The AMD Mantle Thread

Page 79 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.
Status
Not open for further replies.

SiliconWars

Platinum Member
Dec 29, 2012
2,346
0
0
I didn't see it, could you link me to it?

Edit: I see a tweet, saying "in some cases".
What engine are they using? Unreal? CryEngine? Frostbyte? Could it be their own engine, and whay are they comparing? Maybe the state of of and old unoptimized DX path compared to the Mantle path they are working on with AMD?

Anybody saying 3x faster is either unqualified, paid off, or flat out lying.

Or you know, maybe they actually have the demo proving it?



https://twitter.com/repi/status/400803254147485696/photo/1

Oxide's presentation & Mantle demo at #APU13 is awesome, 100k draw calls in their space test game. Great work guys!
http://www.hardware.fr/news/13450/apu13-oxide-fait-exploser-limite-cpu-avec-mantle.html

Clearly they mean Mantle vs D3D (funny how you could believe in an "old and unoptimized dx path" but didn't consider a brand new alpha Mantle path would be substandard. )

The actual demo was shown yesterday to the press. Ryan Shrout has been saying a lot about it.
 
Last edited:
Feb 19, 2009
10,457
10
76
Sorry if this is old news and was already posted, but I found it interesting:

http://www.gamesindustry.biz/articl...hooter-mold-how-oxide-plans-to-revive-the-rts

Thats a great article. I have played many Stardock games in the past, their massive space battles ALWAYS lagged the crap out of my system even when I ran FPS flawlessly. When there are thousands of units on screen and small fighters/bombers flying about, all the AI calls and pathfind seems to run into an artificial choke point. It was a steep fall-off in performance. This same problem occurs in pretty much all strategy games, even Civ 5, Shogun 2 and Rome TW2.

""You'll see people misrepresenting that AMD's pushing this technology, but the reality is that a lot of people - including myself and other graphics architects - have been asking for this type of thing for a long time," said Baker."
 

SiliconWars

Platinum Member
Dec 29, 2012
2,346
0
0
Of course they do. It could also be Mantle against a two year old unoptimized D3D build.

Believe what you want, my sig will be safe.

Yes your sig will be safe regardless. If I'm right you just have to say it was a supporting comment.

When I said "Sadly for Nvidia, SLI'd Titan's still won't be able to match a single 290X in BF4", I left plenty of wiggle room.

At the current outlook, no Nvidia card will be able to match the 290X's image quality. Period. Make it Quad-SLI if you want, the Nvidia cards just won't be capable of the same kind of rendering. Ergo, "SLI'd Titan's still won't be able to match a single 290X in BF4"

The likelihood of seeing an apples-to-apples comparison is extremely small and always was. My comment was always safe, the only difference is you fell for it by assuming the lowest common denominator (performance regardless of settings).
 
Last edited:

SiliconWars

Platinum Member
Dec 29, 2012
2,346
0
0
Sorry if this is old news and was already posted, but I found it interesting:

http://www.gamesindustry.biz/articl...hooter-mold-how-oxide-plans-to-revive-the-rts

I had read some of that before but some of it was new as well. Thanks for the link.

It seems completely apparent to me that Mantle is a godsend to RTS/Strategy games. Possibly MMO's as well. The problem I have here is that the gap between Mantle and DX is so huge that I can't envisage it ever being bridged.

This is where the real battle will be fought. The difference between Mantle strategy games and DX strategy games is going to be massive. There's a real good reason why Star Citizen has gone Mantle too.
 

chimaxi83

Diamond Member
May 18, 2003
5,457
63
101
Yes your sig will be safe regardless. If I'm right you just have to say it was a supporting comment.

When I said "Sadly for Nvidia, SLI'd Titan's still won't be able to match a single 290X in BF4", I left plenty of wiggle room.

At the current outlook, no Nvidia card will be able to match the 290X's image quality. Period. Make it Quad-SLI if you want, the Nvidia cards just won't be capable of the same kind of rendering. Ergo, "SLI'd Titan's still won't be able to match a single 290X in BF4"

The likelihood of seeing an apples-to-apples comparison is extremely small and always was. My comment was always safe, the only difference is you fell for it by assuming the lowest common denominator (performance regardless of settings).

What exactly do you mean by image quality?
 

SiliconWars

Platinum Member
Dec 29, 2012
2,346
0
0
What exactly do you mean by image quality?

It's difficult to envisage how DICE will improve what is still basically just an FPS. However, I believe that the only limit they have is their imagination.

I think we're looking at total maximum settings (including max MSAA), never dropping below 60 fps. On top of that there will be additional effects opened up because of Mantle. Compute shader lighting will be standard even on midrange GCN cards.

Multiplayer could be spectacular. If AMD has any sense at all then they'll understand this and have special maps set aside for 128 players or more. When the CPU limit is removed, all this stuff that has been holding gaming back goes out the window.

That's just my belief of how it'll be. No matter how good the Nvidia cards are they just can't get over the limitations of DX.
 

f1sherman

Platinum Member
Apr 5, 2011
2,243
1
0
Yes your sig will be safe regardless. If I'm right you just have to say it was a supporting comment.

When I said "Sadly for Nvidia, SLI'd Titan's still won't be able to match a single 290X in BF4", I left plenty of wiggle room.

Well it's still a good sig, regardless how much you wiggle
Almost as good as that iPad sig...

At the current outlook, no Nvidia card will be able to match the 290X's image quality. Period. Make it Quad-SLI if you want, the Nvidia cards just won't be capable of the same kind of rendering. Ergo, "SLI'd Titan's still won't be able to match a single 290X in BF4"


RTS/strategy games and multiplier games are definitely CPU bound.
Also being 0% CPU bound is a guarantee of far better and more consistent gaming experience.
Being CPU bound is $#*&

Anyone noticed the shift in Mantle talk, which btw I predicted earlier
After repi's presentation yesterday, speculations and discussions are not so much about GPU anymore, but CPU.

+5% GPU market would mean jack for AMD; +5% CPU/APU - now we're talking
 
Feb 19, 2009
10,457
10
76
+5% GPU market would mean jack for AMD; +5% CPU/APU - now we're talking

Absolutely not true. The GPU division is generating the vast bulk of the profit for AMD. The fact they count APU sales as CPU further shows how important the "GPU" is since its using tech from the GPU R&D. In essence, their GPU division is subsidizing the CPU division.. and their CPU div still cannot be profitable. That shows how horrible it truly is.

There are many slides in the presentation that clearly show the advantages for the GPU side of things, except some of you choose to ignore it. In DICE's presentation there's an entire half of the presentation on how GPU rendering is improved on Mantle. No direct performance figures yet though. That, we still have to wait and see.
 

f1sherman

Platinum Member
Apr 5, 2011
2,243
1
0
OK, I'll let this one slide, and won't be pulling numbers and sheets (its Mantle thread after all)

I watched repi yesterday with great interest, and I'm not denying GPU side of things at all.
Situation is intertwined between the two enough as its.
Just I thought that talk has shifted to CPU... well I could be wrong
 
Last edited:

smackababy

Lifer
Oct 30, 2008
27,024
79
86
There are many slides in the presentation that clearly show the advantages for the GPU side of things, except some of you choose to ignore it. In DICE's presentation there's an entire half of the presentation on how GPU rendering is improved on Mantle. No direct performance figures yet though. That, we still have to wait and see.

Which is why nobody with a brain acknowledges the marketing slides. Yes, the idea behind Mantle (removing a lot of abstraction from the GPU) can lead to great performance. It shouldn't be that hard to make a tech demo that is shows improvements Mantle brings.

In Dec, we will get a taste of what one developer can do with the limited API AMD has. Eventually, we'll know whether Mantle gives any significant improvements.

The problem is, a lot of us remember when MS "abandoned" DOS gaming and added an abstraction layer from the hardware in Windows. Game developers were outraged and thought it would cripple performance. Did it? Not really. If anything, it made gaming so much better. With DX, MS handled all the hardware aspects. You didn't have to make sure your specific hardware was supported.


I will concede removing a lot off the CPU will benefit certain, and maybe all, games that do a lot of CPU intensive work.
 

beginner99

Diamond Member
Jun 2, 2009
5,314
1,756
136
I didn't see it, could you link me to it?

Edit: I see a tweet, saying "in some cases".

Anybody saying 3x faster is either unqualified, paid off, or flat out lying.

It's with their own engine (which is for RTS games) and for a special case were there are a lot! of "units" on the field or said otherwise a ridiculous amount of draw calls. Here it's 3x faster.

Anyone ever having played starcraft 1 and 2 knows that with many issues the at the time most powerful CPU weren't good enough. I think for starcraft 1 it took a PIII to make it playable in 4vs4 with everyone maxed out.

Meaning it's for em understandable that if you reduce this main bottleneck that you can see enormous improvements. However for the average game, say BF4, this will IMHO not be the case. I can see a 20% improvement. Maybe you get better improvements on bad hardware but going from 10 to 20 FPS still doesn't make the game playable.
 

GaiaHunter

Diamond Member
Jul 13, 2008
3,684
338
126
People are focusing on CPU improvements because draw calls is the easy part to understand - "look 5000 calls ->100000 calls".

Way bigger number must be way better.

Stuff like queue management leading to Async DMA transfers, Async compute with graphics, etc - "scratch head".
 

krumme

Diamond Member
Oct 9, 2009
5,956
1,595
136
It's with their own engine (which is for RTS games) and for a special case were there are a lot! of "units" on the field or said otherwise a ridiculous amount of draw calls. Here it's 3x faster.

Anyone ever having played starcraft 1 and 2 knows that with many issues the at the time most powerful CPU weren't good enough. I think for starcraft 1 it took a PIII to make it playable in 4vs4 with everyone maxed out.

Meaning it's for em understandable that if you reduce this main bottleneck that you can see enormous improvements. However for the average game, say BF4, this will IMHO not be the case. I can see a 20% improvement. Maybe you get better improvements on bad hardware but going from 10 to 20 FPS still doesn't make the game playable.

If Kaveri can play BF4 at 900 or 1080 at low or medium with mantle driver at about 35-40fps its a huge step forward imho, and opens a huge future market for selling to kaveri machines on notebooks or desktops. We know from the kaveri demo its within range.

Mantle might just be what an apu like kaveri needs to be a cheap mans gaming machine. (probably we will se a lot of 768 15 inch - lol)
 
Last edited:

OCGuy

Lifer
Jul 12, 2000
27,224
37
91
targeting end of December now for mantle on BF4? those new slides do not sound as confident as the Hawaii presentation
 

Carfax83

Diamond Member
Nov 1, 2010
6,841
1,536
136
AMD needs to stop being coy about Mantle and come clean with their plans (if they have any) to open it up to other IHVs and ISVs..

Mantle will not survive for long unless NVidia, Intel, Microsoft etcetera jump in.. Microsoft definitely will be against Mantle due to them wanting to be the sole ISV for PC gaming, which means DirectX exclusivity.

In fact, Microsoft is already in the process of porting the Xbox One's low level API to Direct3D in Windows.

What's going to Mantle happen when DX12 or whatever has similar low overhead capabilities? You think developers are still going to go with Mantle?
 

smackababy

Lifer
Oct 30, 2008
27,024
79
86
AMD needs to stop being coy about Mantle and come clean with their plans (if they have any) to open it up to other IHVs and ISVs..

Mantle will not survive for long unless NVidia, Intel, Microsoft etcetera jump in.. Microsoft definitely will be against Mantle due to them wanting to be the sole ISV for PC gaming, which means DirectX exclusivity.

In fact, Microsoft is already in the process of porting the Xbox One's low level API to Direct3D in Windows.

What's going to Mantle happen when DX12 or whatever has similar low overhead capabilities? You think developers are still going to go with Mantle?

I stated when AMD first showed their marketing slides about Mantle, this could put a fire under MS' ass and they could actually have to stop coasting with DX.
 

gorobei

Diamond Member
Jan 7, 2007
3,930
1,411
136
AMD needs to stop being coy about Mantle and come clean with their plans (if they have any) to open it up to other IHVs and ISVs..

Mantle will not survive for long unless NVidia, Intel, Microsoft etcetera jump in.. Microsoft definitely will be against Mantle due to them wanting to be the sole ISV for PC gaming, which means DirectX exclusivity.

In fact, Microsoft is already in the process of porting the Xbox One's low level API to Direct3D in Windows.

What's going to Mantle happen when DX12 or whatever has similar low overhead capabilities? You think developers are still going to go with Mantle?

did you actually read the summary or watch the videos?

the bulk of the new features are for win8.1 mobile apps. the only desktop game relevant stuff is tiled resources(which is just the ms official version of rage mega texture or amd's Partial Resident Texture). the latency reduction stuff is more for touch interfaces.

the only really significant thing he glosses over at the start is the core improvement to resource api in loading assets. no mention of draw call improvement.

the new dx stuff is nowhere near what mantle is providing on cpu or gpu performance increase. its mostly dev support.
 

Imouto

Golden Member
Jul 6, 2011
1,241
2
81
Microsoft is being attacked from every single angle and such a gigantic company can't defend itself from everyone. Recently they've been failing at everything and I don't think they can recover from the combined blow of an underpowered console, a gamer oriented OS, the interest of every single player on dethroning their API, the epic failure of GFWL and the collateral damage of the AMD vs Nvidia war on their gaming segment.
 

krumme

Diamond Member
Oct 9, 2009
5,956
1,595
136
targeting end of December now for mantle on BF4? those new slides do not sound as confident as the Hawaii presentation

I agree it looks like it slipped 2 weeks - not the greatest delay seen on a new api in action imho.
Btw I wouldnt call bf4 ready now as it is and perhaps there is a ressource issue here as the ps4 bf4 needs to roll to. Perhaps it will even take more time to tune the mantle path after end dec. Bf4 was released a month to early imho but ttm is often beating all good sense. It all seems rushed from Dice imho amd needs more maturity.
 
Status
Not open for further replies.
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/    |