AMD @ GDC: Partnership with MS next-generation graphics.

Page 9 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

ASM-coder

Member
Jan 12, 2014
193
0
0
Mantle doesn't require GCN, just the feature set that GCN supports.
Ok, so we're arguing semantics. Mantle doesn't need GCN, but GCN has what mantle needs. Still, mantle won't work on current Nvidia cards.
How does DX12 get "closer to the metal" on any and all cards?
 

Noctifer616

Senior member
Nov 5, 2013
380
0
76
Ok, so we're arguing semantics. Mantle doesn't need GCN, but GCN has what mantle needs. Still, mantle won't work on current Nvidia cards.

According to AMD people, Mantle can actually work on the hardware of other vendors (Intel and NVidia) and they would like them to add support for it.
 

f1sherman

Platinum Member
Apr 5, 2011
2,243
1
0
So I just woke uo and I might be groggy from sleep but I seriously thought I was reading a Mantle presentation when reading the PCPer livestream. Those looked exactly like AMD slides, same font even.

And DX12... it's Mantle. The stated goals, the way its features are worded... Microsoft could have used Mantle slides from four months ago and nobody would have noticed.

Now, I'm not stupid, and won't imply Microsoft adopted Mantle or whatever.

But I will say that AMD's development of Mantle and EA, Crytek's and everyone else adoption of Mantle makes A LOT more sense.

well yes... credit where credit is due
I mean it's pretty clear that DX12 (announcement) was inspired by Mantle.
And while it's true that AMD started and inspired this recent movement, its also clear that AMD does not own license to "efficient programming"

There is only so much ways you can do or say low overhead.
Claiming that anyone aiming for low overhead is really using Mantle - that's bizarre.

So until DX12 is out, I'll enjoy my Mantle games very very much . That flower shooter game next please
 

ASM-coder

Member
Jan 12, 2014
193
0
0
According to AMD people, Mantle can actually work on the hardware of other vendors (Intel and NVidia) and they would like them to add support for it.
Right, and I understand that. AMD has made it clear that mantle is not proprietary. But it's not magic. NVidia would need to make changes going forward to add this lower level support. Microsoft seems to be offering a lower level API with no changes to the GPU. That doesn't quite make sense.
 

AnandThenMan

Diamond Member
Nov 11, 2004
3,949
504
126
Microsoft seems to be offering a lower level API with no changes to the GPU. That doesn't quite make sense.
Let's assume that DX12 does offer the same efficiency gains as Mantle but on a much broader range of hardware. Highly suspect yes, but go with it. That would mean Microsoft is basically admitting that currently D3D flat out sucks.
 

Noctifer616

Senior member
Nov 5, 2013
380
0
76
Right, and I understand that. AMD has made it clear that mantle is not proprietary. But it's not magic. NVidia would need to make changes going forward to add this lower level support. Microsoft seems to be offering a lower level API with no changes to the GPU. That doesn't quite make sense.

https://www.youtube.com/watch?v=tDPgJB2x7dQ

2 minute mark.

There is an abstraction layer (just like DX has it right now) that allows Mantle to work on more than one graphics architecture (it's just not as thick as it is in current DX).

No one has said that their competitors would have to make changes to their architecture. They only mentioned the need for a certain feature set to be supported by the architecture for Mantle to work.

That could mean that Mantle could work on Kepler and Fermi, the same way DX12 will work on them (and whatever the Intel graphics architecture is named).

In other words, both DX11 and DX12 have an abstraction layer that make them work on different GPU architectures, however, the one in DX12 is a lot thinner than the one in DX11, making it closer to the metal, but not as close as the API in the PS4 for example (which is only designed for the PS4 specific hardware).
 

ASM-coder

Member
Jan 12, 2014
193
0
0
So until DX12 is out, I'll enjoy my Mantle games very very much . That flower shooter game next please
Yes, funny how this works. Since I bought GCN card, I find myself watching and waiting for mantle supported games. I have BF4 and Thief, and will be watching for Sniper Elite III and any new Cryengine games(that makes use of Mantle).
 

ASM-coder

Member
Jan 12, 2014
193
0
0
Let's assume that DX12 does offer the same efficiency gains as Mantle but on a much broader range of hardware. Highly suspect yes, but go with it. That would mean Microsoft is basically admitting that currently D3D flat out sucks.
And that they could have made it much better long before now.
 

Gloomy

Golden Member
Oct 12, 2010
1,469
21
81
I've played PvZ:Garden Warfare.

It's a good game on its own right. Surprisingly good. I would have picked it up even if it didn't have Mantle. And EA is handling DLC on it surprisingly well (free + cosmetic microtransactions).

That's neither here nor there though.
 

ASM-coder

Member
Jan 12, 2014
193
0
0
That could mean that Mantle could work on Kepler and Fermi, the same way DX12 will work on them (and whatever the Intel graphics architecture is named).
Let me ask it this way.
Do you think mantle could ever work on NVidia cards bought in 2013?
Do you think DX12 will work on NVidia cards bought in 2013?
 

Despoiler

Golden Member
Nov 10, 2007
1,966
770
136
Lol.
That nVidia and Microsoft have been working since last year on a functional driver and enviroment - before AMD announced Mantle - is still ignored? D:

That DX12 supports goes back to hardware from 2010 instead of 2012? That it will be supported by anyone from Intel over nVidia to "ARM"?

DX12 is a huge step forward. And it took time to bring it into a shape which is usable.

Check this out, AMD announced Mantle at the end of September last year, but had been working on it for 2-3 years prior. What were you trying to imply again... They were actually working on it too. Not just talking about their concerns with DX driver overhead. No doubt that Nvidia's 2 year development time for DX 11 MT driver spawned that discussion.

DX12 is a huge step forward....to catching up to where Mantle already is.

Also, I don't know about all of you, but I'd rather take Mantle's 1 man, two months of work instead of 4 months of work within the same API umbrella.

According to Turn 10, the conversion from Xbox One's DX11.x API to an alpha version of DX12 took four man-months to achieve

http://www.eurogamer.net/articles/digitalfoundry-2014-directx-12-revealed-coming-to-xbox-one

MS and Nvidia's announcement smacks of trying to save face that AMD beat them to the punch and did so convincingly early. AMD is laughing their arses off right now because they get to have their cake now and also eat it when DX12 does exactly what they need it to do. I find it funny that team Winvidia are claiming that it will take 6 years to develop an API with their combined resources. That is just sad when broke AMD can do it in 2-3.
 
Last edited:

Noctifer616

Senior member
Nov 5, 2013
380
0
76
I don't believe this is true.

How exactly would AMD make a Mantle driver for NVidia cards without their help?

If Mantle actually is close to the hardware, that would mean it would have some architecture specific commands, would it not? If so, how could they make a driver if they don't have the architecture specifications from NVidia?

It's like saying that Sony and MS can develop their console API's without AMD's help or any in depth knowledge of the GCN architecture.
 

Gloomy

Golden Member
Oct 12, 2010
1,469
21
81
How exactly would AMD make a Mantle driver for NVidia cards without their help?

If Mantle actually is close to the hardware, that would mean it would have some architecture specific commands, would it not? If so, how could they make a driver if they don't have the architecture specifications from NVidia?

It's like saying that Sony and MS can develop their console API's without AMD's help or any in depth knowledge of the GCN architecture.

I think he meant that Mantle uses some GCN things which can't be easily translated to Kepler or whatever
 

ASM-coder

Member
Jan 12, 2014
193
0
0
I think he meant that Mantle uses some GCN things which can't be easily translated to Kepler or whatever
Correct. I don't believe mantle could ever work on current NVidia cards.
Same for current Intel cards. I thought that was the general consensus.
 

Noctifer616

Senior member
Nov 5, 2013
380
0
76
Correct. I don't believe mantle could ever work on current NVidia cards.
Same for current Intel cards. I thought that was the general consensus.

As I said, official word is that they want Mantle to work on competitor hardware, but there was no mention of change in architecture for it to work.

But ye, considering DX12 is MS version of Mantle, I guess we will never know since there is no need for Intel and NVidia to adopt Mantle now.
 

Despoiler

Golden Member
Nov 10, 2007
1,966
770
136
Mantle's HAL already works on Nvidia hardware at a basic level according to Dan Baker. Don't ask me to source it. It's buried in one of the many interviews he did at AMD GPU14. I haven't been able to find it again.
 

ASM-coder

Member
Jan 12, 2014
193
0
0
I found this statement posted by someone. Not sure of it's veracity, but perhaps...

"Mantle is providing a virtual GPU that is a direct 1:1 mapping to hardware functions. It might not be quite as fast, but it should be pretty close because it wouldn't need make any more mode switches than it would for direct hardware access."

Caveat... "virtual"
 

Carfax83

Diamond Member
Nov 1, 2010
6,841
1,536
136

OCGuy

Lifer
Jul 12, 2000
27,227
36
91
http://cdn4.wccftech.com/wp-content/uploads/2013/11/Untitled11.jpg

Slide from the DICE Mantle presentation from the AMD developer summit.

Stop repeating this stuff.


You’ve got to love PR marketing. Earlier last week, AMD revealed Mantle. As the red team hinted during its AMD event, Mantle would be compatible with AMD’s GPUs. Despite some websites claiming that this API will be open to other graphics manufacturers, it was recently revealed that Mantle will require cards based on AMD’s GCN architecture to work.

This was confirmed by both DICE’s Johan Andersson and AMD’s Chief Software Raja Koduri. Not only that, but as PCGamesHardware reported, AMD does not consider Mantle an open standard like OpenCL or OpenGL

http://www.dsogaming.com/news/mantl...k-not-an-open-standard-like-opencl-or-opengl/

It's a nice sentiment, but does that mean AMD is willing to allow an entity traditionally viewed from behind enemy lines make use of Mantle?

"It's hard to say," Hallock said. "If we want it to be an industry-wide API or inspire an industry-wide API, that would mean adoption from Nvidia in some way, shape or form. I can't speak from an architectural level what that would require of them to change."

"But for the good of gamers, [we] would want one ultimate specification that is either Mantle itself or one similar to it. As Highlander said, 'There can only be one."

http://www.techradar.com/news/compu...g-api-to-become-the-industry-standard-1218560
 
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |