very different design decisions than Linus did.

    Heh, one of those "start clean and it'll be so much better". There's been a kazillion patches to Linux to make it scale better, if there was anything essential holding it back they'd fork and run their own supercomputer-linux. Yes, you would use very different design decisions, but those Linux made in the early 90s aren't longer in effect either.

    --
    Live today, because you never know what tomorrow brings
  31. Re:Won't somebody please think of the licensing co by StuartHankins · · Score: 1

    Some Motorola routers can be used as toasters!

  32. My toaster needs an update, if it has an OS by NotQuiteReal · · Score: 2

    I don't know if it has an OS, but my Black & Decker Infrawave toaster oven sometimes gets "hung". I sure wish there was an OS update for it, I really like it.

    This toaster uses what look pretty much like toner fusing light bars to toast/cook. It is really fast, and gives off a nice evil glow when it is working.
    The only problem with it is that you can sometimes confuse it into a very dangerous state - i.e. it can go FULL ON, and the "off" switch has no effect. In this state the door-interlock switch doesn't even work! (I can't even fathom the stupidity of that design... I can hear the switch click, so I guess there must be a hardware engineer's equivalent of the Daily WTF? to explain it. I am a software guy, and even I know that the safety interlock ought to directly cut the heater power, even if you want to let the LCD/button logic run. I guess the logic board is just being "told" the switch went off and is supposed to do something about it. Sheesh.)

    Futhermore, pulling the plug from the wall (for any length of time) only turns it off -- until you plug it in again! Then FULL ON, no stopping!
    Rather than returning it, I've just instructed everyone in the household a work-around I have discovered; When Stuck "on", simply select "toast level 1", even while it is running already. I assume this is the least cooking it can, do, then press "start"... it will turn off after about one "toast level 1" more's worth of time, then it is back to normal (until the next time you piss interrupt it at the wrong time, usually by opening the door while it is full-on, but near the end of a cycle.)

    It is a strange world where my desktop PC is more predictable than my toaster oven. (In terms of not "crashing".)

    --
    This issue is a bit more complicated than you think.
    1. Re:My toaster needs an update, if it has an OS by Anonymous Coward · · Score: 0

      My computer controlled toaster (Sunbeam) is much better:

      The toast is held down by some kind of electromagnet.

      This means that even if the cancel button fails (hasn't yet), pulling the plug ejects the toast.

      I suspect the firmware is simply written in assembly.

    2. Re:My toaster needs an update, if it has an OS by Anonymous Coward · · Score: 0

      The toast is held down by some kind of electromagnet.

      You eat magnetic toast?

  33. Re:Won't somebody please think of the licensing co by Anonymous Coward · · Score: 0

    So do other proprietary and open OSes

    Except not, as the guy you're responding too pointed out. "other proprietary and open OSes" have been pushed out of the Top 500 easily and gently by Linux, as the graph shows.

  34. Excel spreadsheets for banking and stock exchange by snikulin · · Score: 3, Informative

    You will probably laugh but banks and finances do not: Excel spreadsheets.
    Microsoft HPC solution allows distribute it across many nodes.
    Trust me: *huge* money are there (alas, not for you, not for me and not for science).
    It's much cheaper for a bank to rent a supercomputer to calculate a heavy spreadsheet written by programming-challenged but money-wise CPA then to hire a money-challenged, HPC-wise guy to rewrite (and perpetually modify it on a short notice) this spreadsheet to FORTRAN.

  35. Re:Won't somebody please think of the licensing co by Anonymous Coward · · Score: 0

    Toasters that run linux : Toaster (photobucket, jpg)

    You're welcome. By the way, if you happen to come across these on amazon, please share the link. Thank you.

  36. Re:Won't somebody please think of the licensing co by Anonymous Coward · · Score: 0

    You need a lower user score to understand.

  37. Human Brain power reached (approx) by DanielRavenNest · · Score: 1

    Top machine: 2500 x 10^12 floating point ops x 64 bits = 160 x 10^15 bits per second

    Human brain: 10^11 neurons x 10^4 synapses x 100 Hz firing rate = 100 x 10^15 bits per second.

    I am not saying it will wake up tomorrow and launch Skynet, but until now inadequate hardware was a barrier to human-level AI.

    And yes, I am quite aware that a synapse firing is not directly comparable to a binary bit. Call this a rough comparison.

    1. Re:Human Brain power reached (approx) by raftpeople · · Score: 1

      and 10^12 glial cells previously ignored in computation but now it is understood they are part of computation

    2. Re:Human Brain power reached (approx) by mswhippingboy · · Score: 1

      I'm not too sure about your calculations relating the human brain to processing speed. I reminds me of the Drake equation for calculating the number of ET civilizations (a guess multiplied by a guess multiplied by a guess, etc).

      However, I do find the following interesting.

      In 2009 the top spot was a machine capable of 1.1 petaflops. This year the top spot is 2.57 petaflops. IBM is predicting a 10 petaflops machine by next year. At this rate of acceleration, it would not seem unreasonable to expect that by 2012 we could reach the 50 petaflops level.

      Intelligence of a species is sometimes roughly correlated to the ratio of cortex mass (not just brain mass). A mouse has approximately the same brain/body mass ratio as a human, but they are obviously much less intelligent. This is because the cortex of a mouse makes up much less of a percentage of brain mass than a human. However, relating this to a hardware/software simulated brain, body mass is irrelevant, so for simplicity sake, we can ignore this and look strictly at brain mass as an indicator of intelligence.
      In 2009 IBM announced a machine&software that exceeded the scale of a cat's cortex.
      An average cat's brain mass is in the 30g range.
      Given the acceleration of computing speeds and brain mass as a guide, we could expect to simulate a 75g brain this year, and a 300g brain next year. If the trend continues, a brain somewhere in the 1500g range would seem feasible by 2012.

      The human brain is somewhere around the 1400g range.

      Kind of chilling given all the 2012 prophecies going around, eh?

      --
      Sometimes the light at the end of the tunnel is the headlight of an oncoming train.
  38. Re:Won't somebody please think of the licensing co by Anonymous Coward · · Score: 0

    The most awesome toaster in the universe, that's what!

    Also it can rip a hole in the fabric of space time, so um, don't go back and kill any dinosaurs.

  39. Re:Won't somebody please think of the licensing co by MartinSchou · · Score: 0, Troll

    If that's poor scalability, I want to know what's good scalability.

    Well, apparently it doesn't scale down in size to the desktop. If you don't believe me, just look at the usage statistics. Top500 servers: 91% linux. Desktop: 91% Windows.

    Just like a jet-engine is a great way to power a huge aircraft, no so great for powering your lawn mower or chain saw.

    And no it's not flame bait, when you're answering a non-rhetorical question.

  40. Re:Won't somebody please think of the licensing co by Lucractius · · Score: 1

    Mostly because of development costs.
    Much cheaper to work with linux than build a new one from scratch.

    --
    XML - A clever joke would be here if /. didn't mangle tag brackets.
  41. So What, by Anonymous Coward · · Score: 0

    I made a flux capacitor out of a old toilet paper roll, some wire and toothpicks last night. I use it to power my windows 7 box that spell checks my code.

  42. Re:Won't somebody please think of the licensing co by spisska · · Score: 1

    Just like a jet-engine is a great way to power a huge aircraft, no so great for powering your lawn mower or chain saw.

    Maybe you don't have a jet-powered lawn mower, but maybe you're just not that serious about your yard work.

  43. Re:Excel spreadsheets for banking and stock exchan by gartogg · · Score: 2, Informative

    Any other application built for windows has the same issue.
    I work for a company doing modeling for insurance, and the software for catastrophe modeling (RMS, AIR, Eqecat,) all are windows only. The simulations and models take days to run for a large data set, and the software/modeling companies aren't about to switch off of windows for the software licensed from them, and there is nowhere else to go.

    --
    I'm a concientious .sig objector.
  44. lies damn lies and software licensing by petermgreen · · Score: 1

    The thing with MS is they won't sell you licenses to their older products but they WILL sell you volume licenses to their newer proucts that include "downgrade rights".

    So sales get chalked up as sales of the latest version whatever version the customer actually uses.

    Things are even worse for normal consumers who usually don't get the option of downgrading.

    --
    note: i'm known as plugwash most places but i screwd up registering that here somehow in the past and now can't register
  45. MS denied first Petaflop how, exactly? by kenh · · Score: 1

    From the article:

    "While the computer broke a petaflop with both operating systems, it achieved a faster score with Linux, denying Microsoft its first official petaflop ranking."

    If the machine broke a petaflop with both operating systems (Linux and Windows), how was it denied an official Petaflop ranking? It achieved it, why doesn't it count? Is each machine only allowed one ranking? Seems sort of odd, the ranking of the same machine with different OSs would be interesting, no?

    --
    Ken
    1. Re:MS denied first Petaflop how, exactly? by mswhippingboy · · Score: 1

      Because the ranking is by machine, not by OS.
      Since this particular machine achieved it's highest ranking with Linux, the ranking lists Linux as it's OS, not Windows.

      --
      Sometimes the light at the end of the tunnel is the headlight of an oncoming train.
  46. Re:Won't somebody please think of the licensing co by h4rr4r · · Score: 1

    Yet, it works fine on phones and android is outselling others. Almost like their might be something special about the desktop market, some sort of market tampering by a player or two.

  47. Re:Excel spreadsheets for banking and stock exchan by Entropius · · Score: 1

    Wait, people do high performance computing on SPREADSHEETS?

    My world just exploded. Iluvatar, can't they find some schmuck to code them in Perl, even?

  48. Re:Excel spreadsheets for banking and stock exchan by snikulin · · Score: 2, Insightful

    The point is to NOT have anybody to code it at all.

  49. Re:Excel spreadsheets for banking and stock exchan by snikulin · · Score: 1

    Besides, I think Excel easily beats Perl in terms of MIPS/FLOPS (but probably not wisely applied Python+NumPy).

  50. Re:Excel spreadsheets for banking and stock exchan by Entropius · · Score: 1

    Spreadsheets are coding, just a different sort...

  51. Re:Excel spreadsheets for banking and stock exchan by snikulin · · Score: 1

    Yes, "coded" by a specialist in the target area. A perl (or Fortran) schmuck is not a CPA specialist to trust to.

    Your negative response reminds me about mini-era programmers' response to 1-2-3 and IBM-PC ;)

    Welcome to the world of tomorrow!

    But I sure feel your pain.

    And please (re-)read "Diaspora" by Greg Egan. Those folks sure aint need no stinkin programmers! :)

  52. Android (LINUX) & security issues? by Anonymous Coward · · Score: 0

    "Yet, it works fine on phones and android is outselling others" - by h4rr4r (612664) on Sunday November 14, @09:08PM (#34227208)

    A Linux variant, in the Android OS, is also showing security vulnerabilities -> http://mobile.slashdot.org/story/10/11/14/0115255/Android-Holes-Allow-Secret-Installation-of-Apps and everyone around here seems to state that Linux is immune to security problems, and Windows is chock full of them... funny that article link above (which isn't a first either) then, eh?

    1. Re:Android (LINUX) & security issues? by Anonymous Coward · · Score: 0

      APK - fuck off and die please, you cockmuncher.

  53. Re:Won't somebody please think of the licensing co by Anonymous Coward · · Score: 0

    Don't forget the jet powered beer cooler.

  54. Re:Won't somebody please think of the licensing co by Anonymous Coward · · Score: 0

    That has nothing to do with scalability, and everything to do with usability.

  55. Re:Won't somebody please think of the licensing co by Anonymous Coward · · Score: 0

    "scaling" obviously does not mean what you think it does.

    Also, you need to work on your equivalence making skills, so far they look rather "false."

    Cheers.

  56. Re:Excel spreadsheets for banking and stock exchan by kramulous · · Score: 2, Informative

    As a professional HPC programmer, using "days to run for a large data set" is absolutely meaningless to me.

    Define large. Means different things to different people.

    --
    .
  57. Re:Won't somebody please think of the licensing co by gdshaw · · Score: 1

    What the hell kind of toaster runs Linux? There's hardly any justification for a mass-produced toaster to have any logic more complex than a relay.

    Howdy doodly do. How's it going? I'm Talkie, Talkie Toaster, your chirpy breakfast companion. Talkie's the name, toasting's the game. Anyone like any toast?

    [from Red Dwarf IV: White Hole]

  58. The Chinese knockoff doesn't count by sethstorm · · Score: 1

    Chinese Tianhe-1A system at the National Supercomputer Center in Tianjin

    Try again, with a country that doesn't have extensive First World knockoffs.

    --
    Twitter supports and protects racists - by smearing their critics with the "Hate Speech" label.
  59. Why Linux On Clusters? by deadline · · Score: 1

    The reasons Linux is so successful on HPC clusters are numerous. Historically, Linux was the best solution for many reasons. In particular, HPC clearly demonstrates why "open" is superior to closed approaches to a markt.

    --
    HPC for Primates. Read Cluster Monkey
    1. Re:Why Linux On Clusters? by deadline · · Score: 1

      Forgot this link! Why Linux On Clusters?

      --
      HPC for Primates. Read Cluster Monkey
    2. Re:Why Linux On Clusters? by Murdoch5 · · Score: 1

      Linux is the best solution for most systems, Desktop, Server and Cluster

  60. Re:Won't somebody please think of the licensing co by tehcyder · · Score: 1
    On slashdot, there are two types of statistics: ones which are favourable to Linux/UNIX/Mac OSX, and ones which we either ignore or explain away.

    In this case, the 91% figure for servers is entirely accurate (because it is good for Linux) whilst the 91% desktop for Windows figure is one or more of the following:-

    a straightforward lie by Microsoft/some stooges of Microsoft;

    distorted because a lot of people run Linux but emulate Windows, or something;

    distorted because I and all my hip friends use Mac OSX and so therefore the rest of the world must too.

    [if all else fails] only achieved by Microsoft's illegal business tactics;

    --
    To have a right to do a thing is not at all the same as to be right in doing it
  61. Re:Won't somebody please think of the licensing co by Skarecrow77 · · Score: 1

    Exactly. It's a total scam and lie. Nobody REALLY uses windows except clueless MBA wannabe executives who don't understand computers.

    Well, them and our parents.

    ok, and our friends.

    alright, us too. we all have windows computers (somewhere in our lives) but SHHHHH don't tell anybody because we all WANT to run linux on 100% of our computers, right?

    So yeah, pretty much everybody except the art department (for some reason I still don't understand, probably because I'm not an artist) uses windows on at least a semi-regular basis.

  62. Re:Won't somebody please think of the licensing co by badran · · Score: 1

    Intel used to sell these a while back. You can still find tons of them all around the world.

  63. Re:Won't somebody please think of the licensing co by Nethemas+the+Great · · Score: 1

    How about this one And here's a community site devoted to such ideas.

    --
    Two of my imaginary friends reproduced once ... with negative results.
  64. Re:Excel spreadsheets for banking and stock exchan by gartogg · · Score: 1

    It doesn't matter what large means to you; you weren't involved in the discussion. It also does not speak well of your abilities with numbers if "days" means nothing to you. It's multiple, as in more than one.

    A 10gb database may not be huge, but the complexity of the convolutions that need to be performed on the location losses to find the loss curve is a bit difficult. Some re-insurers have an arbitrarily large hardware budget (in the millions per analysis machine, since they only need a couple,) and the software maxes out its ability to use multiple processors after 16 or so, and so HPC solutions in windows would be very useful.

    --
    I'm a concientious .sig objector.