AMD Mantle API [updating]

Discussion in 'Rendering Technology and APIs' started by MarkoIt, Sep 26, 2013.

  1. CarstenS

    Veteran Subscriber

    Joined:
    May 31, 2002
    Messages:
    4,910
    Likes Received:
    2,230
    Location:
    Germany
    My Prediction: Lower Fps, lower power. ;)

    Given it's early state, I think Mantle looks very promising, though I in AMDs stead would have it introduced with Kaveri, rather than with Hawaii.
     
  2. Picao84

    Veteran Regular

    Joined:
    Feb 15, 2010
    Messages:
    1,804
    Likes Received:
    867
    Well, sorry if from a company as big and important as AMD for the CPU/GPU market, I expect a more professional showcase of their technologies. Right today, they should at least had reviewers ready with performance numbers right of the bat, instead of presenting half-baked numbers in completely random test configs.
     
  3. Svensk Viking

    Regular

    Joined:
    Oct 11, 2009
    Messages:
    542
    Likes Received:
    112
    Nice CPU performance for free, hopefully Mantle can revitalize my old Phenom II X4!
     
  4. Dave Glue

    Regular

    Joined:
    Apr 25, 2002
    Messages:
    634
    Likes Received:
    25
    My expectation for Mantle was basically this. It's something to significantly help AMD's own CPU's first and foremost, was never expecting big gains with high-end GPU's and fast CPU's.

    However, what I also expected from Mantle (or at least titles where Mantle is taken advantage of it) is much better frame pacing overall - basically more consistency in frame times, especially with lower-end CPU's.

    [​IMG]

    By looking only at the two frame rate counters, you could say "WTF? Mantle only gives a 4fps boost!" - but then look at the graph on frame times in the lower left.
     
  5. itsmydamnation

    Veteran Regular

    Joined:
    Apr 29, 2007
    Messages:
    1,309
    Likes Received:
    407
    Location:
    Australia
    why they have already done that at a big conference........ today is DICE releasing a patch.....

    .

    when then your ignoring data points that dont fit your position..........
     
  6. Lightman

    Veteran Subscriber

    Joined:
    Jun 9, 2008
    Messages:
    1,817
    Likes Received:
    491
    Location:
    Torquay, UK
    Ha! Reread my post as it specifically states constant FPS. If I need 3GHz i5 under Mantle and 4.5GHz under DX11 to achieve that shoul show some difference on my power meter :)
    Even at the same CPU settings there should be measurable gap I think.
     
  7. Picao84

    Veteran Regular

    Joined:
    Feb 15, 2010
    Messages:
    1,804
    Likes Received:
    867
    I'll just quote myself, ok?

    If I would be running AMD or DICE (they are both at fault here really), I would be seriously pissed at my Marketing employees. Further, if there is a partnership between AMD and DICE on Mantle they should have advanced together with numbers, instead of going each their own way about it.
     
  8. itsmydamnation

    Veteran Regular

    Joined:
    Apr 29, 2007
    Messages:
    1,309
    Likes Received:
    407
    Location:
    Australia
    and i would quote myself but i CBF...... AMD already did that... remember.

    why would DICE do this?

    also how do you get predictable runs in high server load situations unless you "half bake" it , aka use bot/something predefined on unreleased code.......


    the hardware configs them selves are perfectly reasonable....
     
  9. Picao84

    Veteran Regular

    Joined:
    Feb 15, 2010
    Messages:
    1,804
    Likes Received:
    867
    What runs, nevermind predictable? Do you really think it is a coincidence that 5 out of 6 screens show exactly or very approximate (less than 2 fps difference) FPS to the ones used as "average"? And the fact that the 6th screen, which was the only one that showed very different FPS from average (116 vs 121.5), was taken out after someone pointed it was from Single Player?

    Lots of coincidences here...
     
    #929 Picao84, Jan 30, 2014
    Last edited by a moderator: Jan 30, 2014
  10. Dave Glue

    Regular

    Joined:
    Apr 25, 2002
    Messages:
    634
    Likes Received:
    25
    I'm ignoring "data points" that don't affect my position of what I "expected"? Suggest you read my post again, as your response makes no sense in context. I am not making any declarative statements on Mantle performance as an API now or in the future.
     
  11. Alexko

    Veteran Subscriber

    Joined:
    Aug 31, 2009
    Messages:
    4,514
    Likes Received:
    934
    Good to know (about the empty servers).

    If I recall correctly you once said that for Battlefield 4, you would use Mantle mostly to optimize the CPU's load, which certainly seems to be the case based on those early numbers (very nice work, by the way).

    I would imagine that in the future, you'll turn your attention a bit more towards the GPU side of things and further improve Frostbite 3. [Edit: I've just read your blog post which mentions GPU optimizations, so this is apparently already underway] I have a couple of questions:

    1) Is there really much to be gained on the GPU side?
    2) Will Battlefield 4 (and other, upcoming FB3-based games) be retrofitted with future improvements to the engine, in particular Mantle-based improvements?
     
    #931 Alexko, Jan 30, 2014
    Last edited by a moderator: Jan 30, 2014
  12. itsmydamnation

    Veteran Regular

    Joined:
    Apr 29, 2007
    Messages:
    1,309
    Likes Received:
    407
    Location:
    Australia



    well you know if you stop being a whinny little bitch and ask nicely(twitter etc?) repi might clarify or confirm for you, seeing as he is the one who wrote the post ..........


    i do see what so hard understand about the numbers, why must the picture match up exactly, you have like 3 seconds worth of data on the screen.
     
  13. itsmydamnation

    Veteran Regular

    Joined:
    Apr 29, 2007
    Messages:
    1,309
    Likes Received:
    407
    Location:
    Australia
    the multi gpu config with a 6core i7 showed significant performance improvements according to Repi. So its not just low end amd cpu's like you claimed.
     
  14. Dave Glue

    Regular

    Joined:
    Apr 25, 2002
    Messages:
    634
    Likes Received:
    25
    Again, we have a reading comprehension problem here. How could benchmarks released today affect my expectations of what advantages the API would bring for the majority?
     
  15. Dave Glue

    Regular

    Joined:
    Apr 25, 2002
    Messages:
    634
    Likes Received:
    25
    WTF is wrong with you? NeoGaf forums are thataway kiddo.
     
  16. itsmydamnation

    Veteran Regular

    Joined:
    Apr 29, 2007
    Messages:
    1,309
    Likes Received:
    407
    Location:
    Australia
    you never said that, you said

    stop moving goal posts. this statement is wrong.

    never been on NeoGaf, and im not a kiddo old timer...... i just hate pretensions BS, be honest about your agenda dont try to dress it up. if it looks like a duck, walks like a duck and quacks like a duck. then its a duck........

    my agenda, i want to see mantle succeed, and ultimately what people are talking about in the grand scheme is so trivial and inconsequential its not funny.

    question would people rather a rapid software development lifecycle approach for this or still be waiting?i'll take rapid everyday of the week.
     
  17. Picao84

    Veteran Regular

    Joined:
    Feb 15, 2010
    Messages:
    1,804
    Likes Received:
    867
    I did not get exactly you are trying to say here. But the point is right that. How much time did they bench? Did they even walk around? Because the screenshots look to be in exactly the same position in the map, just with slightly different content like smoke or outdoor advertisement. Its like they just drop the player in the exact same coordinates.

    I do not use tweeter or whatever, and he already wrote on this forum, so why not answer here as well?
     
  18. itsmydamnation

    Veteran Regular

    Joined:
    Apr 29, 2007
    Messages:
    1,309
    Likes Received:
    407
    Location:
    Australia
  19. Picao84

    Veteran Regular

    Joined:
    Feb 15, 2010
    Messages:
    1,804
    Likes Received:
    867
    Might be my clumsiness with tweeter, but I failed to see what you were pointing at?
     
  20. ToTTenTranz

    Legend Veteran Subscriber

    Joined:
    Jul 7, 2008
    Messages:
    10,824
    Likes Received:
    5,390
    The lower numbers were taken with a Core i7 4960X, which is a $1000 CPU.

    The purpose of Mantle is to have gamers taking full advantage of their GPUs without requiring a $1000 CPU.
    What will be interesting is to know the difference in performance between a $1000 Intel CPU and a $180 AMD CPU.
    What is not interesting is to show how a very expensive CPU won't benefit at all from Mantle, because that was a given from the start.


    Whoever decided to leak those numbers that way clearly harmed AMD's whole point with Mantle.
     
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...