Slashdot Mirror


Japan Unveils Next-Generation, Pascal-Based AI Supercomputer (nextplatform.com)

The Tokyo Institute of Technology has announced plans to launch Japan's "fastest AI supercomputer" this summer. The supercomputer is called Tsubame 3.0 and will use Nvidia's latest Pascal-based Tesla P100 GPU accelerators to double its performance over its predecessor, the Tsubame 2.5. Slashdot reader kipperstem77 shares an excerpt from a report via The Next Platform: With all of those CPUs and GPUs, Tsubame 3.0 will have 12.15 petaflops of peak double precision performance, and is rated at 24.3 petaflops single precision and, importantly, is rated at 47.2 petaflops at the half precision that is important for neural networks employed in deep learning applications. When added to the existing Tsubame 2.5 machine and the experimental immersion-cooled Tsubame-KFC system, TiTech will have a total of 6,720 GPUs to bring to bear on workloads, adding up to a total of 64.3 aggregate petaflops at half precision. (This is interesting to us because that means Nvidia has worked with TiTech to get half precision working on Kepler GPUs, which did not formally support half precision.)

75 of 121 comments (clear)

  1. Pascal-based? by davidwr · · Score: 5, Insightful

    Am I the only one that thought "LISP machines, okay, but Pascal?"

    --
    Knowledge is how to play a game, intelligence is how to win, wisdom is knowing what game to play.
    1. Re:Pascal-based? by dougdonovan · · Score: 1

      ok, we're on the same page. japan, wake up.

    2. Re:Pascal-based? by cant_get_a_good_nick · · Score: 1

      I was thinking "Mr Wirth would be very happy..."

    3. Re:Pascal-based? by sycodon · · Score: 1

      Umm...is this the Pascal as in the programming language?

      --
      When Fascism comes to America, it will call itself Anti-Fascism, and tell you to give up your guns.
    4. Re:Pascal-based? by Crashmarik · · Score: 2

      Being a Pascal programmer I felt horribly bait and switched.

    5. Re:Pascal-based? by Anonymous Coward · · Score: 1

      The real question is, did anyone NOT think that?

      And, more importantly, just how calculated was that clickbait title, and who or what calculated it?

    6. Re:Pascal-based? by s.petry · · Score: 2

      Pascal has always been exceptional performing math. Makes sense for a super computer IMHO. The fact that I wrote pascal for my math degree is bonus!

      --

      -The wise argue that there are few absolutes, the fool argues that there are no probabilities.

    7. Re:Pascal-based? by Anonymous Coward · · Score: 1

      but Pascal [standardpascal.org]?

      It's more like Pascal or, alternatively, Pascal.

    8. Re:Pascal-based? by ShanghaiBill · · Score: 4, Informative

      Umm...is this the Pascal as in the programming language?

      Does anyone still program in Pascal? The last time I saw it on a resume was more than 20 years ago.

      Anyway, this supercomputer has nothing to do with the Pascal programming language. It is built using NVidia Pascal GPUs.

    9. Re:Pascal-based? by BitterOak · · Score: 1

      Pascal has always been exceptional performing math. Makes sense for a super computer IMHO. The fact that I wrote pascal for my math degree is bonus!

      Are you sure you're not thinking of Fortran? I've never heard that Pascal is unusually good at math compared to other general purpose programming languages.

      --
      If I can be modded down for being a troll, can I be modded up for being an orc, or a balrog?
    10. Re:Pascal-based? by jimtheowl · · Score: 1

      Some people do. It is a very well defined language worth looking into even if only for academic reasons.

      Some would say that everything old is new again; good design merits consideration.

      I am not suprised by this. When faced with coming up with something better, why not choose something old (and proven) rather than try to create something new?

    11. Re:Pascal-based? by Lips · · Score: 1

      Inno Setup is an excellent free installer for Windows programs. It's scripting language is Pascal. http://www.jrsoftware.org/isinfo.php/

    12. Re:Pascal-based? by sycodon · · Score: 1

      OK, thanks.

      I liked Pascal. It was very elegant.

      --
      When Fascism comes to America, it will call itself Anti-Fascism, and tell you to give up your guns.
    13. Re:Pascal-based? by s.petry · · Score: 1

      I programmed Fortran my first year, but after that we used Pascal. Pascal was not as fast for some operations, but in others was faster. C was no match, and yes I took a year of C and even a semester of Cobol just so I could say I did.

      --

      -The wise argue that there are few absolutes, the fool argues that there are no probabilities.

    14. Re:Pascal-based? by jbolden · · Score: 1, Redundant

      Well first off the super computers aren't about the Pascal language but the Pascal chip. I'd disagree that Pascal was all that proven out. It seemed very quickly to have had structural flaws which caused other languages to overtake it. Pascal was fairly low level yet it lacked good low level interfaces. Which is why it lost out to C. Pascal supports admit this and one of the main directions of Turbo Pascal / Delphi was to introduce into Pascal handling for lower level code (example partial compilation).

      If you think of Pascal as a higher level language where bad handling of low level code is acceptable it also wasn't competitive. Pascal is strongly typed but has a poor type system without abstractions. Making types difficult to work with under almost all conditions. It had poor handling of static vs. dynamic data including things like abstracting networks or file systems. There are lots of sacrifices in organization for ease in writing small compilers. A very good choice for early 1980s PC compilers that had to run off a floppy not a good choice since. The languages strictness on looping structures tended to result in duplicate code.

      Etc... Pascal was a partial success. But it died for good reasons.

    15. Re:Pascal-based? by squiggleslash · · Score: 1

      APK does. He's boasted several times his Hosts file manager is written in Delphi, which is apparently an Object Pascal implementation and the successor to Turbo Pascal.

      --
      You are not alone. This is not normal. None of this is normal.
    16. Re:Pascal-based? by angel'o'sphere · · Score: 1

      Sorry but eveything you write about Pascal is wrong. But I'm to lazy to correct it, you can read wikipedia.
      You clearly never used it, so why write that bullshit?

      Pascal, especially as UCSD P-System was for decades the most widely used 'OS' and programming language on the planet.

      --
      Cost free eBook I read (by iBook/Kobo/Amazon/ObookO/Gutenberg etc.): "The Green Odyssey" by Philip Jose Farmer.
    17. Re:Pascal-based? by angel'o'sphere · · Score: 1

      He meant Pascal, the human. Not Pascal, the language.
      And Pascal as languge is as good as C in doing math ... or basically every pro edural language.

      --
      Cost free eBook I read (by iBook/Kobo/Amazon/ObookO/Gutenberg etc.): "The Green Odyssey" by Philip Jose Farmer.
    18. Re:Pascal-based? by angel'o'sphere · · Score: 1

      You should read the relevant wikipedia articles :)

      --
      Cost free eBook I read (by iBook/Kobo/Amazon/ObookO/Gutenberg etc.): "The Green Odyssey" by Philip Jose Farmer.
    19. Re:Pascal-based? by jimtheowl · · Score: 1

      I don't know if other languages overtook Pascal because of 'structural flaws', but I myself adopted C over Pascal because at the time it was obviously better for raw power and speed. This is true for the processors and architectures that I have developed on (6502/x86/SPARC/AMD64).

      As much as I love C, it is not a good fit on other architectures such as stack machines. Burroughs machines (now UNISYS) use an extended version of ALGOL as a system language with impressive results, especially when it comes to security (not vulnerable to buffer overflows).

      I am a C programmer at heart, but have an argument with your assumption that Pascal (or related languages) is dead. I could be wrong, but I think you may be brushing off its merits based on the widespread architecture of today.

      Yet, you may have hit the nail when saying it is about the Pascal chip, but that doesn't exclude the language - it makes it a holistic part of the system design.

  2. Not alone by SuperKendall · · Score: 2

    That is actually the first thing that sprang to mind, even though I had been looking specifically at Pascal based GPU's recently. :-)

    --
    "There is more worth loving than we have strength to love." - Brian Jay Stanley
    1. Re:Not alone by gander666 · · Score: 1

      Ditto here. I had some memories of long dead undergrad programming courses.

      --
      Suppose you were an idiot and suppose you were a member of Congress ... but I repeat myself. - Mark T
    2. Re:Not alone by Anonymous Coward · · Score: 1

      I'm older school and keep hoping for an ALGOL supercomputer.

    3. Re:Not alone by Applehu+Akbar · · Score: 2

      "Ditto here. I had some memories of long dead undergrad programming courses."

      Yes, Pascal, really? If we're going to invoke the age of steam, why not go full Fortran with this project?

    4. Re:Not alone by JanneM · · Score: 1

      Fortran is still very much in use for mathematical programming.

      --
      Trust the Computer. The Computer is your friend.
    5. Re:Not alone by Darinbob · · Score: 2

      Makes no sense. Pascal is a perfectly fine language, even classic Pascal. Fortran, especially classic Fortran 77, is really lacking in many ways (newer versions add newer features but that's like comparing Visual Basic to Basic and trying to call them the same language). Granted Modula-II or Ada is much more suitable than Pascal.

    6. Re:Not alone by Applehu+Akbar · · Score: 1

      Latin is older than English, but a thousand times better as a language.

      The value of Latin is not that it's "better" in modern usage but that as a root of so many later European languages, it is easily used as a lingua franca for European speakers. An Italian MD, a British MD and a French MD all understand what bis in diem on a prescription vial means.

    7. Re:Not alone by JustAnotherOldGuy · · Score: 1

      Latin is older than English, but a thousand times better as a language.

      Which must be why it's used so today. Oh, wait....

      --
      Just cruising through this digital world at 33 1/3 rpm...
    8. Re:Not alone by JustAnotherOldGuy · · Score: 2

      "English is a language that lurks in dark alleys, beats up other languages and rifles through their pockets for spare vocabulary."

      --attributed to James D. Nicoll

      The original, complete quote appears to be:

      "The problem with defending the purity of the English language is that English is about as pure as a cribhouse whore. We don’t just borrow words; on occasion, English has pursued other languages down alleyways to beat them unconscious and rifle their pockets for new vocabulary."

      --
      Just cruising through this digital world at 33 1/3 rpm...
    9. Re:Not alone by Anonymous Coward · · Score: 1

      Your position might be viewed as an example of fallacy of the single cause with elements of argumentum ad populum. -PCP

    10. Re:Not alone by paai · · Score: 1

      Perhaps APL should be revived. Imagine the money to be made by keyboard manufacturers.

      Paai

    11. Re:Not alone by mikael · · Score: 1

      I'm worried the animal activists might take offence at peta-flops.

      --
      Vintage computer adverts: http://www.vintageadbrowser.com/computers-and-software-ads
    12. Re:Not alone by Anne+Thwacks · · Score: 1
      ALGOL supercomputer.

      Now we have multi-threading, Algol68 might actually be the best choice. However, history supports C-more Cray.

      --
      Sent from my ASR33 using ASCII
    13. Re:Not alone by Godwin+O'Hitler · · Score: 1

      Yes, I too would rather have a language with a million inflections to save a dozen pronouns and structured so inflexibly that you have to add a zillion articles and conjunctions.

      --
      No, your children are not the special ones. Nor are your pets.
    14. Re:Not alone by RespekMyAthorati · · Score: 1

      Fortran, especially classic Fortran 77, is really lacking in many ways

      But perfectly adequate for solving differential equations, which is the main task of scientific and engineering programs.

    15. Re:Not alone by michael_wojcik · · Score: 1

      APL was effectively superseded by the J language.

      I taught myself some APL[1] using a standard keyboard and an APL implementation that ran on OS/2, if memory serves. Wasn't bad. Yes, you had to compose all the APL characters using Alt-key sequences[2], but APL is so terse that you didn't have to do it very often.

      J uses ASCII rather than APL's grab-bag of symbols. I'm not sure I'd call it more readable, though.

      It would be interesting to see a less-opaque Iverson-Backus language, with the matrix operators and tacit-programming features.

      [1] Because I believe it's useful to try as many programming-language paradigms as possible, and because I'd read Iverson's and Backus' Turing Award addresses.

      [2] Can't remember whether Alt-Right gave you the GoTo operator or the NarcissisticPersonalityDisorder operator.

    16. Re:Not alone by painandgreed · · Score: 1

      Latin is older than English, but a thousand times better as a language.

      Which must be why it's used so today. Oh, wait....

      Saw an article on a study once about the value of either language standardization and regularness versus freeform and irregular usage given between the examples of French and English. It seems that the irregular and modifyable nature of English actually helps more towards usage and adoption than standardization.

  3. Good for them... by Arkh89 · · Score: 1

    These P100 come with sweet HBM2 and around 500GB/s in memory bandwidth... everything based on dense linear algebra (AI, but also physics simulations) is basically flying on them.

  4. Extra Crispy by fyngyrz · · Score: 2

    experimental immersion-cooled Tsubame-KFC system

    I'm sorry, but I like my KFC hot from the fryer. This experiment should end immediately.

    --
    I've fallen off your lawn, and I can't get up.
    1. Re:Extra Crispy by fyngyrz · · Score: 1

      KFC and fried foods in general are fucking horrible.

      Well, there's your problem, right there. Why not try the appropriate product which was meant for that instead?

      No, no need to thank me. Where would the world be if us experienced types didn't pass along our wisdom to the clueless?

      --
      I've fallen off your lawn, and I can't get up.
  5. Re:Tsubame-KFC by Anonymous Coward · · Score: 2, Informative

    Kepler Fluid Cooled, though Tsubame is a kind of bird and the computers are indeed immersed in oil.

    Also Japan has an unusual tradition of eating KFC for Christmas with reservations made months in advance.

  6. Re:Tsubame-KFC by cant_get_a_good_nick · · Score: 1

    For some reason, Kernel Sanders made me think of Dr Fun: Kernel Panic

    For those that don't know, Dr Fun was the first webcomic 520 weeks, or 10 years worth

  7. Re:Good ol' days by MightyMartian · · Score: 1

    I had a pretty deep fondness for Pascal back in the day, and messed around with Delphi, Modula and Oberon, but the reality is that these aren't exactly common languages anymore, at least not in commercial circles. It's a real pity too, because learning TurboPascal was my sort of "Wizard of Oz black-and-white to color" moment back in highschool, where I shed all the evils that I had learned through mucking around with various flavors of BASIC, and basked in the glory of structured procedural code.

    --
    The world's burning. Moped Jesus spotted on I50. Details at 11.
  8. Re:Good ol' days by Aighearach · · Score: 1

    I thought all Pascal use was for BBS DOOR games, and the internet killed it?

  9. Re:Oh Yeah by Crashmarik · · Score: 2

    I am going to make make a supercomputer that runs on BASIC A.

    Whom the gods would destroy, first they teach basic.

  10. RTFA by subk · · Score: 3, Insightful

    Pascal, the GPU design. Not Pascal, the language.

    --
    Now, if you'll excuse me, I have backups to corrupt.
    1. Re:RTFA by Hognoxious · · Score: 2

      It does make one wonder what they were thinking - if they were at all - when they chose the name.

      --
      Confucius say, "Find worm in apple - bad. Find half a worm - worse."
    2. Re:RTFA by Walter+White · · Score: 2

      Pascal, the GPU design. Not Pascal, the language.

      So... It won't run Delphi then?

    3. Re:RTFA by Walter+White · · Score: 1

      Delphi closed, along with BIX, Prodogy and all the other AOL like online services of the early 90s.

      They're all gone? Compuserve too? Sad!

    4. Re:RTFA by Hognoxious · · Score: 1

      Probably true, but irrelevant. The point is that they didn't think to check if the word was already in use in a related context.

      --
      Confucius say, "Find worm in apple - bad. Find half a worm - worse."
  11. Re:Yay! by jimtheowl · · Score: 2

    You do not need to. Free Pascal is well and alive on multiple platforms and is open source. http://www.freepascal.org/

  12. One of few people by TheOuterLinux · · Score: 1

    I think I'm one of few people that actual likes Pascal. Also prefer Python over JAVA and never really cared for C all that much even though there are similarities. Anyone like or use MyNotex (Linux)? Written in with Pascal. ;)

  13. GPUs have limited applications by 140Mandak262Jamuna · · Score: 3, Insightful
    It keeps coming back. Massively parallel machine, thousands of cores all working in parallel. Naively multiply add up all the megaflops and get some massive number and tout it big. We can simply add all the flops of all the servers in some Amazon cloud and claim that is the super computer. Back in the 80s "transputer" was all the rage. Before that it was the "vector" computers. Then "the network *is* the computer", then GPUs...

    As of now there are very few applications for massively souped up GPU processes. Fluid mechanics loves this GPU. Navier-Stokes is probably the most difficult equation to solve, agreed. But it is hyperbolic, with limited "zone of influence", and numerical equations are quite simple, just mass, momentum and energy balances in the control volume. It plays well in GPU, the calculations fit inside the teensy memory and processor. All time domain problems are hyperbolic and they all can be ported to GPU, theoretically. But try squeezing Maxwell's Equations into that teensy processor!

    Graphics card companies are desperately looking for new markets and they keep pushing this. They might as well push a wet noodle across the table. It ain't gonna go nowhere it didn't wanna go.

    --
    sed -e 's/Chuck Norris/Rajnikant/g' joke > fact
    1. Re:GPUs have limited applications by cheesybagel · · Score: 1

      I wouldn't call a modern GPU that constrained really. The only thing they lack is memory protection. It's also a lot easier to program on a GPU ever since the SIMT paradigm came out (i.e. CUDA, OpenCL). Also plenty of modern processors come with a GPU on the same die as the CPU. Like nearly all smartphones for example.

    2. Re:GPUs have limited applications by slew · · Score: 1

      I wouldn't call a modern GPU that constrained really. The only thing they lack is memory protection. It's also a lot easier to program on a GPU ever since the SIMT paradigm came out (i.e. CUDA, OpenCL). Also plenty of modern processors come with a GPU on the same die as the CPU. Like nearly all smartphones for example.

      Actually all modern GPU have had memory protection for several generations. The problem GPUs have is that don't generally have full support for demand paging and precise exceptions (SIMT makes that pretty expensive). For example, putting in hardware for highest possible performance and hardware to be able to hit a page fault and be able to clean up and restart multiple threads (that might be communicating or synchronizing states) are two different hardware optimization points. That being said, some limited support for demand paging is generally possible.

    3. Re:GPUs have limited applications by slew · · Score: 1

      GPUs are problematic because there's not a good way to compute matrix factorizations on them.

      Have you looked at this paper on large matrix factorization?

    4. Re:GPUs have limited applications by religionofpeas · · Score: 1

      This one is targeted towards neural nets. Does that work ?

    5. Re:GPUs have limited applications by 140Mandak262Jamuna · · Score: 1

      I don't know neural networks. Computational physics, applied math background.

      --
      sed -e 's/Chuck Norris/Rajnikant/g' joke > fact
    6. Re:GPUs have limited applications by 140Mandak262Jamuna · · Score: 1

      Problem is Maxwell is the null space of the curl vector. It results in a rank deficient matrix, without unique solution. It wasn't until 1980 they figured out a way to subtract the null space and uniquify the solution. But that matrix does not have diagonal dominance. So all iterative methods are out. The condition number is very poor. LU decomposition is the only way out. And the unknowns are complex vectors. Not simple scalars like density, pressure and one real velocity vector for NS. Squeezing it all inside a GPU processor is very difficult.

      --
      sed -e 's/Chuck Norris/Rajnikant/g' joke > fact
  14. Pascal? by hublan · · Score: 1

    Making all the other supercomputers Wirth-less.

    --
    My spoon is too big.
    1. Re:Pascal? by slew · · Score: 1

      Making all the other supercomputers Wirth-less.

      Or by name, Veert-ually worthless...

  15. Re:Good ol' days - blame p2c by Anonymous Coward · · Score: 1

    One it was realized you could mechanically translate Pascal to C, then compile the C and get a 2-3x speed up (compared to interpreting p-code), Pascal started dying.

    C has issues, but in practice it has less of them than Pascal, so the resulting code was easy to tweak to get even more performance.

  16. Re:Good ol' days by cheesybagel · · Score: 2

    Pascal usage quickly shrank. I'm not quite sure why, it was a fairly decent compiler-based language.

    I am pretty sure why. More modern operating systems came up and nearly invariably they were all C based. If you wanted to call the OS libraries you were better off using C. That's why Pascal died off.

  17. Borland by s.petry · · Score: 2

    Delphi.. Ohhh such wonderful memories..

    --

    -The wise argue that there are few absolutes, the fool argues that there are no probabilities.

    1. Re:Borland by haruchai · · Score: 1

      Delphi.. Ohhh such wonderful memories..

      I've heard its latest incarnation as Embarcadero Delphi is quite good but I'm no judge of programming environments

      --
      Pain is merely failure leaving the body
  18. Re:Chicken vs. Swallow by hackwrench · · Score: 1

    And you probably prefer your KFC to be chicken and not swallow, which is what Tsubame means.

  19. Re:Oh Yeah by hackwrench · · Score: 1

    And the first step to destroy the gods is to learn BASIC. The next step is to learn how to create and embed your own commands into a BASIC compiler. But tread carefully! The believers in the gods seek out those who would destroy the gods. A man named Steve McNeill, http://www.qb64.net/forum/inde... started down that path and was brought low, and a recent accounting of his tale was scrubbed from the annals of http://www.qb64.net/forum/inde...

  20. Re:Good ol' days by phantomfive · · Score: 1

    It also allowed nesting of functions.

    FWIW GCC allows that now in C.

    --
    "First they came for the slanderers and i said nothing."
  21. Re:Good ol' days by paai · · Score: 1

    Faster hardware is not always a boon. Now we have Java monsters that eat up all the performance of even decent hardware. Easy to learn? Nah, with the myriads of different libraries and paths it is a conceptual mess. And it was supposed to be the cure-all for viruses, but that has not materialized either.

    The good Lord gave us C, Bash and the CLI , and we frail humans should not presume to improve on His creation.

    Paai

  22. Re: Good ol' days by dunkelfalke · · Score: 1

    It is good that I am an atheist, then.

    --
    "It's such a fine line between stupid and clever" -- David St. Hubbins, Spinal Tap
  23. Re:Chicken vs. Swallow by fyngyrz · · Score: 1

    Precisely so. Well played. :)

    --
    I've fallen off your lawn, and I can't get up.
  24. Re:Good ol' days by angel'o'sphere · · Score: 1

    You can call a C library or OS functiom from Pascal, too.
    There is no difference.

    C is not something magically, you know ...

    --
    Cost free eBook I read (by iBook/Kobo/Amazon/ObookO/Gutenberg etc.): "The Green Odyssey" by Philip Jose Farmer.
  25. Re:Good ol' days by haruchai · · Score: 1

    Faster hardware is not always a boon. Now we have Java monsters that eat up all the performance of even decent hardware. Easy to learn? Nah, with the myriads of different libraries and paths it is a conceptual mess. And it was supposed to be the cure-all for viruses, but that has not materialized either.

    The good Lord gave us C, Bash and the CLI , and we frail humans should not presume to improve on His creation.

    Paai

    Those are tools of the Devil; on the 1st day, the Lord created binary, microcode and logic gates and saw that it was good.

    --
    Pain is merely failure leaving the body
  26. Re:Good ol' days by cheesybagel · · Score: 1

    I don't know if there is any difference between calling conventions, but the mere fact you would have to write your own headers in Pascal seems pretty significant to me.

  27. Re:Good ol' days by angel'o'sphere · · Score: 1

    Ofc, there are different calling conventions.
    Usually C pushes arguments from left to right onto the stack and the caller cleans up the stack (because of variable argument lists), in Pascal arguments get pushed from right to left and the called procedure/fuction cleans up the stack.

    Interfacing with C you usually do via so called 'units'. Units have an interface section and an implementation section. In the interface section you define functions/procedures and call also define if they are written in a different language (Assembly, C, Fortran), unfortunately there is no standard how to do that exactly. (Implementation section would be empty and you have to link with the relevant C library, ofc.)

    Most C compilers also used to support 'extern PASCAL' or 'extern FORTRAN' keywords/declarations. But again I think there is no standard for that.

    --
    Cost free eBook I read (by iBook/Kobo/Amazon/ObookO/Gutenberg etc.): "The Green Odyssey" by Philip Jose Farmer.