1. Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.

Intel Reveals Architecture Details of Intel Xeon Phi Co-Processor

Discussion in 'News' started by btarunr, Aug 31, 2012.

  1. btarunr

    btarunr Editor & Senior Moderator Staff Member

    Joined:
    Oct 9, 2007
    Messages:
    28,965 (11.00/day)
    Thanks Received:
    13,757
    Location:
    Hyderabad, India
    During HotChips symposium, George Chrysos, the leading architect of Intel Xeon Phi co-processor shared the new architecture details of upcoming Intel's HPC powerhouse. Designed for highly-parallel applications, Intel Xeon Phi co-processor based on Intel Mani Integrated Core architecture will deliver the combination of industry leading performance per watt with the ability to re-use the existing code and applications without necessity of re-writing them.

    Equipped with more than 50 cores and built using Intel's latest 22nm 3D Tri-gate transistor technology, new co-processors will be in production this year with first supercomputers from top500 list already taking advantage of this technology. In his blog here, George shares his aspirations and goals during designing the co-processor and summarizes all new disclosed information. The HotChips presentation is also available below.

    [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG] [​IMG]
     
    ChristTheGreat, NHKS and m1dg3t say thanks.
  2. Eva01Master

    Joined:
    Feb 27, 2009
    Messages:
    75 (0.04/day)
    Thanks Received:
    5
    Location:
    Caracas/Venezuela.
    This is just what I was looking for, now my browser games will run smoothly XD.
     
  3. m1dg3t

    m1dg3t

    Joined:
    May 22, 2010
    Messages:
    2,247 (1.34/day)
    Thanks Received:
    513
    Location:
    Canada
    Ha ha! Yes! :)
     
  4. Mussels

    Mussels Moderprator Staff Member

    Joined:
    Oct 6, 2004
    Messages:
    42,556 (11.41/day)
    Thanks Received:
    9,828
    so this is what became of larrabee
     
    FordGT90Concept and INSTG8R say thanks.
  5. TRWOV

    TRWOV

    Joined:
    Aug 11, 2011
    Messages:
    3,755 (3.05/day)
    Thanks Received:
    2,341
    Location:
    Mexico
    It's like the Ageia PPU all over again... also, when would I be able to put one in my tower to encode my porn? :)
     
    Crunching for Team TPU
  6. eidairaman1

    eidairaman1

    Joined:
    Jul 2, 2007
    Messages:
    13,646 (5.00/day)
    Thanks Received:
    1,858
    Go Get Laid Heh
     
  7. INSTG8R

    INSTG8R

    Joined:
    Nov 26, 2004
    Messages:
    3,067 (0.83/day)
    Thanks Received:
    550
    Location:
    Lost in Norway
    That's the bells that went off in my head as well.
     
  8. Completely Bonkers New Member

    Joined:
    Feb 6, 2007
    Messages:
    2,580 (0.90/day)
    Thanks Received:
    516
    Rather lackluster in my opinion. It is a "me too". Intel Knights Corner does not make any leaps ahead of the competition. It is neck and neck. And performance per watt improvements? Marginal given they havent launched yet and the competitors architecture is more than a year old. According to Moore, Intel should be at least 2x ahead of last years offerings from nV and AMD.

    In fact, they are probably behind. That chart (slide 5) with 1381 vs. 1380 was finagled for the boss so that the team didn't lose their jobs!
     
  9. FordGT90Concept

    FordGT90Concept "I go fast!1!11!1!"

    Joined:
    Oct 13, 2008
    Messages:
    14,110 (6.24/day)
    Thanks Received:
    3,929
    Location:
    IA, USA
    It is x86. That is the "leaps ahead of the competition." You don't need to code for it, just recompile for it. It makes developing software so much easier. Not to mention, it's also better at scientific applications because it has higher double precision float performance because x86 is designed to do that--not so much GPUs converted to GPGPU use.
     
    jihadjoe, ChristTheGreat and Chevalr1c say thanks.
    Crunching for Team TPU
  10. Delta6326

    Delta6326

    Joined:
    May 21, 2008
    Messages:
    3,842 (1.60/day)
    Thanks Received:
    670
    Location:
    Iowa, USA
    Sounds interesting still wish intel would join the other GPU makers so that prices would go down.
     
  11. largon

    largon

    Joined:
    May 6, 2005
    Messages:
    2,782 (0.79/day)
    Thanks Received:
    433
    Location:
    Tre, Suomi Finland
    Strange.
    .
    .
    .
    Nobody has (yet) complained about PCB color (slide 4).
    Well, he is encoding it. Perhaps he's a home cinematics aficionado?
    [​IMG] :p
     
  12. Completely Bonkers New Member

    Joined:
    Feb 6, 2007
    Messages:
    2,580 (0.90/day)
    Thanks Received:
    516
    Without doubt, x86 means quicker and cheaper re-use/factor of existing code. Great. But looking at slide 5 it doesnt look that KC is computationally much faster. Cheaper. Faster to code. But not necessarily faster to compute. I don't know the details of the Floating Point tests that were done, but it may well be that there are a set of problems where KC will clearly win (ie. double precision problems). However, most computational problems are not double-precision, and also keep in mind that KC is double-precision and not x86 (which is extended 80-bit float since the x87 days). So when moving x87 code to KC you need to be careful!
     
  13. FordGT90Concept

    FordGT90Concept "I go fast!1!11!1!"

    Joined:
    Oct 13, 2008
    Messages:
    14,110 (6.24/day)
    Thanks Received:
    3,929
    Location:
    IA, USA
    There is a penalty for x86 versus what is effectively machine code on other GPGPUs but Intel makes up for that with smaller fab.


    In scientific applications, double precision is yearned for. The only reason why everything isn't double precision is because, until recently, graphics cards either didn't support double precision or took a huge performance penalty if they did double precision. These cards are going to end up in multi-million dollar science-conducting machines. Double precision performance is going to be a huge selling point for these cards.
     
    Chevalr1c says thanks.
    Crunching for Team TPU
  14. deleted New Member

    Joined:
    Jan 12, 2011
    Messages:
    80 (0.06/day)
    Thanks Received:
    14
    The most important thing about these cards is that they're normal x86 processors and don't require any sort of special consideration (although optimization is always nice). It's basically 50 Pentium Is with Sandy Bridge FPUs tacked onto them, fabbed on a 22nm process.
     
  15. Morgoth

    Morgoth

    Joined:
    Aug 4, 2007
    Messages:
    3,795 (1.41/day)
    Thanks Received:
    250
    Location:
    Netherlands
    [​IMG]
     
    ChristTheGreat says thanks.
  16. suraswami

    suraswami

    Joined:
    Apr 5, 2005
    Messages:
    6,253 (1.76/day)
    Thanks Received:
    837
    Location:
    Republic of Asia (a.k.a Irvine), CA
    Is this something to do with Graphics (like video card, APU etc)?
     
  17. TRWOV

    TRWOV

    Joined:
    Aug 11, 2011
    Messages:
    3,755 (3.05/day)
    Thanks Received:
    2,341
    Location:
    Mexico
    more like physics, rendering and video encoding. Also HPC (its main intended market) but that's hardly of interest for the common folk. :)

    Basically it's a 50 Pentium Pro cluster in an add-on card. Can't wait for some of these to appear in retail... in a couple of years. :banghead:
     
    Crunching for Team TPU
  18. theoneandonlymrk

    theoneandonlymrk

    Joined:
    Mar 10, 2010
    Messages:
    3,414 (1.95/day)
    Thanks Received:
    573
    Location:
    Manchester uk
    They are Now physics cards lol, its a direct stepping decendant of larrabee, and it from what i have previously seen it would take 3 sli'd or intelied or whatever to run crysis, I do want one though and its interesting to me that they run a lynux kernal on each core of it, linked virtually via regular net protocals, like a hive virually inside your rig, ill takes 3:D:cool:
     
  19. Jizzler

    Jizzler

    Joined:
    Aug 10, 2007
    Messages:
    3,464 (1.29/day)
    Thanks Received:
    650
    Location:
    Geneva, FL, USA
    Yeah, it took 8 of the slower 32-core models to do Wolfenstein:

    [​IMG]

    Three or four of these new Phi's could do it, and in a couple years it'll only take one.
     
  20. cadaveca

    cadaveca My name is Dave

    Joined:
    Apr 10, 2006
    Messages:
    14,138 (4.45/day)
    Thanks Received:
    7,331
    Location:
    Edmonton, Alberta
    HOly crap that's an interesting picture!
     
  21. ChristTheGreat

    ChristTheGreat

    Joined:
    Jun 29, 2007
    Messages:
    973 (0.36/day)
    Thanks Received:
    474
    can't wait to see the power consumption of this, Might be good for crunching :D
     
    Crunching for Team TPU
  22. james888

    james888

    Joined:
    Jun 27, 2011
    Messages:
    4,746 (3.72/day)
    Thanks Received:
    1,956
    I look at this. I think its cool. I then get an "I want one" feeling. I just don't have a good use for it. I don't encode often or fold. Still though, MOAR POWA!
     
    Crunching for Team TPU
  23. Morgoth

    Morgoth

    Joined:
    Aug 4, 2007
    Messages:
    3,795 (1.41/day)
    Thanks Received:
    250
    Location:
    Netherlands
    i would want to get one if valve batch compile get supports up to 64 threads now it only does 16 threads
     
  24. deleted New Member

    Joined:
    Jan 12, 2011
    Messages:
    80 (0.06/day)
    Thanks Received:
    14
    You forgot the part where it was raytracing the entire thing in real time. Kepler doesn't even come close to that.
     
  25. Steevo

    Steevo

    Joined:
    Nov 4, 2005
    Messages:
    8,551 (2.56/day)
    Thanks Received:
    1,314
    A ring bus for memory controller, and a 4X1, and 2X1 setup on "streaming" scalar units? Looks like a X1xxx series to me, just grown up a bit and tweaked for processes.


    Their X86 interface is the same idea behind AMD's "Fabric", one interface that handles the requests and issues them to the faster or least busy of the CPU cores, or GPU "shaders".


    Larrabee, plus all the IP that AMD handed over a couple years ago to Intel as part of the monopoly payment/trade.
     
    10 Million points folded for TPU

Currently Active Users Viewing This Thread: 1 (0 members and 1 guest)

Share This Page