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. Anarchist4000

    Veteran Regular

    Joined:
    May 8, 2004
    Messages:
    1,439
    Likes Received:
    359
    A prosumer workstation card with Apple brand. Not surprised. Unclear what the product support looks like, but that could be a fair price for a pro product. Just look at WX and Quadro cards.

    Still a bit cringeworthy.
     
    BRiT likes this.
  2. ToTTenTranz

    Legend Veteran Subscriber

    Joined:
    Jul 7, 2008
    Messages:
    9,960
    Likes Received:
    4,553
    It's not a Pro card, though. It's a Vega 56, not a WX8200...
     
  3. del42sa

    Newcomer

    Joined:
    Jun 29, 2017
    Messages:
    166
    Likes Received:
    82
    Computerbase did test RX480 and it says the opposite, the memory bandwith is issue with Polaris.

    https://forums.anandtech.com/threads/how-memory-frequency-starved-is-polaris.2479648/

    https://forums.anandtech.com/threads/how-memory-frequency-starved-is-polaris.2479648/#post-38348803
     
  4. Anarchist4000

    Veteran Regular

    Joined:
    May 8, 2004
    Messages:
    1,439
    Likes Received:
    359
    If the entire workload fit into the cache practically zero memory bandwidth would be required. The issue would be the geometry pipeline stalling and making memory the bottleneck due to cache misses. Then consider the effect of any bandwidth saving techniques.

    The newer memory types aren't anything special. Just typical process improvements applied to the prior version. The question is why one card requires more bandwidth than another.
     
  5. del42sa

    Newcomer

    Joined:
    Jun 29, 2017
    Messages:
    166
    Likes Received:
    82
    if that were true, no high-performance GPU needs a bus larger than 256bit and Nvidia could save some money on GTX 1080/1080Ti memory as well as AMD on Vega 64/56 ...
     
  6. Anarchist4000

    Veteran Regular

    Joined:
    May 8, 2004
    Messages:
    1,439
    Likes Received:
    359
    They simply wouldn't if the caches were that large. Caches and register files have a huge amount of bandwidth relative to actial memory. It's the culling, reuse, and compression schemes, or lack of effective implementation, that can make a huge difference. Check out Nvidias tiled rasterizer for example.
     
  7. del42sa

    Newcomer

    Joined:
    Jun 29, 2017
    Messages:
    166
    Likes Received:
    82
    too much "if" ....
     
  8. ToTTenTranz

    Legend Veteran Subscriber

    Joined:
    Jul 7, 2008
    Messages:
    9,960
    Likes Received:
    4,553
    From Anandtech's live blog of AMD's Next Horizon event:

    MI60?

    If the MI25 was a single Vega with 12.3 TFLOPs FP32 / 24.6 TFLOPs FP16, going by the same logic the MI60 should be ~30 TFLOPs FP32 / 60 TFLOPs FP16.

    Maybe it's a 2x Vega 20 card with each chip clocked at 1.8GHz?
    And with 4x HBM2 stacks, we could be looking at cards with a whopping 64 GB VRAM.
     
  9. DavidGraham

    Veteran

    Joined:
    Dec 22, 2009
    Messages:
    2,773
    Likes Received:
    2,560
    It's Vega 20 with 15TF FP32, 30TF FP16 and 60TF FP/INT 8.
     
  10. Esrever

    Regular Newcomer

    Joined:
    Feb 6, 2013
    Messages:
    594
    Likes Received:
    298
    anandtech quotes:
    if double fp16, it would be close to 30TF fp16. Which would require 2 of them for 60TF, which doesn't really make sense to me.
     
  11. Samwell

    Newcomer

    Joined:
    Dec 23, 2011
    Messages:
    112
    Likes Received:
    129
    Yes, 4096 Cores at 1,8 Ghz at 300W. they just changed their naming scheme a bit, as bigger numbers sound better.
     
  12. Rootax

    Veteran Newcomer

    Joined:
    Jan 2, 2006
    Messages:
    1,169
    Likes Received:
    576
    Location:
    France
    1.8ghz at 300w ? We're not that far under Vega 10, I was expecting better, even if it's not "just" a die shrink...
     
  13. fellix

    fellix Hey, You!
    Veteran

    Joined:
    Dec 4, 2004
    Messages:
    3,489
    Likes Received:
    400
    Location:
    Varna, Bulgaria
  14. 3dilettante

    Legend Alpha

    Joined:
    Sep 15, 2003
    Messages:
    8,122
    Likes Received:
    2,873
    Location:
    Well within 3d
    Pushing for the upper range of performance runs into decidedly non-linear penalties. The promised gains in circuit performance iso-power were stated as being ~1.25x, which if comparable to earlier slides from AMD is a downgrade from ~1.35x. Something more fundamental to the architecture would need to change to do more than incrementally shift where the chip hits a wall.
     
    Alexko, xpea, pharma and 1 other person like this.
  15. DavidGraham

    Veteran

    Joined:
    Dec 22, 2009
    Messages:
    2,773
    Likes Received:
    2,560
    Exactly my thoughts, like I said, they would need to significantly change the arc in order to scale the frequency more than Vega 10. Also it seems power efficiency is rather bad at the core of the Vega architecture, 300W @1.8GHz on 7nm is not really that big of an improvement after all.
     
    A1xLLcqAgt0qc2RyMz0y likes this.
  16. Love_In_Rio

    Veteran

    Joined:
    Apr 21, 2004
    Messages:
    1,452
    Likes Received:
    110
    Much more attractive is Vega 10 performance at 150 watts. With some Navi improvements is what next gen consoles will get. On the other hand is sad to think they need 7nm to get with their current architecture the perf/watt of Pascal with 16nm.
     
    xpea likes this.
  17. Geeforcer

    Geeforcer Harmlessly Evil
    Veteran

    Joined:
    Feb 6, 2002
    Messages:
    2,297
    Likes Received:
    464
    96/128 CU @ 2GHz @ 250W @ $550 @ Christmas 18, "easily" though.
     
    w0lfram and DavidGraham like this.
  18. 3dilettante

    Legend Alpha

    Joined:
    Sep 15, 2003
    Messages:
    8,122
    Likes Received:
    2,873
    Location:
    Well within 3d
    There was some speculation concerning the Apple A12's clock speeds on 7nm, which may have hinted at somewhat less power or clock scaling than originally expected. Wire delay and resistance was something everyone was wary of, and it's possible that Vega's architectural targets feel those effects more keenly--given that Vega's changes at 14nm were notably underpinned by trying compensate for wire delay or reach higher clock speeds.

    Additionally, there's a wider and faster memory subsystem and a decent amount of additional IO. There's a power hit when those features were added to Nvidia's enterprise lines as well.
     
    DavidGraham likes this.
  19. yuri

    Newcomer

    Joined:
    Jun 2, 2010
    Messages:
    178
    Likes Received:
    147
    300W, 7nm, +300MHz - guess they shove this laughable GPU out of their doors solely because Hawaii got really rusty.

    Seeing the predictions "north of 2GHz"... oh my, god. Vega simply has to be clocked to ~1.2GHz to be effective. How would a 7nm Fiji do? The same I guess.
     
  20. DavidGraham

    Veteran

    Joined:
    Dec 22, 2009
    Messages:
    2,773
    Likes Received:
    2,560
    AMD is comparing V100 PCI-E (250W) vs MI60 (300W). Both cards trade blows in a number of benchmarks. Though they avoided the comparison with the 10% faster V100 NVLink (300W).

    [​IMG]

    [​IMG]
     
    Lightman 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...