AMD Vega 10, Vega 11, Vega 12 and Vega 20 Rumors and Discussion

Discussion in 'Architecture and Products' started by ToTTenTranz, Sep 20, 2016.

  1. BRiT

    BRiT (╯°□°)╯
    Moderator Legend Alpha Subscriber

    Joined:
    Feb 7, 2002
    Messages:
    12,514
    Likes Received:
    8,723
    Location:
    Cleveland
    Now you're the one being silly. There is no such thing as free lunch.

    You are not comparing like for like unless you take into account functionality. Perhaps all the extra transistors is needed for that additional functionality. How do you know the competitors wouldnt end up with even more trannies to hit the advanced functionality?
     
  2. digitalwanderer

    digitalwanderer Dangerously Mirthful
    Legend

    Joined:
    Feb 19, 2002
    Messages:
    17,276
    Likes Received:
    1,788
    Location:
    Winfield, IN USA
  3. CaptainGinger

    Newcomer

    Joined:
    Feb 28, 2004
    Messages:
    92
    Likes Received:
    47
  4. digitalwanderer

    digitalwanderer Dangerously Mirthful
    Legend

    Joined:
    Feb 19, 2002
    Messages:
    17,276
    Likes Received:
    1,788
    Location:
    Winfield, IN USA
    It is a very exciting time to be alive!
     
  5. eastmen

    Legend Subscriber

    Joined:
    Mar 17, 2008
    Messages:
    9,985
    Likes Received:
    1,497
    Digi get me a Vega tell them I'm a stock holder
     
    digitalwanderer and Lightman like this.
  6. ToTTenTranz

    Legend Veteran Subscriber

    Joined:
    Jul 7, 2008
    Messages:
    9,999
    Likes Received:
    4,571
    Me too!
    Tell them although I'm not a stock holder, I am indeed a person who would very much like to hold a stock of brand new graphics cards.
     
    digitalwanderer and eastmen like this.
  7. ShaidarHaran

    ShaidarHaran hardware monkey
    Veteran

    Joined:
    Mar 31, 2007
    Messages:
    3,984
    Likes Received:
    34
    I'm not from Missouri, but I still need to be shown the results before I'll believe the pronouncements.
     
  8. BacBeyond

    Newcomer

    Joined:
    Jun 29, 2017
    Messages:
    73
    Likes Received:
    43
    We don't know what the power draw will be, Vega FE was running @ 1600mhz @ 1.1v and around 300w.

    1080 AIB run mostly 200w+ out of the box for 5-10% more perf than 1080 FE (which throttled like crazy to keep its low TDP)

    Sadly sites don't test power draw of a 1080 OC'd because then we'd get rid of this ridiculous Vega power hungry meme. Yes, Vega FE uses more power than a 1080, but not a significant amount. We haven't seen how RX power consumption compares but it should bring better perf/watt over FE.
     
    digitalwanderer likes this.
  9. 3dilettante

    Legend Alpha

    Joined:
    Sep 15, 2003
    Messages:
    8,122
    Likes Received:
    2,873
    Location:
    Well within 3d
    It's a pretty safe bet packed math means packed data format, that is, within a register. The packed terminology goes back at least as far as the introduction of MMX, and CPU SIMD extensions readily included packed math on the data arranged in a packed format within a single SIMD register.

    AMD's packed FP16 instructions aren't doubling their register fields, and the non-packed FP16 operations have selection bits to choose operands from within a standard register.

    How bad are the yields on the mature 315mm2 product? It would need to be measurably worse even now for even perfect yields to get past the area disparity, and if they were that perfect there wouldn't be a cut-down Vega.
     
    digitalwanderer and silent_guy like this.
  10. DavidGraham

    Veteran

    Joined:
    Dec 22, 2009
    Messages:
    2,789
    Likes Received:
    2,598
    #3130 DavidGraham, Jul 31, 2017
    Last edited: Jul 31, 2017
    sonen and pharma like this.
  11. 3dilettante

    Legend Alpha

    Joined:
    Sep 15, 2003
    Messages:
    8,122
    Likes Received:
    2,873
    Location:
    Well within 3d
    What has me thinking is that, if we were to take AMD's Vega marketing shot from a few months back at face value, the areas with the least ambiguous departure from expectation are the CU arrays and potentially the strip of silicon down the center where the command front ends and geometry processor hardware sits.

    The front-end section has about the same proportion of the die as other GPUs like Polaris 10, but on a die about twice as large as Polaris 10 it doesn't yield a leap in culled geometry throughput. The non-culled throughput in the synthetics does show some measurable improvement and it's not that far from some Nvidia GPUs. The inability to cull in the same range may be where this area might not be punching at its weight. Perhaps this is related to primitive shaders or somesuch, but it would be unfortunate if even slight improvement needs software intervention. I wouldn't be sure if the beyond3d synthetics are the type that the new rasterizer would necessarily provide much benefit for, since the tests don't strive to create a very complex culling situation.

    Perhaps more curious is the area of the CU arrays, relative to what they've offered so far. If they were to shrink to the area of a Polaris CU, I think Vega could be perhaps ~15% larger than GP104, the area AMD gives them in its marketing is that unusually disproportionate. I think I agree that FP16 shouldn't be responsible for the area increase.
    (ed: at least not the very large increase seen)
     
    #3131 3dilettante, Jul 31, 2017
    Last edited: Jul 31, 2017
  12. Anarchist4000

    Veteran Regular

    Joined:
    May 8, 2004
    Messages:
    1,439
    Likes Received:
    359
    I'd agree, but with tensor style operations there exists the possibility of four independent input operands. That's the sole reason I'm withholding judgement. Another possibility with Tensors is a scalar broadcast freeing operands. Tensors may very well share an operand allowing some really interesting capabilities along with the scalar broadcast. Getting four multiplications per lane in a single cycle if the hardware allows it.

    Not that bad, but there could be a performance aspect to it. Cut would be a result of the fabric working around defects with no extra steps. If all control is over the fabric, there is very little that couldn't be redundant. At the very least it may offset some of the cost.
     
  13. Anarchist4000

    Veteran Regular

    Joined:
    May 8, 2004
    Messages:
    1,439
    Likes Received:
    359
    So in the worst case Vega is nearly twice (26 to 46) as fast as 1080? Doesn't seem that terrible.
     
    RootKit likes this.
  14. DavidGraham

    Veteran

    Joined:
    Dec 22, 2009
    Messages:
    2,789
    Likes Received:
    2,598
    These are minimum fps, not averages, and they are cherrypicked as well. Since they show FuryX having better minimums than 1080.
     
    xpea and pharma like this.
  15. Malo

    Malo Yak Mechanicum
    Legend Veteran Subscriber

    Joined:
    Feb 9, 2002
    Messages:
    7,038
    Likes Received:
    3,108
    Location:
    Pennsylvania
    It's a decent range of games though. Part of what AMD was touting with their blind tests was the better delivery of frames so perhaps there is something to the architecture that will give us more consistent frame times and much better minimums. After all, we've been moving towards that as both a benchmark measurement and the result providing a better gaming experience.

    We should have a decent range of reviews from the good testers to show us this in practice soon.
     
    RootKit, digitalwanderer and BRiT like this.
  16. 3dilettante

    Legend Alpha

    Joined:
    Sep 15, 2003
    Messages:
    8,122
    Likes Received:
    2,873
    Location:
    Well within 3d
    I see what the superset of Hypertransport is used for in the CPU space, and what it accomplishes there. I do not see a mechanism provided on why it should change the GPU silicon yield picture, at least not for the better.
     
  17. DavidGraham

    Veteran

    Joined:
    Dec 22, 2009
    Messages:
    2,789
    Likes Received:
    2,598
    Maybe, but Vega FE (which is 95% of RX Vega) didn't show any of these alleged better minimums. And again, FuryX doesn't have better minimums than a 1080. These are facts we already knew and tested.
     
    xpea, Malo, pharma and 1 other person like this.
  18. sonen

    Newcomer

    Joined:
    Jul 13, 2012
    Messages:
    53
    Likes Received:
    33
    Guys, read it again:
    "Minimum FPS range for {...}"



    For all we know AMD might be claiming that 1080 gives better minimums and better frame times in 9 out of 10 games
     
    pharma and DavidGraham like this.
  19. Malo

    Malo Yak Mechanicum
    Legend Veteran Subscriber

    Joined:
    Feb 9, 2002
    Messages:
    7,038
    Likes Received:
    3,108
    Location:
    Pennsylvania
    So the Liquid Cooled version is not available by itself but only in the "pack" for $699 which includes $100 off a Ryzen and $200 off a Samsung Ultrawide monitor. It's a fantastic deal for new builders.... tough shit for me though.
     
    Lightman, Silent_Buddha, BRiT and 2 others like this.
  20. DavidGraham

    Veteran

    Joined:
    Dec 22, 2009
    Messages:
    2,789
    Likes Received:
    2,598
    RX Vega is 12% faster in Doom than GTX 1080 FE(AMD's best case?)
    [​IMG]
    [​IMG]

     
    pharma likes this.
Loading...

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...