DirectX and OpenGL to get low level access according to leaked statements (GDC 2014)

[MeldarthX]

After way Khronos handled 3.3 yea.....I have complete faith in them; not.

MS how many times have they promised this [bull honkey]. PC gaming hasn't even been an afterthought for MS for years - and promises of they will make sure PC gamers are taken care of *[bull honkey] again*

I'm in the camp of; if they actually deliver awesome; but also will use Mantle to keep those two honest.

If mantle developes into something far greater also as it keeps the pressure on MS and Khronos to actually get off their [padded seating apparatusses] and do sometime. Until then its lip service.

AMD's actually delivering....now lets see if MS and Khronos will or if its more bs

Inappropriate language is not allowed in VC&G.
-Elfear

 

[Gikaseixas]

MS sat on their [redacted] all these years. This is a reactive action due to Mantle no doubt so THANK YOU AMD

Inappropriate language not allowed in VC&G

-Elfear

 

[OCGuy]

With Mantle being delayed on another title, I think any DX improvements are welcome.

 

[cytg111]

In this unprecedented sponsored session, Graham Sellers (AMD), Tim Foley (Intel), Cass Everitt (NVIDIA) and John McDonald (NVIDIA) will present high-level concepts available in today’s OpenGL implementations that radically reduce driver overhead–by up to 10x or more.

Compile Error line 1. [high-level concepts available in today’s] [reduce driver overhead–by up to 10x]
If it is available today, how can it improve a factor of 10? Relative to what? Something 10 times slower? Earlier revision x? Mkay.
I am sure its all good though .. Interesting times. (numbers, numbers, numbers, numbers)
Oh yea, lets get this thread closed, its heading nowhere fast.

 

[Will Robinson]

Any close to the metal API refinements that MS implement are a direct result of AMD inventing and delivering with Mantle.
Everyone wants Direct X to be more granular and allow greater freedom to developers whilst still being hardware agnostic.
AMD is right there at the Microsoft meeting,that's a smart move and is hard to fault.

 

[Atreidin]

MS sat on their [redacted] all these years. This is a reactive action due to Mantle no doubt so THANK YOU AMD

This push forward is clearly due to AMD lighting a fire under everybody's [redacted]. However I'm not surprised with the usual suspects spinning this to be as anti-AMD as possible.

Inapproriate language not allowed in VC&G
-Elfear

 

[n0x1ous]

Thank you AMD!

 

[Will Robinson]

Intel really need to deliver some big IPC gains and get a move on as graphics chips are disappearing over the horizon.

 

[OCGuy]

Any close to the metal API refinements that MS implement are a direct result of AMD inventing and delivering with Mantle.
Everyone wants Direct X to be more granular and allow greater freedom to developers whilst still being hardware agnostic.
AMD is right there at the Microsoft meeting,that's a smart move and is hard to fault.

Tiled resources.in 11.2 were announced months before Mantle.

 

[Gloomy]

So what, we'll have to wait three years or more for everyone to move onto whatever Windows version is a mandatory install, whatever video cards are mandatory upgrades, and for developers to see the increased audience and decide to ship a game that uses it... and it'll still be only a handful of games.

I mean don't get me wrong, I want games that run fast as much as anyone else. Unlike the folks who spent the last three months bashing Mantle though, my expectations are tempered by the reality that was DX11 adoption... which is just recently gaining steam despite being unveiled in... what, 2008? Cripes.

I really do hope Mantle and OpenGL (which all three GPU manufacturers are pushing now) make Microsoft wake up and handle DX better. Because otherwise we are in for another long and drawn out transitional period.

Actually, scratch that. I hope they bungle this and OpenGL beats it into the ground.

 

[MeldarthX]

See my post - we've seen just how well Khronos runs [redacted] with 3.3 debacle. MS has been promising years; not just a couple its 6+ years now that PC gaming will once again take for front with MS.

[Redacted] on both fronts - as I said; I'll believe it when I see it. Until Both MS and Khronos actually put their money where their mouth is and actually deliver what they promise in a timely fashion. *aka not 5+ years from now for MS and 10+ years for Khronos; but actually now* I will continue to support mantle. Its not DOA - its actually delivering for beta software in partly alpha form.

It took MS how long with DX to make it useful? 6.1 - wasn't until DX 9 that it passed opengl in features - its taken Opengl how long to just actually catch up to DX? Nearly 10 years......

People are now cheering for MS and Khronos to do something they should of done 10 years ago? No I'm not cheering as I've heard this [redacted] all before and until they actually delivery *you know like AMD actually has* then its all lip service.

Great if they do....and I'm saying a big IF - until then enjoying Mantle....

Inappropriate language not allowed in VC&G
-Elfear

 

[SirPauly]

Well I can easily answer this. Competition is good, and reducing CPU bottlenecks and increasing draw calls is great.

But there's a right way and a wrong way to go about doing that. What we're seeing right now from Microsoft and the Khronos Group is the right way.

Mantle is the wrong way....imo.

imho,

Mantle offered choice now, improved gaming potential now, created more competition and awareness, may benefit the industry, move the industry forward with industry standards improving and maturing.

The question is not about right or wrong but was mantle worth the resources to spend for AMD? How much benefit will AMD receive over time?

 

[BFG10K]

As far as AMD's strategy... Who knows what it is exactly?

I can tell you what it isn't: spending millions on Mantle development with the intention of encouraging DX/OGL to make it even more irrelevant than it is now.

If their intention was to simply reduce CPU overhead to encourage Microsoft, they're now out of pocket for millions while their competitors benefit for free. You'd have to be an absolute moron to run a business like that.

They also said that they hoped others would adopt Mantle. While it's too early to tell exactly where this is going and what they are all up to, none of this contradicts that and AMD is well known for simply offering their work up for open standards.

Who do you think will adopt Mantle if these optimizations come to fruition?

Actually, benchmarks will all start looking like the current i7+290x mantle vs fx8350 + 290x mantle. The AMD CPUs will get much more boost. If most games will be GPU bottlenecked, then this whole exercise with DirectX reducing CPU rendering overhead will be pointless.

Unless you think Intel's CPU performance is the pinnacle and we need nothing more, I fail to see how this statement is relevant. If AMD gets a boost then so does Intel.

If Intel isn't getting a boost it means their CPUs are already fast enough to create GPU bottlenecks in that particular scenario. If that's the case, their older dual-core CPUs will see boosts like AMD's.

Everyone wants Direct X to be more granular and allow greater freedom to developers whilst still being hardware agnostic.

Then Mantle is already a failure right out of the gate given it'll never work on anything but certain AMD parts. That's not hardware agnostic.

 

[parvadomus]

imho,

Mantle offered choice now, improved gaming potential now, created more competition and awareness, may benefit the industry, move the industry forward with industry standards improving and maturing.

The question is not about right or wrong but was mantle worth the resources to spend for AMD? How much benefit will AMD receive over time?

I think it was a smart move, even if Mantle dies prematurely, something that I doubt.
If mantle dies, and DX and OGL gets to its level, then its a win for AMD processors, they will perform better for gamers and start being competitive again.
If mantle wins, its a plus for their Radeon line, just like physx is for Nvidia.

Offtopic: Now that I talk about physx, what would happen if you combine physx with mantle? Maybe you can even run the entire physics simulation over the CPU, as it gain a lot of headroom for additional processing with Mantle.

 

[Despoiler]

I'm sure this thread will eventually get locked, but like I and many others have been saying all a long, Microsoft has no intentions of surrendering their PC gaming monopoly (even though they've taken it for granted over the years) and will not allow Mantle to supersede DirectX.

Microsoft has more experience with this sort of thing than both AMD and NVidia combined.. I'm sure they can pull it off, while retaining their broad architectural compatibility.

DirectX & OpenGL catching up with Mantle, will offer low-level access to reduce draw overhead..

That article is terrible because it pulls stuff from 3 different GDC sessions and then reports them in sequence so you can't tell what the context is.

Approaching Zero Driver Overhead in OpenGL (Presented by NVIDIA) is the talk where AMD, Intel, and Nvidia are holding a joint session. (see link to session below). This session is specifically targeted at techniques programmers can use right now.
http://schedule.gdconf.com/session-id/828316

DirectX: Evolving Microsoft's Graphics Platform (Presented by Microsoft) is about the future of DX, but will announce a new set of tools to compete with AMD's Mantle tools.
http://schedule.gdconf.com/session-id/828184

DirectX: Direct3D Futures (Presented by Microsoft) is the talk about future DirectX.
http://schedule.gdconf.com/session-id/828181

It looks like AMD is pushing the entire industry forward. AMD stated before Mantle was released that they were working on getting Mantle like functionality folded into the OGL spec. No surprises there. MS is going to talk about what they are going to do ie haven't done yet. I suspect they will release better tools sooner than later if not immediately to tide developers over. DX12, or whatever version includes all of these changes, will force you to buy whatever their next OS version is. That is part of their OS business model. Add in the time OS adoption and for devs to switch to the new DX....that will be several years from now.

 

[Nintendesert]

yes i think they will improve DX 11 so win 7 can advantage.

Why?

MS uses DX as leverage to force upgrades into the latest OS. Maybe new management will change that business decision, but there's not a lot of incentive for MS to keep catering to people stuck on old OSes.

 

[tolis626]

Well,personally I believe that this was the whole point of Mantle.Not that AMD created it with that purpose,but that this was its only future.It was a wrong step in the right direction.We NEED better APIs,we just don't need hardware exclusivity.I'd take an improved version of DirectX over Mantle any day for obvious reasons (e.g. not everyone has or wants a Radeon),but I wholeheartedly support Mantle because,as it turns out,it leads to a better gaming industry.And that's what I suspect will be the case with G-Sync.I think it won't be too long before we see monitors with variable refresh rates a la G-Sync that will be available for all.Maybe AMD gets some sort of "patent money" with this,similar to what I expect NVidia would gain from G-Sync if others adopted similar technologies.

All in all,it's too early to be decisive about any of this.I think of the past decade (2000-2010) as a sort of dark age for gaming,if not for the PC industry as a whole.Yes,we have had many improvements and new stuff came out like crazy,but what was actually revolutionary?Games improved because hardware improved.Now that hardware improvements have slowed down,developers have to be actually creative to improve their stuff.And IMHO that's the way to go.

PS : We can't forget that another pressure point for Microsoft is SteamOS.They really need to step up their game if they want to keep one of their most important markets,which is gamers.

 

[wand3r3r]

I'm sure this thread will eventually get locked

I wonder why.

So suddenly a few are super interested in a similar alternative to do a similar thing to mantle? Yeah sure it's got the industry backing it so I can say it sounds good, but weren't some of you just explaining over and over and over how multithreading or whatever "should" solve the issues or be an alternative and trying to imply how bad mantle was etc.

After weeks of trying to throw mud on mantle, suddenly it sounds good under an alternative name? I wish you guys could at least uphold your standards across the board instead of only when your favorite company is involved.

/double standards, goalpost switching, brand allegiance

This sounds like AMD lit the fire under some companies rears and now it's getting results.

 

[Arkanius]

But will this require tailored architectures and future graphic cards?
Because Mantle works GCN which exists RIGHT NOW.

 

[cytg111]

Well I can easily answer this. Competition is good, and reducing CPU bottlenecks and increasing draw calls is great.

But there's a right way and a wrong way to go about doing that. What we're seeing right now from Microsoft and the Khronos Group is the right way.

Mantle is the wrong way....imo.

Competition is good! - But alas those who are bringing the competition is doing it wrong and those getting competed with is doing it right. hmmm... hmmm... naw still not getting it.

 

[cytg111]

I wonder why.

So suddenly a few are super interested in a similar alternative to do a similar thing to mantle? Yeah sure it's got the industry backing it so I can say it sounds good, but weren't some of you just explaining over and over and over how multithreading or whatever "should" solve the issues or be an alternative and trying to imply how bad mantle was etc.

After weeks of trying to throw mud on mantle, suddenly it sounds good under an alternative name? I wish you guys could at least uphold your standards across the board instead of only when your favorite company is involved.

/double standards, goalpost switching, brand allegiance

This sounds like AMD lit the fire under some companies rears and now it's getting results.

Yea, sounds like someone is actually arguing with themselves and not realizing it. Whatever, lock this beep down. Please.

 

[cytg111]

Why?

MS uses DX as leverage to force upgrades into the latest OS. Maybe new management will change that business decision, but there's not a lot of incentive for MS to keep catering to people stuck on old OSes.

Indeed, yet another good reason why Directx/Khronos is "the right way". (apply irony in moderate dose)

 

[OCGuy]

Yea, sounds like someone is actually arguing with themselves and not realizing it. Whatever, lock this beep down. Please.

 

[PPB]

I dont know what those 2 companies are smoking, according to our beloved folks at AT, MT scaling on DX 11 is great, command lists work like a charm and who needs more than 5K draw calls?


(apply irony in more than moderate dose)

 

[sushiwarrior]

Well, looks like the consumers win in this case. Maybe AMD will lose money and Mantle will die off prematurely, but I'm just glad that it means people who own Nvidia or AMD get better performance and better games. Good for the industry!