AMD Mantle API [updating]

What I'm questioning is the slide and claim that in the future we should continue to develop some portable version of Mantle alongside DirectX/GL - that simply doesn't makes sense in my opinion unless there's an absolute failure to integrate the relevant improvements into those.

Let me put this another way... what's AMD/DICE's move if NVIDIA (again, for example) says "sure, let's standardize the Mantle concepts but we'd like Microsoft onboard" and the result becomes a new DX version (or similar for some OpenGL reboot)? Does AMD continue to develop new versions of Mantle along-side that effort? If truly the goal is to get to a portable, standard API, that should be considered the ideal end-goal for everyone, right?
I don't work in this area and may be naive, but I would think if OpenGL adopts some of the same methods as Mantle resulting in there being < 5% performance difference between the two the business case for maintaining Mantle will go away.
 
Suddenly I am becoming excited with Mantle. And this coming from someone with a slight bias to nvidia :D

However, not really about GPUs per se, but the impact it seems to have on CPU performance as well.. Supposedly an AMD FX8350 can compete with the Core i7 4770K using Mantle. Granted while using more power, but this can be the beginning of very good things for AMD and consumers alike :cool:
 
If Mantle is multi-vendor API I will buy 780Ti. :LOL:

September 25, AMD says:
Mantle works with all GCN GPUs.
PCGH asked Raja Koduri about Mantle and its "openess". He replied that AMD doesn't see Mantle as an open standard like OpenCL or OpenGL. He also tried to brush aside comparisons with Glide but then stated: If a competitor were to approach AMD to make their own backend and drivers for Mantle, AMD would not dismiss them right away.


November 14, AMD says:
Mantle not not tied to GCN really. Believes Mantle would be a much more efficient model for other GPU vendors (NVIDIA) as well. Opening the door to NVIDIA... this is big. Hopefully NV will accept. It would be a big win for gaming, since MS hasn't been wanting to invest in pushing out DX.

Idiots in AMD corp. LOL. :LOL:
 
If Mantle is multi-vendor API I will buy 780Ti. :LOL:

September 25, AMD says:
Mantle works with all GCN GPUs.
PCGH asked Raja Koduri about Mantle and its "openess". He replied that AMD doesn't see Mantle as an open standard like OpenCL or OpenGL. He also tried to brush aside comparisons with Glide but then stated: If a competitor were to approach AMD to make their own backend and drivers for Mantle, AMD would not dismiss them right away.


November 14, AMD says:
Mantle not not tied to GCN really. Believes Mantle would be a much more efficient model for other GPU vendors (NVIDIA) as well. Opening the door to NVIDIA... this is big. Hopefully NV will accept. It would be a big win for gaming, since MS hasn't been wanting to invest in pushing out DX.


Idiots in AMD corp. LOL. :LOL:

"Idiots"? Both statements aren't mutually exclusive to be true.
And you don't know what performance gains could ever be had if you use a Kepler GPU.
 
Suddenly I am becoming excited with Mantle. And this coming from someone with a slight bias to nvidia :D

However, not really about GPUs per se, but the impact it seems to have on CPU performance as well.. Supposedly an AMD FX8350 can compete with the Core i7 4770K using Mantle. Granted while using more power, but this can be the beginning of very good things for AMD and consumers alike :cool:

I think it's going to matter a lot more to (small) APUs, especially those with dynamic bi-directional power management, as the power saved on the CPU side will be available for the GPU side, which could result in really nice gains.
 
If Mantle is multi-vendor API I will buy 780Ti. :LOL:

September 25, AMD says:
Mantle works with all GCN GPUs.
PCGH asked Raja Koduri about Mantle and its "openess". He replied that AMD doesn't see Mantle as an open standard like OpenCL or OpenGL. He also tried to brush aside comparisons with Glide but then stated: If a competitor were to approach AMD to make their own backend and drivers for Mantle, AMD would not dismiss them right away.


November 14, AMD says:
Mantle not not tied to GCN really. Believes Mantle would be a much more efficient model for other GPU vendors (NVIDIA) as well. Opening the door to NVIDIA... this is big. Hopefully NV will accept. It would be a big win for gaming, since MS hasn't been wanting to invest in pushing out DX.

Idiots in AMD corp. LOL. :LOL:

It wouldn't make sense for a dev to use Mantle for cards whose hardware functions and memory model aren't closely mapped to the Mantle language even if it were open; adoption and openness are different and I think Raja was probably talking about adoption by nVidia. AMD's mantle will have plenty of traction though since they had all those console design wins. Edit: We also have this Quote:

Andersson made it clear that, while it only supports GCN-based GPUs right now, Mantle provides enough abstraction to support other hardware—i.e. future AMD GPUs and competing offerings. In fact, Andersson said that most Mantle functionality can work on most modern GPUs out today. I presume he meant Nvidia ones, though Nvidia's name wasn't explicitly mentioned. In any event, he repeated multiple times that he'd like to see Mantle become a cross-vendor API supported on "all modern GPUs."

One of those slides posted above was interesting:

http://techreport.com/news/25651/ma...ite-games-dice-calls-for-multi-vendor-support

it said that the Mantle core renderer is closer to PS4 than DX11; makes sense since the PC's architecture is closer to the PS4's as it doesn't have eSRAM. Maybe DX12 will get some optimization from work done for XBOne: it could eventually expose some Mantle functions or rewrite existing functions in a better way, but I doubt they'd be willing to expose all the un-abstracted memory management available to Mantle to a vendor agnostic PC API.
 
Last edited by a moderator:
Nemo, are you confusing Johans comments with "AMD"?

I'm sorry if I wrong, Dave. :oops:


It wouldn't make sense for a dev to use Mantle for cards whose hardware functions and memory model aren't closely mapped to the Mantle language even if it were open; adoption and openness are different and I think Raja was probably talking about adoption by nVidia. AMD's mantle will have plenty of traction though since they had all those console design wins. it said that the Mantle core renderer is closer to PS4 than DX11; makes sense since the PC's architecture is closer to the PS4's as it doesn't have eSRAM. Maybe DX12 will get some optimization from work done for XBOne: it could eventually expose some Mantle functions or rewrite existing functions in a better way, but I doubt they'd be willing to expose all the un-abstracted memory management available to Mantle to a vendor agnostic PC API.

Thanks. I see two other slides about DX/GL Parallelism and Parallel Dispath with Mantle... but many years NV has this features in DX11 too. ;)
 
I see two other slides about DX/GL Parallelism and Parallel Dispath with Mantle... but many years NV has this features in DX11 too. ;)
AMD's claim is Mantle's parallel dispatch is better than DX's implementation.
 
The reality is if process technology's were not slowing down/getting more expensive then we would have much faster CPUs and GPUs every 12-18 months - which would allow DX to continue down it's inefficient for modern GPUs (Fermi, Kepler and GCN) path.

The longer console cycles, and the slowing of new hardware releases should of prompted MS to invest R&D into DX12 to make it a more console-style (low-level) API like Mantle. IMHO Microsoft has dropped the API ball.

If Mantle forces MS to make a new DX12 (especially after noises from MS have said the DX11 would be their last API!) all the better.
 
I think the multi-GPU benefits could be astounding for that market. For so long it's always been AFR, doing tricks to smooth timing issues, not able to use shared resources etc. The ability to allocate specific rendering tasks to either GPU or even onboard APU combined with discrete is fantastic.
 
cut

I fully agree, but then the question remains - why do we need Mantle if we can just adopt similar improvements into DX/GL? I still have yet to get an answer to what is wrong with the current standards setup.

cut


because Amd is a company and rightly looks to its interests before those of competitors? In a situation like the present one, ie hw of both consoles provided by AMD, why not take advantage to push its own hw also in pc? From the business point of view the "move" of mantle is outstanding, they have also caught the right partner with DICE by me.
 
Yes, as pMAX says the possibility of running GPGPU code on the integrated GPU for example is very exciting and something AMD has alluded to in a previous slide. It would certainly make AMD CPU's more appealing but then you have the 8 core scaling benefits competing with the iGPU GPGPU benefits. Would be nice to see these advantages extend to other vendors in the form of an open API though. To harness both the CPU and iGPU power of Haswell for example would be amazing!
 
cut


I'm not too sure, their quality assurance is shockingly bad


I do not know on what basis you say this, however BF4 is one of the hottest titles at the moment, certainly an important showcase for Mantle, and other "blockbusters" based on frostbite3 as ME4 or the new Dragon Age are just as important at least in terms of potential diffusion
 
I don't work in this area and may be naive, but I would think if OpenGL adopts some of the same methods as Mantle resulting in there being < 5% performance difference between the two the business case for maintaining Mantle will go away.
Right, and I had been assuming that was the plan too. But Johan's comments seemed to indicate otherwise... guess I'll wait for clarity.

because Amd is a company and rightly looks to its interests before those of competitors?
... which is totally fine, as I said. I'm not criticizing anything they've done, just the claim that in the future everyone should "adopt" Mantle as the future of graphics APIs. They're trying to play a PR game here and deflect criticism about doing a proprietary API. If they're going to do that, I think it's fair to ask for a firm statement about their future plans with respect to the rest of the industry.

I don't expect to get an answer, but enthusiasts deserve to know the other side of the story.
 
AMD's first interest should be to outclass the competitors. The way to success passes only through this. If they look after what their competitors are interested in, they will never beat them, and never grow... Isn't this exactly what they want?

Oh, and here it is the customers interest to get more performance on the same hardware... I am open with my two hands and waiting for it... Can't wait!
 
cut
... which is totally fine, as I said. I'm not criticizing anything they've done, just the claim that in the future everyone should "adopt" Mantle as the future of graphics APIs. They're trying to play a PR game here and deflect criticism about doing a proprietary API. If they're going to do that, I think it's fair to ask for a firm statement about their future plans with respect to the rest of the industry.

I don't expect to get an answer, but enthusiasts deserve to know the other side of the story.


ok, if you look at my interventions in this same thread, you will find that from this point of view I completely agree with you, and in fact as a consumer i'm not at all happy with mantle (while recognizing the the flow rate of innovation and being attracted by promises improvements): my only hope is that it will shake the industry for the agnostic api improved and go back to being free to choose the pc components especially for their "goodness" intrinsic, not because they are better than others thanks to "tricks".
 
Back
Top