AMD Mantle Support?

[Cmdr Eagleboy]

Then I am glad to report:

There's been comments early on out of AMD that they would like to see the Mantle API supported on other platforms and it was reiterated this week during AMD's APU13 Developer Summit. AMD would like Mantle on Linux and Apple OS X as it would be significantly easier to do an efficient renderer with Mantle than OpenGL, according to AMD. Mantle also has uses beyond game-engines, reportedly in workstations and R&D too. One of the slides shared during the APU13 summit stated "Mantle + SteamOS = powerful combination!"

Sorry, but I don't buy this. OpenGL support to current level came to Linux in what 10 years? No time to waste support some theoretical third party API when there's already established tool set to do OpenGL.

Also AMD fglrx driver support for Linux is catastrophic.

 

[Maxeren]

The trouble with OpenGL as I understand it is that it moves really slowly in comparison to its competitors. I'd say it's likely that you'll see similar features appear in DirectX long before OpenGL.

Regarding whether NVIDIA take on the Mantle API, it will depend on how much of a performance benefit it brings and how many of the big game development studios adopt it. If AMD GPUs deliver much higher performance at the same price point as NVIDIA ones simply due to an implementation of an API, you can bet that they'll get support for that API implemented as soon as possible. Or if not, they'll be working to create their own or get something similar into one of the 'standard' APIs.

Actually features come in opengl before directx

Opengl might not have the "press" that directx has.. but opengl is very powerful.

 

[Dirk Braben]

Sorry, but I don't buy this. OpenGL support to current level came to Linux in what 10 years? No time to waste support some theoretical third party API when there's already established tool set to do OpenGL.

Also AMD fglrx driver support for Linux is catastrophic.

Currently everything is speculative.

Some speculate it will never happen, AMD speculates it will happen. Try to look on the bright side, they definitely don't deny possibility.

 

[Stachel]

I'm still reeling from the crushing disappointment that the Alpha does not support my child in Poland. Quietly optimistic for Beta.

 

[Pyros]

AFAIK, DX has its roots way too fixed in old concepts, accretion bloat and lacks cross environment (OS) support.

OpenGL is even worse as a gaming API - it comes from "another world" altogether.

In my almost complete ignorance of the subject, I think modern age gaming is needing a new API... whether mantle or another think.

 

[KING5TON]

I love the way everyone just ignores my post that contains actual hands on experience and links to figures just so they can continue arguing

 

[Im_Lost]

If mantle is only going to be for AMD cards then it's a waste of time tbh. Why invest the time in something only half your customers are ever going to use? You might as well spend all the time optimizing for a single API like OpenGL, which is cross platform and everyone can use equally.

I think mantle will go the same way Glide did unless it becomes open to all chipsets. It will be popular for a short while and then die off. It's not the future of gaming by any stretch. APIs of this kind are a good idea, but not unless it's open source.

 

[jabokai]

If mantle is only going to be for AMD cards then it's a waste of time tbh. Why invest the time in something only half your customers are ever going to use? You might as well spend all the time optimizing for a single API like OpenGL, which is cross platform and everyone can use equally. Especially with Linux and MacOS becoming more popular.

I think mantle will go the same way Glide did unless it becomes open to all chipsets. It will be popular for a couple of years and then die off.

Bit of a danger for nvidia that people will choose AMD cards (all else being equal) if Mantle gains at least moderate support, no? I usually buy the best bang for buck GPU at time of purchase - don't care whether it's AMD or nvidia - if a few choice titles support Mantle I can see that tipping the scales. Star Citizen will support it and, as I've pledged for that, that's me already thinking "hmmmm... AMD".

 

[Mazhurg]

If mantle is only going to be for AMD cards then it's a waste of time tbh. Why invest the time in something only half your customers are ever going to use? You might as well spend all the time optimizing for a single API like OpenGL, which is cross platform and everyone can use equally.

I think mantle will go the same way Glide did unless it becomes open to all chipsets. It will be popular for a short while and then die off. It's not the future of gaming by any stretch. APIs of this kind are a good idea, but not unless it's open source.

Really, why maximizing and using a piece of hardware properly instead of "Walt Disney" it?

Heck, why not make all hardware the same way, like console?.

<- sarcastic tag...

 

[Kerrash]

Really, why maximizing and using a piece of hardware properly instead of "Walt Disney" it?

Heck, why not make all hardware the same way, like console?.

That is the good thing about the PC space, is the opportunity for innovation; Mantle will have to expand in order to survive, but the growth can come later. Right now it is still finding its feet.

CUDA beat DirectCompute to market, so anything is possible.

 

[Robert Maynard]

Why invest the time in something only half your customers are ever going to use? You might as well spend all the time optimizing for a single API like OpenGL, which is cross platform and everyone can use equally.

Like Physx, for example?

 

[Stachel]

Like Physx, for example?

Indeed. If I ran a hardware business and I wanted to increase my market share I'd send a bunch of evaluation units to Frontier to include support in their game. Plus some cash obviously. I'd then find and pay the top content providers to demo and rave about my hardware and then some time after that I'd count my money.

The HOTAS guys seem to have done pretty well. Saitek in particular must be investigating the possibility of a new corporate HQ off the back of this crowd.

In fact ED is probably the first Kickstarter game I have seen that will actively encourage you to buy third party hardware to 'play it to its fullest'. Crappy flight sims and some driving games from the dark ages aside ..

 

[jabokai]

Indeed. If I ran a hardware business and I wanted to increase my market share I'd send a bunch of evaluation units to Frontier to include support in their game. Plus some cash obviously. I'd then find and pay the top content providers to demo and rave about my hardware and then some time after that I'd count my money.

The HOTAS guys seem to have done pretty well. Saitek in particular must be investigating the possibility of a new corporate HQ off the back of this crowd.

In fact ED is probably the first Kickstarter game I have seen that will actively encourage you to buy third party hardware to 'play it to its fullest'. Crappy flight sims and some driving games from the dark ages aside ..

I hate to mention "the other game" but at this stage if I were a hardware manufacturer I'd be courting CIG with my freebies. From what I gather in one of the Star Citizen updates they are indeed getting sent hardware. They're also (from what I read) in discussion with some joystick manufacturer to produce a custom HOTAS product.

Perhaps (and hopefully) ED will turn out the better game but it's undeniable that SC has the publicity and hype just now - which will attract such things.

 

[Doctor_Demento]

And lets not forget. AMD has a standing offer for Nvidia to use Mantle FREE. It's up to Nvidia to use Mantle. So if it ends up being "unequal", it will be Nvidia's fault, not AMD. And I am not letting mantle stop me from buying any game. I have 2 AMD 7850 in Crossfire. My concern is I hope FD supports Crossfire. (In fact Mantle code is free to ANY company that wants to use it.) Nvidia on the other hand STILL has code that if it detects a AMD video GPU (including onboard that is not being used) it shuts OFF PhysX. That is pretty petty in my mind.

 

[Wolfs Spirit]

AMD Mantle

With the new AMD mantle comming up , i seriously wonder if we could use it in Elite.
Since it boosts videocards FPS and gameplay, even better as direct-X .. less stress on your system and hardware using mantle.
I seen some titles online already using it and some benchmarks and the average difference in speed is 10-40% depending on the videocard.
I ran a benchmark myself today with the new mantle beta drivers and was very happy about it.

So please at least consider it

I would love to see a reply from a DEV and what their opinion is about this new tech

For info on what Mantle exactly does:

http://www.extremetech.com/gaming/175676-amds-mantle-finally-emerges-turns-out-its-actually-for-boosting-low-end-cpus-not-gpus

 

[Y2K]

DX 11.2 is just as good as Mantle. For the sake of a few extra fps which only really shows on mid-top end machines its not worth the hassle. DX 12 will leave mantle for dust.

So yeh, mantle is good in one way, it made MS update DX

 

[Sir.Tj]

Merged a couple of threads into this one as they are all on the same subject.

 

[Lorenzo]

Mantle will never be used by the majority of the Dev for one reason developing a game is expensive and coding two API's it's even more expensive, no game company in the right mind would develop a game for just half of the audience.
And that is why dx 11.2 and dx12 will be used over mantle.

 

[Robert Maynard]

Mantle will never be used by the majority of the Dev for one reason developing a game is expensive and coding two API's it's even more expensive, no game company in the right mind would develop a game for just half of the audience.
And that is why dx 11.2 and dx12 will be used over mantle.

So why did some code for Physx after NVidia subsumed the capability into their graphics cards?

 

[ICDP]

Mantle will never be used by the majority of the Dev for one reason developing a game is expensive and coding two API's it's even more expensive, no game company in the right mind would develop a game for just half of the audience.
And that is why dx 11.2 and dx12 will be used over mantle.

The majority of devs may not use Mantle, but not for the reasons you assume. It will be because the majority of games run perfectly fine on DirectX and most devs will not see any benefit by adding Mantle support. For other larger developers the added cost of implementing Mantle may be worth it. Mantle's biggest advantage is that it allows much lower end systems to play games they normally cannot. As PC/Laptop specifications drop, so does the cost of the system and by association, the number of sales. Cheaper sells more than expensive. So if you realistically reduce the minimum system requirements for a game, you by definition increase the potential number of sales.

With Mantle, laptops and PCs that could only run modern games at low 20s can now run them at 30+ FPS. This may not seem like much but it transforms a game from unplayable to playable.

As for your point on Mantle being expensive and time consuming to implement. The Star Swarm developers (not a big developer) stated that implementing Mantle required only 2 months work by 1 person.
http://image.slidesharecdn.com/gs-4145danbaker-131121095113-phpapp01/95/slide-22-638.jpg?cb=1385158383

Oxide's Dan Baker in a Maximumpc interview:

"Baker: APIs come and go. Once you support more than one, it's pretty easy to support a dozen–assuming there is parity in the hardware features, and assuming you don't have to rewrite your shaders in an entirely different language. If you release a title right now, you would end up with likely six paths. An Xbox360, a PS3, a PS4, a Xbox One, a DX9, and a DX11. For us, the graphics system is just a module that talks to the API. All we did for Mantle was replace the D3D module with a Mantle one. It's about 3,000 to 4,000 lines of code for the Mantle version, which took me personally about two months to write. In terms of support, at least for us, it wasn't terribly difficult."