AMD: R9xx Speculation

Discussion in 'Architecture and Products' started by Lukfi, Oct 5, 2009.

  1. Kaotik

    Kaotik Drunk Member
    Legend

    Joined:
    Apr 16, 2003
    Messages:
    8,706
    Likes Received:
    2,502
    Location:
    Finland
    With the "AMD" logo on it, I wouldn't put my money for Fermi, but each to their own ;)
     
  2. GZ007

    Regular

    Joined:
    Jan 22, 2010
    Messages:
    416
    Likes Received:
    0
    You mean Quadro cards if u dont count tesselation :wink:.
     
  3. 3dilettante

    Legend Alpha

    Joined:
    Sep 15, 2003
    Messages:
    8,263
    Likes Received:
    3,450
    Location:
    Well within 3d
    The B3d article on Fermi indicates that Cypress can be affected by the fatness of the control points and math in the HS.
    Having more capacity may help with the former problem.

    The description doesn't seem specific enough to indicate there isn't on-die storage that may spill to memory.
     
  4. Mize

    Mize 3dfx Fan
    Moderator Legend Veteran

    Joined:
    Feb 6, 2002
    Messages:
    5,073
    Likes Received:
    1,137
    Location:
    Cincinnati, Ohio USA
    In trying to ascertain if it was a fake I was assuming faking an AMD more plausible than an entire card.
    Anyway...
     
  5. Mintmaster

    Veteran

    Joined:
    Mar 31, 2002
    Messages:
    3,897
    Likes Received:
    87
    Didn't the B3D article say that tessellation data is kept in the GDS? There could be some data bottlenecks with that.

    Does anyone know how fast RV770 and newer ATI GPUs process triangles that pass through a trivial geometry shader?
     
  6. rUmX

    Newcomer

    Joined:
    Aug 27, 2010
    Messages:
    5
    Likes Received:
    0
    Crysis Warhead > 60FPS @ 25x16 4xAA Enthusiast? One can only dream... :razz::lol:
     
  7. Alexko

    Veteran Subscriber

    Joined:
    Aug 31, 2009
    Messages:
    4,512
    Likes Received:
    930
    Isn't that amply sufficient?
     
  8. Jawed

    Legend

    Joined:
    Oct 2, 2004
    Messages:
    10,873
    Likes Received:
    767
    Location:
    London
    GDS is used to send parameters to TS, I believe.

    There's a separate data path from HS direct to DS. Additionally DS consumes the output of TS (obviously). So HS and TS data needs to be staged for consumption by DS - in theory covering quite a bit of lag between the two data streams. This appears to be the crux of the buffering issue. The B3D article, I believe, describes "locking" HS and DS together as a pair within a SIMD. This then limits the amount of data that can be staged, and presumably also affects the SIMDs' ability to sink the output of TS.

    No. A key characteristic of GS since R600 has been pushing all the data off-die through the ring buffer. This is how GS was originally able to support huge amounts of data per vertex, before D3D10 got cut back in favour of NVidia's architecture.

    So it appears this hint is for some kind of ring buffer (or multiple ring buffers?) off die for DS to consume.

    My problem with this concept is that tessellation, generally, is supposed to reduce VRAM bandwidth (and space) usage by doing stuff on die instead of dealing with hugely-expanded vertex data streams. Shoving HS/TS data off die really works against that. Unless there's a healthy Fermi style L2 cache, it seems like not much progress to me.
     
  9. Jawed

    Legend

    Joined:
    Oct 2, 2004
    Messages:
    10,873
    Likes Received:
    767
    Location:
    London
    Seems NVidia has quite a reserve, both in terms of unlocking throughput (Quadro is the real deal for throughput) and in terms of clocks. So, no, I don't think it's sufficient. Bearing in mind Cayman looks like it's going to have to last for a year+ (emphasis on +). Also, can it scale further? Is it really scalable?
     
  10. Alexko

    Veteran Subscriber

    Joined:
    Aug 31, 2009
    Messages:
    4,512
    Likes Received:
    930
    GeForces are only limited in geometric throughput when tessellation is disabled, right? That doesn't sound like a bottleneck you'd be likely to hit outside of pro rendering applications.

    Besides, I know that tessellation is trendy —and rightly so, I suppose— but the main objective is to render games with max details and smooth framerates, right? As far as I can tell, even Cypress is capable of doing that, and it has yet to crumble under the weight of high geometric demands on any game. Barts is better than Cypress in terms of tessellation, and Cayman apparently offers further improvements over that.

    So where's the problem? I'd understand your concern if Cypress were struggling with, say, Alien vs Predator, but I don't see any reason to be worried here.

    Geometric throughput is just one metric. Should NVIDIA drastically increase FLOPS because AMD leads in this area? Only actual performance matters.
     
    #4310 Alexko, Oct 29, 2010
    Last edited by a moderator: Oct 30, 2010
  11. no-X

    Veteran

    Joined:
    May 28, 2005
    Messages:
    2,333
    Likes Received:
    290
    I think the question is how effectively will Cayman use its geometry power. In theory it should be capable of about 1700 megatriangles per second.

    Shouldn't it be enough to achieve more than 60 FPS on Eyefinity-6 configuration made of 2560*1600 LCDs displaying scene made of single-pixel triangles?
     
  12. Unknown Soldier

    Veteran

    Joined:
    Jul 28, 2002
    Messages:
    2,238
    Likes Received:
    33
    And that's why I guess AMD were aiming for 32nm. Of course that didn't happen.
     
  13. Mintmaster

    Veteran

    Joined:
    Mar 31, 2002
    Messages:
    3,897
    Likes Received:
    87
    TS data is very small, though. It's just 4 bytes per vertex if you use a triangle strip, and close to half if you do caching. If you can stage just one kilobyte then you have several wavefronts of vertices buffered up.

    Like I said, TS data is 4 bytes per vertex, which means 2-4 bytes per triangle. Even Fermi's peak of 4 tris per clock would consume under 11 GB/s using an off-die buffer for the TS output.
     
  14. eastmen

    Legend Subscriber

    Joined:
    Mar 17, 2008
    Messages:
    10,021
    Likes Received:
    1,531
    I'm wondering why you think it will have to last over a year. Surely when they move to 28nm sometime in 2011 they will replace cayman
     
  15. AnarchX

    Veteran

    Joined:
    Apr 19, 2007
    Messages:
    1,559
    Likes Received:
    34
    • 32 ROPs @ 850MHz ~ 153GB/s -> 32 ROPs @ 900MHz ~ 162GB/s
    • 256-Bit @ 5.8Gbps ~ 185GB/s
    • 8 memory channels 23GB/s each.

    So Cayman turns with tessellation to 224-Bit (162GB/s) mode with 1792MiB general VRAM and an exclusive 23GB/s 256MiB tessellation buffer? :lol:
     
  16. Jawed

    Legend

    Joined:
    Oct 2, 2004
    Messages:
    10,873
    Likes Received:
    767
    Location:
    London
    :oops: I got that the wrong way round, sigh.

    GTX460 is faster than HD5870 in Civ 5:

    http://www.techspot.com/review/320-civilization-v-performance/page9.html

    Even with tessellation off:

    http://www.techspot.com/review/320-civilization-v-performance/page7.html

    AMD had devrel involved in making that game.

    I don't see Metro 2033 performance holding up, either (not even highest in-game settings):

    http://www.techreport.com/articles.x/19844/12
     
  17. MistaPi

    Regular

    Joined:
    Jun 12, 2002
    Messages:
    362
    Likes Received:
    7
    Location:
    Norway
    I have another question about MLAA. If I enable MLAA in the driver and set the level to 8x samples, does it mean 8xMLAA or 8xMSAA+MLAA? I am thinking the latter and that MLAA is a fixed filter?
     
  18. fellix

    fellix Hey, You!
    Veteran

    Joined:
    Dec 4, 2004
    Messages:
    3,503
    Likes Received:
    418
    Location:
    Varna, Bulgaria
    That would be 8xMSAA+MLAA.
     
  19. MistaPi

    Regular

    Joined:
    Jun 12, 2002
    Messages:
    362
    Likes Received:
    7
    Location:
    Norway
    Ok. Thanks.
     
  20. Man from Atlantis

    Regular

    Joined:
    Jul 31, 2010
    Messages:
    733
    Likes Received:
    6
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...