The mantle driver support 1 uArch, the Mantle API (against which you code) works for any hardware a mantle driver exists for.
Why should we want Mantle in games if it only supports one architecture. PC doesn't keep one arch like consoles.
Nvidia went through G80, G200, GF100, and GK100 with 4 different architectures.
Even AMD had VLIW5, VLIW4, and GCN for the past 3.
So instead of evolving the arch, they'll rely on Mantle?
The mantle driver support 1 uArch, the Mantle API (against which you code) works for any hardware a mantle driver exists for.
There has been a lot of speculation regarding AMD's new Mantle low-level API, specifically regarding if it's open or not, meaning can Nvidia & Intel add support to Mantle if they wish ? the official answer from AMD's Robert Hallock, Enthusiast Graphics Marketing Manager is a definitive NO.
Tech Fan@ic . ‏
@Thracks is MANTLE open source ?
Details
Robert Hallock ‏
@GnrlKhalid No. It is an API for the industry-standard GCN Architecture and its specific ISA, done at the request of game developers.
So not only is MANTLE AMD specific, it's also architecture specific, so it's only compatible with Graphics Core Next (GCN) based products, that's the 7000 series and up for discrete graphics, Kaveri & later for APUs.
Thats not what AMD says.
The people living in a bubble when this was pointed out for them literally countless times throughout this thread really need to stop posting.
Its a classic hype case. And even worse, its mixed in with advocates, focus members and the like. Just look at the numbers. We already passed the 50% mark. And some think 250% faster is possible. Completely out of touch with reality.
Or look at the sound. Nobody cared about EAX etc. And now a company with several year old tech is suddenly the best thing in the world.
Not to mention no specs, no SDK for Mantle until 1-2 years down the road. Or the illusion that its a console API and will run on SteamOS as well.
This combined with the fact that this supposed mantle is only claiming to multi-thread draw calls.
It literally claims nothing else concretely whatsoever.
There were reports yesterday about Mantle being an open standard ???
Chris Hook, Head of PR - Mantle is an industry standard.
So Mantle is not an open standard ? Let's say some IHVs [Independent Hardware Vendors] want to write a Mantle backend/driver, what would be the requirements for them ?
RK - Mantle is in a very early stage, it's the first disclosure about it we've done, we have the first proof point using that, that is going to ship into some products. We are open to many possibilities with Mantle. We are open to being open; we are open to being standard. How it evolves if our competitor approaches us and says "we want to be compatible with Mantle" ? ... That's a conversation we are not going to shut down.
Chris Hook, Head of PR - There aren't many companies of course... Because of GCN they don't have Mantle capable hardware today
RK - But Johan said it clearly in his video that he's hoping that Mantle becomes a standard adopted by other companies which means, because game developers were involved in the design, there was feedback loop, that it is not designed in such a way that it can only work on our architecture. It's a thin abstraction, it's low level. Still it kind of amazingly provides all the performance, all what can be allowed on our architecture.
Is Mantle already influencing future GPU designs ? Could it bring more freedom for you to add extra features ?
RK - What's happening, the next DirectX, advances in OpenGL, advances in OpenCL, it's the same initiative that we have. We take all of this into consideration. I wouldn't say that we are just looking at Mantle and say "oh I can go off and do something crazy", definitely not thinking along this direction. But it does bring an ability for us to expose if we come off with an hardware innovation and we couldn't get it into a standard API for whatever reason, because of the cycle or something It does provide a path mechanism for us to make it available to the developers, which is always a nice thing for a hardware company to be able to do.
Could we imagine that in a couple of years, a future architecture won't be able to run the first Mantle games ? Or did you design Mantle to be forward compatible ? There's always this kind of tradeoff with a lower level access
RK - Those are all great questions but Frankly we'll see how it goes. At the end of the day forward compatibility and backward compatibility are important aspects but if they're getting in the way of solving a problem at a given point of time, if they're getting in the way of exposing something that the new hardware is capable of that makes the game be hundred times more realistic, we have to be practical about it and thats how we move things forward. We move technology forward and at some point of time we have to say "out with the old compatibility", and move forward. If not you get stuck.
Sounds fine. GCN is already 2 years old and brand new GCN cards are releasing soon. AMD is using Mantle to leverage large performance advantages in games that use the API and taking advantage of their console dominance to get developers using it.
So any AMD card from two years ago and going forward will support it. Obviously all their cards going forward will continue to since they're not just doing this for a short while and tossing it away. This looks to have been planned for a while now.
http://www.hardware.fr/focus/89/amd-mantle-interview-raja-koduri.html
I think it's an awesome innovation and if it can bring even 20% nevermind the possible higher performance gains just by a more efficient render API rather than having to wait for process nodes improvement it will be a huge win.
We'll find out in a couple months when we see AMD DX11 vs AMD Mantle vs Nvidia DX11 benchmarks in Battlefield 4 just how big a deal this is going to be for AMD performance.
Ah, right. AMD can't design new hardware. That's why their GPU's are in the Playstation 4, the XBox One, the Wii U and in the PC market. That must also be why Nvidia got squeezed out of all of the next gen consoles. They're way too busy designing other new hardware. Like... project Shield.That's the plan. Designing new hardware cost a lot of money. Something AMD doesn't have - nVidia is investing around $900 millions into graphics R&D in this year. That is 66% of AMD's graphics revenue...
AMD saw a way to leverage increased performance from existing and future hardware through cross-platform porting and low-level programming. What's wrong with free performance boosts?With a proprietary API they do not need to invest the same kind of money because there is no fair fight anymore between them and at least nVidia.
snip
http://www.tomshardware.com/news/Tegra-4-PlayStation-PS4-Tony-Tamasi-PhysX,21530.htmlNow, in 2012, with the Wii U leading the next-generation pack, Nvidia isn't involved at all other than PhysX and APEX support in the PlayStation 4 SDK (so far). Tony Tamasi (Nvidia Senior VP of Content and Technology) indicated that Nvidia is just too busy with other projects to invest in console development, including Nvidia GRID for Internet-based cloud gaming and Nvidia Shield for local cloud gaming.
"We're building a whole bunch of stuff, and we had to look at console business as an opportunity cost," he said. "If we, say, did a console, what other piece of our business would we put on hold to chase after that?"
He goes on. "In the end, you only have so many engineers and so much capability, and if you're going to go off and do chips for Sony or Microsoft, then that's probably a chip that you're not doing for some other portion of your business," he said. "And at least in the case of Sony and Nvidia, in terms of PS4, AMD has the business and Nvidia doesn't. We'll see how that plays out from a business perspective I guess. It's clearly not a technology thing."
Ah, right. AMD can't design new hardware. That's why their GPU's are in the Playstation 4, the XBox One, the Wii U and in the PC market. That must also be why Nvidia got squeezed out of all of the next gen consoles. They're way too busy designing other new hardware. Like... project Shield.
It's not free. Without using the API you dont have a "free performance boost".AMD saw a way to leverage increased performance from existing and future hardware through cross-platform porting and low-level programming. What's wrong with free performance boosts?
Yes. If AMD cant be competitive on a open plattform they should leave the market. If they think console are so much better they can concentrate on their supplier role.Are you honestly trying to tell us that AMD should have scrapped Mantle because it wouldn't be a "fair fight" between them and Nvidia?
You're the one who said that AMD can't design hardware because they have no money, not me. Obviously with their GPU's being incorporated into the WiiU, the PS4, the XBox One and coming out with their next generation PC video card, AMD is more than capable of turning out multiple simultaneous high-end designs.nVidia is making money, AMD is not. So maybe next time you should not talk about other companies which doing much better.
And what's your problem with Shield? At least i have more than one game on it. :awe:
If Mantle can give me better framerates than DX11 on my GCN video card, then as far as I'm concerned it's free performance. It's no different than getting higher framerates due to an improved driver.It's not free. Without using the API you dont have a "free performance boost".
You mean open platforms like PhysX?Yes. If AMD cant be competitive on a open plattform they should leave the market. If they think console are so much better they can concentrate on their supplier role.
I doubt Mantle is designed to be a simple stop-gap measure due to the 20nm delay. Since GCN hardware will be present in the console market for at least the next 6-10 years, I would expect AMD to continue to leverage their presence in both the PC and console with Mantle.Again I don't see why they need to anyway. If you compare say the 6970 to the upcoming 290X there is a huge 100%+ gap in performance. Even if AMD ditched GCN at 20nm - which we know isn't going to happen - the pure performance lead of the new cards would still overtake the old cards under Mantle unless Mantle gives some really spectacular performance gains.
I don't really see it as much of an issue so long as it's understood Mantle is a bonus that might only last 1-2 years on your graphics card, which is pretty much as long as should be expected anyway?
I doubt Mantle is designed to be a simple stop-gap measure due to the 20nm delay. Since GCN hardware will be present in the console market for at least the next 6-10 years, I would expect AMD to continue to leverage their presence in both the PC and console with Mantle.
I'd agree.
If nothing else it'll allow AMD to keep competitive in the OEM market with future APU's based on GCN technology. Maybe the predicted all things transitioning to mobile is the real big picture for Mantle?
Because many people don't want a PC port with worse graphics than the console version.Why should we want Mantle in games if it only supports one architecture. PC doesn't keep one arch like consoles.
I don't think that AMD want to replace GCN in the following years. This architecture support many features. It will take two or three years for Nvidia to catch up in the hardware side. The API is the bigger issue now.Nvidia went through G80, G200, GF100, and GK100 with 4 different architectures.
Even AMD had VLIW5, VLIW4, and GCN for the past 3.
Every driver is multi-threaded. AMD and NVIDIA is also doing many hacks to improve performance. The only thing what AMD don't support is command list, because they can gain more performance with their multi-threaded hacks in Civilisation V. Other games don't support DX11 multi-thread/command list.Also, think of all the people stuck with GCN cards that don't have multi-threaded drivers to go with them and how massive the draw calls will be in games like probably the next elder scrolls game and grand theft auto game.
What I would like to know is what problems are there in DX11 where major gains could be had and how they would translate into real world performance.