The AMD Mantle Thread

[Carfax83]

Your CPU is 1 GHZ faster, that would make pretty big difference.

Also what MSAA? They were running at 4X.

Also try maxing out the blue (to bring it to the same look)

The single player campaign isn't CPU intensive, and I have speedstep enabled, so I doubt the CPU was running at 4.5ghz.. The CPU frequency tends to vary a lot with speedstep enabled, because the game doesn't need all that CPU power in campaign mode.

Also, setting it to ultra defaults the MSAA to 4x. And what do you mean by maxing out the blue?

 

[krumme]

This first path seems focusing on CPU optimizations. GPU side like crossfire and memory will come later.

http://battlelog.battlefield.com/bf4/news/view/bf4-mantle-live

I dont know why people think its final judgementday. Its an entirely new API and new driver. In beta stage ffs! The tools have just been released in beta stage end 2013. Lets at least give this ½ a year to develop and mature. Secondly fb3 is new and its their first mantle release. So:

beta tools + beta API + beta driver + first implementation of mantle vs a highly optimized dx 11 platform

If anyone actually cared about Johans presentation he lists lots of GPU optimizations they are just more complex and difficult to implement. There is lots of work to be done. That said bf4 is not the most obvious platform for launching mantle, but then we have just better performance for eg. rts waiting for us.

 

[jackstar7]

Also, setting it to ultra defaults the MSAA to 4x. And what do you mean by maxing out the blue?

Blue -> Blur

 

[Paul98]

The screenshots I posted were very telling, and just goes to show how under optimized AMD's drivers are when running the Direct3D 11.1 path.

Even my GTX 770s, which aren't even top of the line, outperformed the 290x CF rig. Only with Mantle do they offer comparable performance, and it's not like they are a huge leap over mine anyway.

Basically, this just goes to show what I, and others have been saying is true. AMD's drivers have inferior CPU utilization.. It's not that the GPUs aren't capable, it's the drivers which aren't properly optimized for multicore processors.

That's the only way I can explain such a massive difference..

You can't have any idea that they are setup the same. This is why we have reviewers so you can compare. If you have a custom config file to turn off blur, your in game settings won't make a difference.

 

[Skurge]

The screenshots I posted were very telling, and just goes to show how under optimized AMD's drivers are when running the Direct3D 11.1 path.

Even my GTX 770s, which aren't even top of the line, outperformed the 290x CF rig. Only with Mantle do they offer comparable performance, and it's not like they are a huge leap over mine anyway.

Basically, this just goes to show what I, and others have been saying is true. AMD's drivers have inferior CPU utilization.. It's not that the GPUs aren't capable, it's the drivers which aren't properly optimized for multicore processors.

That's the only way I can explain such a massive difference..

Lets just wait for reviews before making claims like the above shall we. Also reviews have shown AMD cards being faster than Nvidia cards in BF4 ESPECIALLY in crossfire.

 

[Paul98]

I dont know why people think its final judgementday. Its an entirely new API and new driver. In beta stage ffs! The tools have just been released in beta stage end 2013. Lets at least give this ½ a year to develop and mature. Secondly fb3 is new and its their first mantle release. So:

beta tools + beta API + beta driver + first implementation of mantle vs a highly optimized dx 11 platform

If anyone actually cared about Johans presentation he lists lots of GPU optimizations they are just more complex and difficult to implement. There is lots of work to be done. That said bf4 is not the most obvious platform for launching mantle, but then we have just better performance for eg. rts waiting for us.

He also said they will continue to work with mantle on BF4.

 

[krumme]

The screenshots I posted were very telling, and just goes to show how under optimized AMD's drivers are when running the Direct3D 11.1 path.

Even my GTX 770s, which aren't even top of the line, outperformed the 290x CF rig. Only with Mantle do they offer comparable performance, and it's not like they are a huge leap over mine anyway.

Basically, this just goes to show what I, and others have been saying is true. AMD's drivers have inferior CPU utilization.. It's not that the GPUs aren't capable, it's the drivers which aren't properly optimized for multicore processors.

That's the only way I can explain such a massive difference..

I wouldnt want to play multiplayer on 1.67ghz jaguars as the consoles does Try doing that with dx using an NV card.

The talk about amd dx cpu utilization in bf4 is still unsubstantiated and your personal opinion.

 

[ASM-coder]

The single player campaign isn't CPU intensive,...

Johan says otherwise.
"This single-player scene is heavy on both the CPU and GPU with lots of action going on."
And that's where Mantle really helps. It allowed his test CPU to perform as well as your overclocked CPU.

 

[krumme]

He also said they will continue to work with mantle on BF4.

Yes he did. And he have said as i recal they have made an entire new rendering pipeline for mantle. They need to get this job done good, because its also the platform for their fb3 engine, and its going to be used for at lot of games.

 

[tonyfreak215]

The single player campaign isn't CPU intensive, and I have speedstep enabled, so I doubt the CPU was running at 4.5ghz.. The CPU frequency tends to vary a lot with speedstep enabled, because the game doesn't need all that CPU power in campaign mode.

Also, setting it to ultra defaults the MSAA to 4x. And what do you mean by maxing out the blue?

Just because you doubt it was running at 4.5, doesn't mean you can claim it as a comparison.

Blue=Blur. It was a simple typo.

 

[smackababy]

If anyone actually cared about Johans presentation he lists lots of GPU optimizations they are just more complex and difficult to implement. There is lots of work to be done. That said bf4 is not the most obvious platform for launching mantle, but then we have just better performance for eg. rts waiting for us.

So, it takes more than 2 man months to get anything meaningful from the API?

 

[jackstar7]

So, it takes more than 2 man months to get anything meaningful from the API?

I don't understand your question...

 

[Carfax83]

OK, just maxed out the blur, and it made no difference in frame rate or appearance.. I have no idea why AMD's screenshot is so blurry. Perhaps it was taken while the character was in motion, but that's a stupid way to take a screenshot.

My screenshot looks way more detailed than AMD's.

 

[ASM-coder]

So, it takes more than 2 man months to get anything meaningful from the API?

Objection your honor. The question is argumentative, and board has already answered substantially similar questions.

 

[Stuka87]

So, it takes more than 2 man months to get anything meaningful from the API?

The 2 man months was for adding Mantle after the fact to a game that was already mostly finished. But even at that, 2 man months is not much at all when you look at how many people Dice has working on BF4.

Anytime you add something like this late in the game, it will take longer than if you go through and start implementing it from day one.

 

[parvadomus]

The screenshots I posted were very telling, and just goes to show how under optimized AMD's drivers are when running the Direct3D 11.1 path.

Even my GTX 770s, which aren't even top of the line, outperformed the 290x CF rig. Only with Mantle do they offer comparable performance, and it's not like they are a huge leap over mine anyway.

Basically, this just goes to show what I, and others have been saying is true. AMD's drivers have inferior CPU utilization.. It's not that the GPUs aren't capable, it's the drivers which aren't properly optimized for multicore processors.

That's the only way I can explain such a massive difference..

A 770SLI is NOWHERE NEAR a 290X CF setup, the 290x is ~25% faster. Your screenshots dont even look the same as the ones submitted by AMD, and the test setup, hardware, software, etc. is not even the same. Basically a pointless claim.

PS: 290X is 40% faster in BF4 according to this review Link You really think you can touch a 290X CF with a pair of 770? lol

 

[krumme]

Johan says otherwise.
"This single-player scene is heavy on both the CPU and GPU with lots of action going on."
And that's where Mantle really helps. It allowed his test CPU to perform as well as your overclocked CPU.

I dont care for sp the slightest.
But there is plenty of places and situations in mp 64 man where my min fps goes below 60 fps (i5 ib at 4GHz (4c 4t) and where i am not gpu limited. Often when there is eg levolution. And i miss some of this consistent steady fps.

As the cpu frames are more inconsistent than the gpu frames, i hope we will get better smothness of the game using mantle to help the consistency of the cpu frame to frame.

 

[jackstar7]

OK, just maxed out the blur, and it made no difference in frame rate or appearance.. I have no idea why AMD's screenshot is so blurry. Perhaps it was taken while the character was in motion, but that's a stupid way to take a screenshot.

My screenshot looks way more detailed than AMD's.

Wait, you don't think that taking a screen while someone is actively playing (moving) is better than standing still?

 

[Stuka87]

Here's a screenshot comparison on my rig to the example DICE/AMD gave on the battlelog website.

First off, here are the examples AMD/DICE gave, which were run on a 3960x and 290x CF rig at 1080p ultra:

Mantle off:


Mantle on:

And now here's mine, run at 1080p ultra. I have no idea why my screenshot is so clear, whilst AMD's so blurry. Motion blur is set to default, which is 50%. CPU is overclocked to 4.5ghz (although I'm pretty sure it wasn't running full speed) and GTX 770 SLI 4GB GPUs were at stock clocks, which is 1241 with boost. If you notice, it says I'm running Direct3D 11 even though I'm on Windows 8.1 Pro:

Uhm, not only is your whole system entirely different, but AMD's screenshots are while actively playing and moving around, which is why the screen is blurry. They have motion blur set up. You took a screen shot with nothing happening. So of course yours will look better.

How about waiting for a review? Your claims of a SLI 770 setup being faster than a CF 290X setup are just straight wrong. As proven by MANY review sites.

 

[tonyfreak215]

Uhm, not only is your whole system entirely different, but AMD's screenshots are while actively playing and moving around, which is why the screen is blurry. They have motion blur set up. You took a screen shot with nothing happening. So of course yours will look better.

How about waiting for a review? Your claims of a SLI 770 setup being faster than a CF 290X setup are just straight wrong. As proven by MANY review sites.

Not to mention the whole 1 GHZ faster processor...

 

[Carfax83]

Johan says otherwise.
"This single-player scene is heavy on both the CPU and GPU with lots of action going on."
And that's where Mantle really helps. It allowed his test CPU to perform as well as your overclocked CPU.

OK I played through the scene in windowed mode, and using CPU-Z, verified that yes, my CPU was running at 4.5ghz..

Not sure if that explains the huge discrepancy between the Mantle off FPS, and what I got though. A 3960x has a max turbo boost of 3.9ghz, which isn't too far off from 4.5ghz.

 

[frozentundra123456]

We're really focusing on average FPS? Good god, it's like "Inside the Second" never happened. Those Kaveri frametime graphs are ridiculously improved- that gameplay is going to be a LOT smoother than it was under DirectX.

Maybe the frametimes are improved, but it is still at 720p low settings. Even if you could force it to medium or high on 720p, you would still be better off with a console.

 

[tonyfreak215]

OK I played through the scene in windowed mode, and using CPU-Z, verified that yes, my CPU was running at 4.5ghz..

Not sure if that explains the huge discrepancy between the Mantle off FPS, and what I got though. A 3960x has a max turbo boost of 3.9ghz, which isn't too far off from 4.5ghz.

Turbo wouldn't be at 3.9 using all 6 cores. More likely 3.5-3.7ish depending on cooler.

 

[Skurge]

Turbo wouldn't be at 3.9 using all 4 cores. More likely 3.5-3.7ish depending on cooler.

You mean 6 cores.

 

[tonyfreak215]

You mean 6 cores.

Thanks. Edited.