AMD Mantle results are in (driver tomorrow)

Discussion in 'General Discussion' started by Shamrock, Jan 31, 2014.

  1. Shamrock

    Shamrock Registered

    Joined:
    Dec 6, 2012
    Messages:
    287
    Likes Received:
    36
    This is Battlefield 4 ONLY, so far. Goto link at bottom for actual screenshots.

    Test case 1: Low-end single-player
    CPU/GPU: AMD A10-7850K (‘Kaveri’ APU), 4 cores @ 3.7 GHz
    Settings: 720p MEDIUM settings.
    OS: Windows 7 64-bit
    Level: Singapore “Beach”
    This area is heavy on the CPU as it is quite a lot of action going on, but the game is primarily GPU-bound both on DX and with Mantle but thanks to GPU optimizations with Mantle we get a good performance improvement.
    Result: 26.6 ms/f -> 23.3 ms/f = 14% faster
    DX11.1 - 39fps
    Mantle - 43fps

    Test case 2: Standard 64-player multiplayer
    CPU: AMD FX-8350, 8 cores @ 4 GHz
    GPU: AMD Radeon 7970 3 GB
    Settings: 1080p ULTRA 1x MSAA
    OS: Windows 8 64-bit
    Level: Siege of Shanghai
    Level was tested with 64 “pseudo players” that we have for our own internal testing that simulates heavy game workload that we have in multiplayer in order to get more deterministic results compared to full real multiplayer. 64 players on the large Battlefield levels is really demanding of the CPU so this test case is primarily CPU-bound.
    Result: 18.87 ms/f -> 15.08 ms/f = 25.1% faster
    DX11.1 - 53fps
    Mantle - 67fps


    Test case 3: High-end single-player with multiple GPUs
    CPU: Intel Core i7-3970x Extreme, 12 logical cores @ 3.5 GHz
    GPU: 2x AMD Radeon R9 290x 4 GB
    Settings: 1080p ULTRA 4x MSAA
    OS: Windows 8 64-bit
    Level: South China Sea “Broken Flight Deck”
    This single-player scene is heavy on both the CPU and GPU with lots of action going on. Test was done on the highest end Intel CPU on Windows 8, which is the fastest option before Mantle thanks to DirectX 11.1. Still this CPU is not fast enough to keep the 2 290x GPUs fed at 1080p on Ultra settings so we get a significant CPU performance bottleneck which results in major performance improvement when enabling Mantle.
    Result: 13.24 ms/f -> = 8.38 ms/f = 58% faster
    DX11.1 - 78fps
    Mantle - 116fps

    http://battlelog.battlefield.com/bf4/ja/news/view/2955063418790832415/
     
  2. Spinelli

    Spinelli Banned

    Joined:
    Jan 28, 2012
    Messages:
    5,290
    Likes Received:
    32
    At first I didn't see test result 3 and was therefore somewhat disappointed with the 14 & 25 % improvement as I was expecting something like a 40-60 % improvement. Then I scrolled down and noticed the third test...BAM! 58% improvement :)

    I didn't even know that the 7970 is compatible with Mantle, I thought only the R9s were.

    I also heard that DX 11.2 is going to have something to say about Mantle when it gets released, we'll see. Exciting times ahead for PC gaming :).

    Now all we need is for game makers to actually take advantage of all the power of all the threads of CPUs, and not only take advantage of all that power and all those threads, but to use them toward much more complex physics and audio, rather than everything being about graphics, graphics, graphics. Pure gameplay mehanics/physics have hardly changed in most mainstream games over the past 10 years, the newer games just do the same old basic stuff but just with a prettier face/shell. Pretty pathetic actually.

    Anyways Great job AMD! :) I hope we get more info about the "TrueAudio" stuff that the new drivers apparently come with/enable (I believe on R9 cards only).
     
    Last edited by a moderator: Jan 31, 2014
  3. Murtaya

    Murtaya Registered

    Joined:
    Jan 25, 2012
    Messages:
    531
    Likes Received:
    0
    So the developers need to implement mantle and that can only be done with DX11?
    Still Nvidia for this software then isn't it? Unless you can persuade them to change to DX11 and do a lot of extra work to implement a feature that would only benefit customers with 3 models of AMD card. I hope mantle means exciting times, but it sounds a bit irrelevant to rF2, and any software where the developers don't fancy doing the extra work. Can they charge more for software by doing the work to enable mantle? No. Will AMD gpu users still buy software that doesn't have mantle? Yes. Where is the incentive to do the work? AMD would have to pay wouldn't they? I can't see that happening except for mass market console port type games, not simulations.
    Sounds like I'm being down on AMD I'm not, I always used their cards (until rF2) as they represent better value for money most of the time. I just don't see mantle as very relevant. If I am wrong please tell me why.
     
  4. Capeta

    Capeta Registered

    Joined:
    May 31, 2012
    Messages:
    268
    Likes Received:
    48
    So, I'm not that good in technical stuff, I ask you guys, if I have a Sapphire Radeon 7950 Vapor-X does I need to install Mantle to obtain better performances ? And if yes, does it concern rF2 too ?

    Thanks guys.
     
  5. DrR1pper

    DrR1pper Registered

    Joined:
    Apr 29, 2012
    Messages:
    3,294
    Likes Received:
    36
    From what i understand it won't benefit you in rf2 Capeta. Only dc11 games, rfactor 2 is dx9.

    But i must say, very impressive performance boosts, kudos to AMD. I wonder how nvidia is going to react.
     
  6. Capeta

    Capeta Registered

    Joined:
    May 31, 2012
    Messages:
    268
    Likes Received:
    48
    Thanks DrR1pper.
     
  7. Marcel van der Linden

    Marcel van der Linden Registered

    Joined:
    Dec 11, 2010
    Messages:
    29
    Likes Received:
    0
    Great but why this post on a rFactor 2 forum?
     
  8. DurgeDriven

    DurgeDriven Banned

    Joined:
    Mar 20, 2012
    Messages:
    6,320
    Likes Received:
    43
  9. Jamie Shorting

    Jamie Shorting Registered

    Joined:
    Sep 11, 2013
    Messages:
    2,628
    Likes Received:
    3

    To show benefits of this new tech I imagine. AFAIK, Mantle is sort of like opensource graphics code with AMDs tech. I remember when they first mentioned it a couple/few months ago and it seemed quite interesting. I haven't kept up with the news recently though.
     
  10. Marcel van der Linden

    Marcel van der Linden Registered

    Joined:
    Dec 11, 2010
    Messages:
    29
    Likes Received:
    0
    Yea but its only dx11 and rfactor2 is dx9.

    So still.

    What i want is smooth graphics and amd/ati isn't doing anything about it.
     
  11. Spinelli

    Spinelli Banned

    Joined:
    Jan 28, 2012
    Messages:
    5,290
    Likes Received:
    32
    I'm pretty sure the game has to support Mantle, not any DX11 automatically recieves a boost, the game has to have Mantle implemented, im almost sure.
     
  12. DurgeDriven

    DurgeDriven Banned

    Joined:
    Mar 20, 2012
    Messages:
    6,320
    Likes Received:
    43
    Oh yeah I real exicted !

    Already ordered my new AMD !@!




    lopl
     
  13. 88mphTim

    88mphTim racesimcentral.net

    Joined:
    Sep 23, 2010
    Messages:
    10,840
    Likes Received:
    314
    Yeah it's still interesting info.

    Though there's really no other title out there except AC and iRacing that I would use to benchmark to show percentages. DICE BF games really are NOTHING like a simulator and the gains will be quite different for anything math heavy. That said, however, I have shared this info with Joe.
     
  14. Spinelli

    Spinelli Banned

    Joined:
    Jan 28, 2012
    Messages:
    5,290
    Likes Received:
    32
    RFactor 2?
     
  15. 88mphTim

    88mphTim racesimcentral.net

    Joined:
    Sep 23, 2010
    Messages:
    10,840
    Likes Received:
    314
    Other than rF2, there's only two other (current) titles I would describe as math heavy, those are it. A DICE example doesn't give any indication of how it would help rF2. If AC charts went up, or iRacing charts went up if they supported it... Then that would give a really good idea of where rF2 would benefit.

    But for general gaming, this is an awesome sign. Remains to be seen what it can do for simulations.
     
  16. madquad

    madquad Registered

    Joined:
    Jan 31, 2014
    Messages:
    35
    Likes Received:
    12
    first of all I apologize for the English, google translator. : P
    I am closely following mantle and I think that is exactly in the simulations where all the power of this api can shine as it releases cpu load, which can be used precisely to mathematical calculations, multiple cores, threads I think it's the future.
    A strategic step:: Rolleyes: I'd say!
     
  17. DurgeDriven

    DurgeDriven Banned

    Joined:
    Mar 20, 2012
    Messages:
    6,320
    Likes Received:
    43
    From one test.

    Remember the Bulldozer hype anyone.

    Virtually anyone easily led has a 3800+ up is going to expect big gains, from one test.

    I think it remains to be seen what sims can do for it, not the other way round. It is up to the developer.
     
  18. 88mphTim

    88mphTim racesimcentral.net

    Joined:
    Sep 23, 2010
    Messages:
    10,840
    Likes Received:
    314
    Joe is certainly aware of it as he just told me how it works. We'll see.
     
  19. MJP

    MJP Registered

    Joined:
    Oct 5, 2010
    Messages:
    988
    Likes Received:
    21
    I think I would have been a bit concerned if he wasn't aware or had some idea of how it worked.
     
  20. madquad

    madquad Registered

    Joined:
    Jan 31, 2014
    Messages:
    35
    Likes Received:
    12
    more computing power, more fluidity, more likely to increase polygons on screen, richer environments and support amd insurance.:rolleyes:
     

Share This Page