Nvidia GT300 core: Speculation

Discussion in 'Architecture and Products' started by Shtal, Jul 20, 2008.

Thread Status:
Not open for further replies.
  1. chavvdarrr

    Veteran

    Joined:
    Feb 25, 2003
    Messages:
    1,165
    Likes Received:
    34
    Location:
    Sofia, BG
    1 day in near future, a writing on the screen when starting your brand new IBM PC compatible...


    "no CPU detected, starting software emulation"

    LOL
     
  2. MfA

    MfA
    Legend

    Joined:
    Feb 6, 2002
    Messages:
    6,743
    Likes Received:
    469
    It's not really a big deal, hell there are C++ to C translators ... although I fail to see the point of Fortran apart from the warm and fuzzy feeling the name generates. It's not like even porting legacy code to it is an option, the level of algorithmic changes needed to suit a GPU make a rewrite the only realistic option. Fortran doesn't seem to me to be a great language to write kernels in.

    PS. http://www.pgroup.com/resources/cudafortran.htm
     
  3. trinibwoy

    trinibwoy Meh
    Legend

    Joined:
    Mar 17, 2004
    Messages:
    10,426
    Likes Received:
    423
    Location:
    New York
    Well the question is what features of C++ do they currently NOT support? The answer to that question would probably provide hints as to what else they've changed
     
  4. Scali

    Regular

    Joined:
    Nov 19, 2003
    Messages:
    2,127
    Likes Received:
    0
    I think the biggest issue is that of using function pointers. A lot of the object-oriented features of C++ are implemented through the manipulation of function pointers. As far as I know, they could only branch with fixed offset so far .
     
  5. MfA

    MfA
    Legend

    Joined:
    Feb 6, 2002
    Messages:
    6,743
    Likes Received:
    469
    Aren't those required for DX11?
     
  6. rpg.314

    Veteran

    Joined:
    Jul 21, 2008
    Messages:
    4,298
    Likes Received:
    0
    Location:
    /
    The biggest C++ change would be new and delete inside kernels.
     
  7. muzux2

    Newcomer

    Joined:
    Jan 31, 2009
    Messages:
    2
    Likes Received:
    0
    Location:
    India
    i think, GT300 packs an additional SM(Stream multiproceesor) up from 3 in GT200 and 16 TPC up from 10 in GT200..

    As G80 had 8 TPCs with 2 SMs inside each TPC. Each SMs contains 8 SPs, thus have total of 16 SPs in each TPC, equals total of 128 SPs

    8(TPC) * (8 * 2) = 128

    GT200 had 10 TPC with 3 SMs inside each TPC. Each SMs contains 8 SPs, thus have total of 24 SPs in each TPC, equals total of 240 SPs

    10(TPC) * (8 * 3) = 240

    Now according to BSN rumour, i think, GT300 will have 16 TPC with 4 SMs inside each TPC. Each SMs containing 8 SPs, thus will have total of 32 SPs in each TPC, equals total
    of 512 SPs..

    16 (TPC) * (8 * 4) = 512


    GT300 might be GT200 on Steriods... i may be wrong
     
  8. trinibwoy

    trinibwoy Meh
    Legend

    Joined:
    Mar 17, 2004
    Messages:
    10,426
    Likes Received:
    423
    Location:
    New York
    It's really shaping up like Nvidia built Larrabee while Intel was talking about building it. I'm itching to know what fixed function stuff they might have gotten rid of, or if there are any changes to the rendering pipeline.

    According to Rys, you are :)
     
  9. Scali

    Regular

    Joined:
    Nov 19, 2003
    Messages:
    2,127
    Likes Received:
    0
    Didn't think so... but I'm talking about current hardware here.
     
  10. Ailuros

    Ailuros Epsilon plus three
    Legend Subscriber

    Joined:
    Feb 7, 2002
    Messages:
    9,416
    Likes Received:
    178
    Location:
    Chania
    It might be a big deal for the lazy ones out there *shrugs*
     
  11. Scali

    Regular

    Joined:
    Nov 19, 2003
    Messages:
    2,127
    Likes Received:
    0
    I don't think those will work, since 'C for Cuda' isn't fully ANSI C. C++ can only be translated to C if it supports all features... like I said, function pointers are key to the object model.
     
  12. Bouncing Zabaglione Bros.

    Legend

    Joined:
    Jun 24, 2003
    Messages:
    6,363
    Likes Received:
    82
    If it's true, it looks like Nvidia went GPU->CPU while Intel are trying to do CPU->GPU ie both trying to solve the same problems from opposite starting points. It's certainly a very ambitious approach and a big step towards convergence of GPU/CPU.

    I guess all those questions about Nvdia not having a x86 licence are kind of moot if you can talk to the new chip via a compiler the same way as you talk to any CPU.
     
  13. Arty

    Arty KEPLER
    Veteran

    Joined:
    Jun 16, 2005
    Messages:
    1,906
    Likes Received:
    55
    Very typical of Theo, convenient how both hardware-Infos & bsn come out with this 'exclusive' 'breaking' news story AFTER Rys' hint :D

    By the way, when is the webcast? (est)
     
  14. Ailuros

    Ailuros Epsilon plus three
    Legend Subscriber

    Joined:
    Feb 7, 2002
    Messages:
    9,416
    Likes Received:
    178
    Location:
    Chania
    There's a huge difference between an educated hw analysis and being first and 2nd at nothing.:shock:
     
  15. KimB

    Legend

    Joined:
    May 28, 2002
    Messages:
    12,882
    Likes Received:
    207
    Location:
    Seattle, WA
    Quite a lot of scientific work is still done in Fortran, and though it is possible to get Fortran and C/C++ to play together, it can be difficult and fraught with difficulties with compiling properly. So having a native Fortran version of Cuda could be a boon for getting it adopted within the scientific community.
     
  16. Scali

    Regular

    Joined:
    Nov 19, 2003
    Messages:
    2,127
    Likes Received:
    0
  17. trinibwoy

    trinibwoy Meh
    Legend

    Joined:
    Mar 17, 2004
    Messages:
    10,426
    Likes Received:
    423
    Location:
    New York
  18. 3dilettante

    Legend Alpha

    Joined:
    Sep 15, 2003
    Messages:
    8,122
    Likes Received:
    2,873
    Location:
    Well within 3d
    The Rys blur-o-gram had a lot of the same colors in the area that the GT200 one had for shader and triangle setup. It looks like there's still some kind of texture block.
    The compute portion appears to be heavily reworked, and the area that was the ROP section is still there, but I can't infer much from a gray (oddly dark gray...) smudge.

    If the setup, texturing, and ROP specialized sections persist, the Fermi architecture would be the answer to the question "what if we made Larrabee without x86, and gave it ROPs and a rasterizer?"
    The next question would be, "what if we built Larrabee with an inferior process", but I digress.

    The rumors seem to reflect that the birthing process for this new chip could have been smoother.

    I'm not sure.
    They are pretty small, and they are structured to provide peak bandwidth for the common case of filtered texture fetches.
    I'm not sure how much of their behavior changes if they are tasked with linearly addressed memory. If the data is structured to make the most of them, then their bandwidth can be used.
    Their size and read-only nature makes them less than generally useful.
     
  19. MfA

    MfA
    Legend

    Joined:
    Feb 6, 2002
    Messages:
    6,743
    Likes Received:
    469
    Wouldn't that be NVIDIA's hint? (If you're under NDA you tell what you are told you can tell.)
     
  20. dnavas

    Regular

    Joined:
    Apr 12, 2004
    Messages:
    375
    Likes Received:
    7
    Wow, no wonder the parking lot was full late last night! I thought we had a couple of weeks to go. I wonder if they brought the demo forward for competitive reasons?

    Also, I realize Rys says everything has changed, but:
    1) 16kb per 8-wide set of SPs does actually work out
    2) I like that there are four blue dots and four sets of SPs in there
    3) I wonder what bits in the chip run the C++ code
    4) If DP runs half-speed, they really have done some work in there.
    5) Isn't it great that each SP can run an instruction per clock per thread? Why, all I have to do to increase performance is add more threads! Infinite TFlops!
     
Loading...
Thread Status:
Not open for further replies.

Share This Page

  • About Us

    Beyond3D has been around for over a decade and prides itself on being the best place on the web for in-depth, technically-driven discussion and analysis of 3D graphics hardware. If you love pixels and transistors, you've come to the right place!

    Beyond3D is proudly published by GPU Tools Ltd.
Loading...