Thursday, January 30th 2014

DICE Posts its Own Battlefield 4 DirectX vs. Mantle Performance Numbers

Along with its highly anticipated game patch that includes an AMD Mantle renderer for Battlefield 4, DICE posted numbers from its own testing, pointing out the performance difference between DirectX 11.1 and Mantle. DICE put Battlefield 4 through three test scenarios, entry-level gaming, mainstream gaming, and enthusiast gaming. The entry-level test-bed comprised of an AMD A10-7850K APU, with its integrated Radeon R7 200 series GPU (512 stream processors, 720 MHz GPU clock). This is a CPU and GPU limited scenario, in which the game was tested at 1280 x 720 pixels resolution. DICE notes that with Mantle, the game yielded about 14 percent higher frame-rates.

Next up, is mainstream gaming. The test-bed runs an AMD FX-8350, which offers roughly the same gaming CPU performance as a Core i5-3570K. A Radeon HD 7970 is in charge of graphics, and the game is run at 1920 x 1080 pixels resolution, with 1x MSAA and "Ultra" preset. DICE found that the setup yields about 26 percent higher frame-rates. Lastly, there's the enthusiast test-bed, running an Intel Core i7-3960X CPU, and dual Radeon R9 290X (CrossFire) graphics. The resolution stayed at 1920 x 1080, settings at "Ultra" preset, but the anti-aliasing was cranked up to 4x MSAA. The result? A stunning 58 percent higher frame-rates. It's important to note here that in addition to settings, the other thing that's not constant between the three setups is the test scene. Even if DICE' assessment is most generous towards AMD's claims, there really does seem to be a performance increment on offer, with Mantle. Can't wait to check it out for ourselves. For more details and notes from the developer, check out the source link.

Source: DICE
Add your own comment

63 Comments on DICE Posts its Own Battlefield 4 DirectX vs. Mantle Performance Numbers

#1
zhangteng242007
by: Fluffmeister
Battlefield 4 + Mantle
  • AMD FX-8350 + R9 290X +23% Performance increase Vs. Direct X
  • Core i5-4670k + R9 290X +7.5% Performance increase Vs. Driect X
  • Core i7-4960X CPU + R9 290X GPU[list]
  • 1080p, Ultra Preset, 4xAA: 9.2% improvement with Mantle
  • 1600p, Ultra Preset, 4xAA: 10% improvement with Mantle
  • Core i7-4960X CPU + R7 260X GPU
    • 1080p, Ultra Preset, 4xAA: 2.7% improvement
    • 1600p, Ultra Preset, 4xAA: 1.4% improvement
  • A10-7700K CPU + R9 290X GPU
    • 1080p, Ultra Preset, 4xAA: 40.9% improvement
    • 1600p, Ultra Preset, 4xAA: 17.3% improvement
  • A10-7700K CPU + R7 260X GPU
    • 1080p, Ultra Preset, 4xAA: 8.3% improvement
    • 1600p, Low Preset: 16.8% improvement
    [/list]Source: http://wccftech.com/amd-launches-mantle-beta-low-end-cpus-not-gpus/
  • We need to be optimized, rather than an independent technology, it couldn't survive long!Unless everyone want to the API.
    Posted on Reply
    #2
    the54thvoid
    by: zhangteng242007
    We need to be optimized, rather than an independent technology, it couldn't survive long!Unless everyone want to the API.
    Dude, stop shouting.....
    Posted on Reply
    #3
    TheMailMan78
    Big Member
    I THINK ITS AWESOME! WE SHOULD ALL TALK WITH BOLD CAPS! I LOVE PIE!
    Posted on Reply
    #4
    Cheeseball
    [SPOILER]I WISH I WERE A BIRD[/SPOILER]

    Hopefully I'll be able to see great gains with my current setup.
    Posted on Reply
    #5
    TheHunter
    nvidia fanboys need to bitch @ nvidia

    Let NV make a proper mantle driver - its a open API not bound to GCN, end of story.

    But nooo, its AMD fault and AMD sucks and what not.. Like i said this once some nv fanboys are like a plague in gaming industry...

    You should have seen all the commnets at battlelog, Omg:rolleyes:


    I own a NV gpu and I still think Mantle is almost God sent.. Just wait until its more widespread.
    Posted on Reply
    #6
    tokyoduong
    by: zhangteng242007
    The Mantle's Visual effects same as DirectX?
    And DirectX 11,11.2 was support?
    I think this technology is not practical.

    English? Are you in China being paid by NV or something?
    Are you using your translator properly?
    Posted on Reply
    #7
    TRWOV
    by: Supercrit
    I 'm kind of disappointed at the lower end system improvements. The whopping 58% higher performance is where it doesn't matter, not to mention the test is not done by a neutral 3rd party. At least it seems that the stuttering problem is gone.
    I think that's because of the iGPU's memory bandwidth, think of a DDR3 HD7750 vs the GDDR5 version. The other setups had the benefit of using GDDR5 plus I suppose ROPs have a hand in it too (8 vs 32 vs 64x2)






    by: tokyoduong
    English? Are you in China being paid by NV or something?
    Are you using your translator properly?
    Posted on Reply
    #9
    Crap Daddy
    • AMD FX-8350 + R9 290X +23% Performance increase Vs. Direct X
    • Core i5-4670k + R9 290X +7.5% Performance increase Vs. Driect X
    Good, in multiplayer they brought the 8350 close to a 4670, so basically if you run a Haswell i5 you'd still be better off that with an FX

    Posted on Reply
    #10
    btarunr
    Editor & Senior Moderator
    by: zhangteng242007
    The Mantle's Visual effects same as DirectX?
    YES IDENTICAL (THEY ARE CODE COMPATIBLE, WITH MANTLE HAVING ADDITIONAL CAPABILITIES THAT ARE EXCLUSIVE TO XBOX DIRECTX.)

    by: zhangteng242007
    [SIZE=6]And DirectX 11,11.2 was support?



    DIRECTX 11.1 IS SUPPORTED.

    by: zhangteng242007
    I think this technology is not practical.
    by: zhangteng242007

    [/SIZE]
    by: zhangteng242007

    THE GREEDIEST GAME STUDIO ON THE PLANET (EA) DISAGREES WITH YOU.

    Alright guys, enough screaming.
    Posted on Reply
    #11
    zhangteng242007
    by: tokyoduong
    English? Are you in China being paid by NV or something?
    Are you using your translator properly?
    Yes,China's English!Forgive me,My English was bad,I will to learn more in free time.
    Actually,I really like english,but when I was a child did not study hard
    Posted on Reply
    #12
    zhangteng242007
    by: btarunr
    YES IDENTICAL (THEY ARE CODE COMPATIBLE, WITH MANTLE HAVING ADDITIONAL CAPABILITIES THAT ARE EXCLUSIVE TO XBOX DIRECTX.)


    DIRECTX 11.1 IS SUPPORTED.


    THE GREEDIEST GAME STUDIO ON THE PLANET (EA) DISAGREES WITH YOU.

    Alright guys, enough screaming.
    Good reply!God reply!Thanks
    Posted on Reply
    #13
    Prima.Vera
    with all this huge bold text all over I thought my Windows 8'd DPI are fracked up again. ;))) Actually I was also trying to zoom out like an idiot...
    Posted on Reply
    #14
    FX-GMC
    by: Crap Daddy
    Good, in multiplayer they brought the 8350 close to a 4670, so basically if you run a Haswell i5 you'd still be better off that with an FX


    I'm curious to know why the FX6300 has a higher fps than the FX8350 in your picture there. This is contrary to logic, all other tests i've seen, to all the people whining that their FX six cores are struggling (From battlelog forums) and my own experience. Unless the combination of a FX8320 (4.6) + GTX760 is faster than a FX8350 (stock) + 7970Ghz or GTX770.
    Posted on Reply
    #15
    Crap Daddy
    by: FX-GMC
    I'm curious to know why the FX6300 has a higher fps than the FX8350 in your picture there. This is contrary to logic, all other tests i've seen, to all the people whining that their FX six cores are struggling (From battlelog forums) and my own experience. Unless the combination of a FX8320 (4.6) + GTX760 is faster than a FX8350 (stock) + 7970Ghz or GTX770.
    Well, hardwarepal, where I find these benchmarks says:
    As we continue we see again that the i3 and i5 beat the i7 as well as the FX 6300 beating the FX 8350. We concluded that this is an optimization issue, since Frostbite 3 Engine employs CPU’s with an amount of load that a quad core CPU can handle. Don’t get us wrong, this doesn’t mean that the game doesn’t utilize extra cores or threads, it means that for example the FX 8350 is working at ~50% load while the FX 6300 works at 66%. Non of them work at 100%, however since data is being more efficiently processed with less cores/threads you will get a weird situation where the i7 and FX 8350 are performing worse than the slower CPU’s.

    Read more: Battlefield 4 Benchmark – Multiplayer CPU and GPU W7 vs W8.1 http://www.hardwarepal.com/battlefield-4-benchmark-mp-cpu-gpu-w7-vs-w8-1/
    I just pass the info. We mostly rely on reviews to make decisions regarding what hardware we buy. This is one of them and it tests the CPUs in multiplayer conditions, the only thing worth playing in BF4. Whether it's accurate, I realy can't say.
    Posted on Reply
    #16
    FX-GMC
    by: Crap Daddy
    Well, hardwarepal, where I find these benchmarks says:



    I just pass the info. We mostly rely on reviews to make decisions regarding what hardware we buy. This is one of them and it tests the CPUs in multiplayer conditions, the only thing worth playing in BF4. Whether it's accurate, I realy can't say.
    That weird situation where the i7 and 8350 are performing worse that slower cpu's means something with their test system is not optimized.

    These are more in line with the real world (or at least what i've seen/read):





    To give reference, my setup (8350 @4.6 + GTX760 @ 1267MHz) gets an average of 72fps with a minimum of around 58-60fps.

    1080p Ultra settings 4xmsaa high post, etc.
    Posted on Reply
    #17
    NeoXF
    by: Crap Daddy
    Well, hardwarepal, where I find these benchmarks says:



    I just pass the info. We mostly rely on reviews to make decisions regarding what hardware we buy. This is one of them and it tests the CPUs in multiplayer conditions, the only thing worth playing in BF4. Whether it's accurate, I realy can't say.
    They sure don't look accurate. Most reviews on CPU performance, including the early Alpha/Beta tests, show it being close to, or even faster than the i5 4670K, and FX 9590 being at or slightly under i7 4770K levels.

    Edit: Pretty much what FX-GMC just said/posted before I pressed post (thanks!).
    Edit2: So what now again... is a FX 8350 build ~15% faster than i5 4670K one in BF4? AMD are witches! We all now Bulldozer sucks! Booooo! etc etc...

    by: Mathragh
    Yeah, when you think about it, BF4 isn't really an optimal game to showcase mantle on when it comes to performance, since it was already quite CPU-agnostic compared to lots of other games. Would've probably been a lot better for something like the newest Total War game, or Civilization V.
    Nope, BF3 was quite CPU agnostic... BF4 is a pretty different kind of beast. I guess you haven't followed many CPU benches on BF4, have you. :)
    Posted on Reply
    #18
    tokyoduong
    by: FX-GMC
    That weird situation where the i7 and 8350 are performing worse that slower cpu's means something with their test system is not optimized.

    These are more in line with the real world (or at least what i've seen/read):





    To give reference, my setup (8350 @4.6 + GTX760 @ 1267MHz) gets an average of 72fps with a minimum of around 58-60fps.

    1080p Ultra settings 4xmsaa high post, etc.
    Your system gets that frame rates at what map? how many players? what is happening? Does your settings match theirs? Does your set up match theirs?

    Your FPS can vary by just about anything. This is why benchmarks are made! Same exact repeatable scenario and expected results!
    Posted on Reply
    #19
    FX-GMC
    by: tokyoduong
    Your system gets that frame rates at what map? how many players? what is happening? Does your settings match theirs? Does your set up match theirs?

    Your FPS can vary by just about anything. This is why benchmarks are made! Same exact repeatable scenario and expected results!
    Except by nature, multiplayer benchmarks aren't repeatable.

    Here we go:

    Your system gets that frame rates at what map? No specific map (do note I am talking about the vanilla maps). When I play I notice fps in the low 70's most of the time. Lowest I've seen is around 55fps but usually min frames are around 60. Max frames can go up to 90.

    How many players? 64......duh.

    What is happening? Ever played battlefield? Shooting, explosions, people raging, flying, driving. That's what happens in battlefield.

    Does (I think you mean do there) your settings match theirs? Either matches their settings or they are skewing the numbers. You must of missed the part where I said MAX settings 1080p. (Well i didn't say MAX, but Ultra, 4xmsaa, and high post should cover max settings.)

    Does your setup match theirs? No it doesn't. Mine should be weaker, but my performance is better. If you would have followed along this has all been posted already.




    Got anymore questions?
    Posted on Reply
    #20
    Crap Daddy
    I'll post another one from sweclockers where the 4670k is considerably faster than an 8350, both stock with a high-end card.
    Posted on Reply
    #21
    FX-GMC
    by: Crap Daddy
    I'll post another one from sweclockers where the 4670k is considerably faster than an 8350, both stock with a high-end card.
    What do you mean by "both stock and with a high-end card"?

    Also, why are we talking about the i5 4670k now (I'm not taking the bait)? This was strictly about the FX6300 being faster in their "test" when it's not in the real world.
    Posted on Reply
    #22
    Deadlyraver
    TBH Frame rate consistency is more my concern than frame rates. Whats the point drooling on high frame rates when they don't even stay up for long? See this kind of comparison brings me assurance that there will be less slowdowns in the midst of air strikes.
    Posted on Reply
    #23
    Crap Daddy
    by: FX-GMC
    What do you mean by "both stock and with a high-end card"?

    Also, why are we talking about the i5 4670k now (I'm not taking the bait)? This was strictly about the FX6300 being faster in their "test" when it's not in the real world.
    It wasn't about the 6300. It was about the Dice results with Mantle and the 8350 vs. the 4670 paired with the same AMD card. Remember this is a thread about Mantle. Go back to my first post and you'll see that my conclusion regarding mantle is that, with high end set-ups it improves framerates for AMD CPUs better than with Intel CPUs, thus bringing the FX closer if not equal to Haswell i5. I showed you a couple of benchmarks to prove this.
    Posted on Reply
    #24
    FX-GMC
    by: Crap Daddy
    It wasn't about the 6300. It was about the Dice results with Mantle and the 8350 vs. the 4670 paired with the same AMD card. Remember this is a thread about Mantle. Go back to my first post and you'll see that my conclusion regarding mantle is that, with high end set-ups it improves framerates for AMD CPUs better than with Intel CPUs, thus bringing the FX closer if not equal to Haswell i5. I showed you a couple of benchmarks to prove this.
    The only part of your post that I had an issue with was the first benchmark you posted because it doesn't conform with real world usage. Remember this:
    I'm curious to know why the FX6300 has a higher fps than the FX8350 in your picture there. This is contrary to logic, all other tests i've seen, to all the people whining that their FX six cores are struggling (From battlelog forums) and my own experience. - ME
    I wholeheartedly agree that Mantle will benefit AMD procs more than Intel's. I just didn't get why you posted a benchmark that was 4670k and 8350 when I wasn't talking about any intel processors. Then again, I did assume you posted it in response to me. If you weren't posting it in response to me than my apologies and carry on.
    Posted on Reply
    #25
    MxPhenom 216
    Corsair Fanboy
    What in the hell. Looked at the pictures, after what people were saying with the fog, and it looks like they just reduced the draw distance and covered it with fog it to gain performance...............
    Posted on Reply
    Add your own comment