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

NVIDIA Taunts AMD's GCN Architecture Performance

Discussion in 'News' started by btarunr, Jan 25, 2012.

  1. Andrei23 New Member

    Joined:
    Dec 30, 2010
    Messages:
    243 (0.17/day)
    Thanks Received:
    25
    Until Nvidia actually comes up with something good to counter AMD's efforts it needs to shut it's f***ing mouth.
     
  2. Fluffmeister

    Fluffmeister

    Joined:
    Dec 22, 2011
    Messages:
    712 (0.67/day)
    Thanks Received:
    207
    Wow, so much anger and hatred based on one off the cuff remark.

    Chill out.:twitch:
     
  3. EastCoasthandle

    EastCoasthandle New Member

    Joined:
    Apr 21, 2005
    Messages:
    6,889 (1.97/day)
    Thanks Received:
    1,505
    Here is something even more interesting.
     
  4. wiak

    wiak

    Joined:
    Sep 5, 2004
    Messages:
    1,747 (0.47/day)
    Thanks Received:
    200
    Location:
    Norway
    this aint news, everyone know nvidia will be faster and use alot more power, its a matter of how nvidia works
     
  5. erocker

    erocker Super Moderator Staff Member

    Joined:
    Jul 19, 2006
    Messages:
    39,882 (13.09/day)
    Thanks Received:
    14,280
    Even translated I can barely understand what they are saying.
     
  6. OneCool

    OneCool

    Joined:
    Nov 27, 2005
    Messages:
    849 (0.26/day)
    Thanks Received:
    68
    Location:
    Look behind you!!

    I was killing brain cells trying to read it in Google translate :wtf: :roll:
     
  7. ViperXTR

    ViperXTR

    Joined:
    Jan 31, 2011
    Messages:
    1,394 (1.00/day)
    Thanks Received:
    407
    acerace and eidairaman1 say thanks.
  8. seronx

    seronx

    Joined:
    Jul 10, 2010
    Messages:
    994 (0.62/day)
    Thanks Received:
    219
    Location:
    USA, Arizona
    I agree
     
  9. claylomax

    claylomax

    Joined:
    Apr 10, 2010
    Messages:
    1,612 (0.96/day)
    Thanks Received:
    261
    Location:
    London
  10. Nihilus

    Joined:
    Jul 19, 2011
    Messages:
    219 (0.18/day)
    Thanks Received:
    21
    Fanboyism in all its glory. Forget real benchmark results or performance/watt. It's performance/ transistor count that concerns 99% of the consumers. :nutkick:
    Anyway, for you reading pleasure:

    http://www.tomshardware.com/reviews/processor-architecture-benchmark,2974-15.html
    http://en.wikipedia.org/wiki/Transistor_count
     
  11. 20mmrain

    20mmrain

    Joined:
    Oct 6, 2009
    Messages:
    2,774 (1.48/day)
    Thanks Received:
    826
    Location:
    Midwest USA
    I know I will get slack for this but here it goes.....

    This really reminds me of the GTX 480 vs HD5870 match up. In which Nvidia rushed their chip into production just to gain back some of the product market. But what happened??? Well because Nvidia did this we got a GTX 480 (Which was really an unfinished GTX 570) that ran way to hot, showed up to the customers house DOA on a regular basis, and if not DOA it would often die shortly after little loose.(Of course there are a lot of exceptions I am just using blanket statements) Not to mention just being a huge power hog.
    In the mean time.... AMD designed the HD6970 which while didn't beat the GTX 580 when finally released it did a really great job in the price vs. performance category.
    The way I am speculating this will play out is Nvidia will release the GTX 680.... Which will be really a GTX 770/760. This will compete very well against the HD7970. But because it was rushed I believe it will have a great deal of many problems. Even if the GTX 680 doesn't end up having any issues it will still buy more time for AMD just to release another version (A better higher clocked version) of the HD7970.
    While I have no doubt Nvidia will have no problem beating AMD's 25% to 30% performance lead.... you got to wonder if it was AMD's strategy.... release something conservative just to keep Nvidia on their toes and push them to release something before they are ready.
    Of course I have nothing telling me this is how this will play out. It is all just speculation. But people say that history repeats it's self and I think it will again in this instance.
     
  12. Benetanegia

    Benetanegia New Member

    Joined:
    Sep 11, 2009
    Messages:
    2,683 (1.41/day)
    Thanks Received:
    694
    Location:
    Reaching your left retina.
    Those have to be the most irrelevant links that I've ever seen posted on a forum. Pff you could try better than that crap.

    Sure most people don't care about transistors. Most people are stupid too.

    GPUs are made of transistors. Whether people care about transistors or not, they are key and if a 3 billion transistor GPU (GF110) is so close to a 4.3 billion transistor GPU from the competitor, you better bet that a GPU with 50% more transistors and similar architecture will smack such competitor.

    Maybe you can't warp your simple mind around the concept that GPUs are made of transistors and that more transistors means you can create more powerful GPUs if the architecture accompanies, but that's how it works.

    GCN is the first time that AMD uses 1D shaders and that's one of the reasons their transistor count went up so badly. GCN is the fisrt AMD GPU to support half rate double precision, which requires a lot of transistors to implement. Transistors yes, not fairy dust. GCN also implements a lot of cache and memory management features, which also require a lot of transistors. And all of the above is why Tahiti is so big for so little performance gain.

    Fermi already had all of this, or most of it, so Nvidia does not need to spend horrendous amounts of transistors again, on top of the ones they already spent on Fermi. Unlike GCN vs VLIW, Fermi vs Kepler won't be characterized by a large increase in transistor count per work unit. It's simples, simple math. Now get your head out your ass and start thinking, before calling others fanbois.
     
  13. seronx

    seronx

    Joined:
    Jul 10, 2010
    Messages:
    994 (0.62/day)
    Thanks Received:
    219
    Location:
    USA, Arizona
    GF110: Fermi 16 SMs -> 512 CUDA Cores
    GK112?: Kepler 32 SMs -> 1024 CUDA Cores
    GM110: Maxwell 128 SMs -> 4096 CUDA Cores

    So, abouts from official sources that talk about Maxwell being ~10 TFLOPs

    Fermi -> 1581.056 FMA GFlops (512 x 4 x .772) 512 Cores at 772MHz
    Kepler -> 3481.6 FMA GFlops (1024 x 4 x .850) 1024 Cores at 850MHz
    Maxwell -> 9945.088 FMA GFlops (4096 x 4 x .607) 4096 Cores at 607MHz

    Estimations by Seronx^ not related to official sources above

    [​IMG]

    Calculations based on this and official sources
     
    Last edited: Jan 26, 2012
  14. Aceman.au

    Aceman.au

    Joined:
    Jun 19, 2008
    Messages:
    1,445 (0.62/day)
    Thanks Received:
    62
    No doubt Nvidia will have a stronger card BUT will it be putting out enough performance to make it viable price to performance wise. Can't wait for the first release of Nvidia and a big drop on price for the 7970. Might even wait longer for a 7990!

    Time will tell...
     
  15. mrthanhnguyen

    Joined:
    Aug 27, 2011
    Messages:
    200 (0.17/day)
    Thanks Received:
    4
    ok, so if kepler is faster than amd 7000, what is the price? $700 or $650 for a single card? do they really know that our economy gonna crash again.
     
  16. seronx

    seronx

    Joined:
    Jul 10, 2010
    Messages:
    994 (0.62/day)
    Thanks Received:
    219
    Location:
    USA, Arizona
    It will be the same price as the 580GTX

    GK104 is a 16 SM part like Fermi

    probably less actually in price since it is just Same Trannies + Clock Rate increase I would say GK104 will be

    512 CUDA Cores with a clock near ~950 or so

    512 x 4 x .950 = 1894.4 FMA GFlops
    vs
    512 x 4 x .772 = 1581.056 FMA GFlops

    1894.4/1581.056 => ~1.20x
    and if it has more SMs even better each SM you add though will probably decrease the clock about ~15-33MHz

    G104 has two rumors about it is SM count which is either 16(512) or 24(768)

    768 x 4 x .686 => 2107.392 FMA GFlops
     
    Last edited: Jan 26, 2012
  17. nikko New Member

    Joined:
    Dec 16, 2011
    Messages:
    42 (0.04/day)
    Thanks Received:
    2
    Amd will love punishing early adopters with prices. Hope they will still love amd back after this. Nvidia can release GTX580 at 28nm half the chip size, e.g. 250mm2 and still beat the big 350mm2 child amd has produced with clock speeds alone. 250mm2 chip card costs 140$ for the ti version at launch. and probably 70$ when the time comes.
     
  18. seronx

    seronx

    Joined:
    Jul 10, 2010
    Messages:
    994 (0.62/day)
    Thanks Received:
    219
    Location:
    USA, Arizona
    520mm² <-- 580GTX

    GK104 -> 300-360mm²

    Just saying
     
  19. Nihilus

    Joined:
    Jul 19, 2011
    Messages:
    219 (0.18/day)
    Thanks Received:
    21
    The quote is relevant to your transistor post which showed transistor relationship to performance, which shows how transistor count trends have no merit on product success or performance - not the Nvidia rep comment

    Most people are stupid as they don't care about transistor count? All hail the elitist tech master! :respect: I realize most people are a little nerdy on this site, but you my friend are as disconnected from reality as they come! :shadedshu
     
  20. radrok

    radrok

    Joined:
    Oct 26, 2011
    Messages:
    2,990 (2.66/day)
    Thanks Received:
    803
    Location:
    Italy
    While I agree with you, Benetanegia, I think that you sure have a harsh way to make your point :)
     
    Nihilus says thanks.
  21. nikko New Member

    Joined:
    Dec 16, 2011
    Messages:
    42 (0.04/day)
    Thanks Received:
    2
    Yes, I was hypothesising about GTX650 that would give the 7970 a run for it's money. cause 660 will clearly be classes above it. with more processors than 580 and more frequency, it's just insane how much better it could look and how easely they could end up with big transistorial non-sesne like amd.
     
  22. Super XP

    Super XP

    Joined:
    Mar 23, 2005
    Messages:
    2,773 (0.79/day)
    Thanks Received:
    539
    Location:
    Ancient Greece, Acropolis
    More Nvidia fluff, trying to convince people to wait for there cards. While NV is blowing smoke, HD 7900 Series Radeons are selling like hot cakes.
     
    eidairaman1 says thanks.
  23. Steevo

    Steevo

    Joined:
    Nov 4, 2005
    Messages:
    8,430 (2.55/day)
    Thanks Received:
    1,252
    Yeah cause more transistors immediately means more performance.;)
     
    10 Million points folded for TPU
  24. neko77025

    neko77025

    Joined:
    Jun 4, 2011
    Messages:
    76 (0.06/day)
    Thanks Received:
    8
    this is funny. First off what do you think A competitor is going say. "Aww Man, were fucked, oh well get them next time" ... of course they have too say something like this, they have too save their rep.

    Fact is, AMD showed up first to the party with their new Lamborghini 7970. They got the party started, all the bitches took turns taken A ride. Come 2:01am Nvida is going Show up in their new Ferrari ... but its too late all the bitches are drunk and not going care. Oh whats this, AMD went and got their new 7975, 7980,7985 .. (cause we all know they are coming, Stocked OCed verson).

    Late is Late.
     
  25. seronx

    seronx

    Joined:
    Jul 10, 2010
    Messages:
    994 (0.62/day)
    Thanks Received:
    219
    Location:
    USA, Arizona
    It is actual going to be a 680GTX because 7970 performs about the same as a 900MHz 580GTX

    512 CUDA Core GK104(100) will be around 950MHz with a TDP around 200Ws

    Nvidia is disappointed because they were going to release a 2048 CUDA part with the 1024 CUDA part

    But they can just stick with the 512 CUDA part and just clock it really high and keep TDP within 200W

    ---Remember this----
    GeForce 8800 GTX - 90nm
    PCIe 1.1 x16
    484mm²
    575MHz
    128 CUDA Cores

    GeForce 9800 GTX - 65nm
    PCIe 2.0 x16
    324mm²
    675MHz
    128 CUDA Cores
    ---------------------

    Well they are doing this here:

    GeForce 580 GTX - 40nm
    PCIe 2.0 x16
    520mm²
    772MHz
    512 CUDA Cores

    GeForce 680 GTX - 28nm
    PCIe 3.0 x16
    ~300mm²
    ~950MHz
    512 CUDA Cores
     

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

Share This Page