• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

The AMD Mantle Thread

Page 85 - 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 said:
Games are GPU and CPU bound at various stages. Mantle will remove the CPU limitation in nearly all cases. Obviously the bigger gains are with CPU bound scenarios, but the latest slides show that the gains are still large in GPU bound scenarios as well.

20% is low-balling, and this doesn't factor in that the IQ will also be improved. Very few devs are going to use Mantle simply for fps improvements, most will be more interested in adding IQ. BF4 on Mantle could end up with double the draw distance and still be 30% faster. However you look at it, it's really bad news for Nvidia.
Click to expand...

THIS People are forgetting/overlooking/ignoring that Mantle is a new feature set. Not just a more efficient render path.

Mark my words, whatever settings Mantle gives the biggest improvements with will be the least important with the anti Mantle crowd.
 
desprado said:
If u read more carefully he said that
so we're probably looking at something closer to 20 percent
but still it will hurt Nvidia until they figure out something

But that performance will not hurt a MS a bit or nether DX and it will only hurt Nvidia
Click to expand...

Actual quote from article - "Well AMD claims 20 to 50 percent, which sounds very impressive indeed, if not too optimistic - so we're probably looking at something closer to 20 percent."

"so we're probably looking at something closer to 20 percent" = pulled straight from his uninformed a$$.
 
SiliconWars said:
Games are GPU and CPU bound at various stages. Mantle will remove the CPU limitation in nearly all cases. Obviously the bigger gains are with CPU bound scenarios, but the latest slides show that the gains are still large in GPU bound scenarios as well.

20% is low-balling, and this doesn't factor in that the IQ will also be improved. Very few devs are going to use Mantle simply for fps improvements, most will be more interested in adding IQ. BF4 on Mantle could end up with double the draw distance and still be 30% faster. However you look at it, it's really bad news for Nvidia.
Click to expand...

50% might be lowballing it on Kaveri playing say: (slide 37)

Plants and Zombies:Garden Warfare.

- Very different rendering compared to BF4.☺
- Frostbite Mantle renderer will work out of the box.
- Focus on APU performance.

Looking forward to seeing Kaveri's numbers on this game.
 
Last edited:
DICE's APU13 Presentation slide deck bullet points.

1. MANTLE FOR DEVELOPERS JOHAN ANDERSSON – TECHNICAL DIRECTOR FROSTBITE ELECTRONIC ARTS

2. Mantle? Simplify advanced development  Improve performance  Enable developers to innovate  Challenge the status quo

3. Developer impact areas Control CPU performance Programmability GPU performance Platforms

4. Control New model Traditional Model: Black Box Explicit Model: Mantle  Middle-ground abstraction – compromise between performance & “usability”  Thin low-level abstraction to expose how hardware works  Hidden resource memory & state  App explicit memory management  Resource CPU access tied to device context  Resources are globally accessible  Driver analyzes & synchronizes implicitly  App explicit resource state transitions

5. Control App responsibility  Tell when render target will be used as a texture ‒ And many more resource state transitions  Don’t destroy resources that GPU is using ‒ Keep track with fences or frames  Manual dynamic resource renaming ‒ No DISCARD for driver resource renaming  Resource memory tiling  Powerful validation layer will help!

6. Control Explicit control enables  App high-level decisions & optimizations ‒ Has full scene information ‒ Easier to optimize performance & memory  Flexible & efficient memory management ‒ Linear frame allocators ‒ Memory pools ‒ Pinned memory  Reduced development time ‒ For advanced game engines & apps ‒ Easier to get to target performance & robustness

7. Control Explicit control enables  Transient resources ‒ Alias render targets within frame ‒ Major memory savings ‒ No need to pre-allocate everything  Light-weight driver ‒ Easier to develop & maintain ‒ Reduced CPU draw call overhead

8. CPU performance

9. CPU perf Core concepts  Descriptor sets  Monolithic pipelines  Command buffers

10. CPU perf Descriptor sets  Table with resource references to bind to graphics or compute pipeline Image Memory Sampler Link  Replaces traditional resource stage binding ‒ Major performance & flexibility advantage ‒ Closer to how the hardware works  Example 1: Single simple dynamic descriptor set ‒ Bind everything you need for a single draw call ‒ Close to DX/GL model but share between stages Dynamic descriptor set VertexBuffer (VS) Texture0 (VS+PS) Constants (VS) Texture1 (PS)  App managed - lots of strategies possible! ‒ Tiny vs huge sets ‒ Single vs multiple ‒ Static vs semi-static vs dynamic Texture2 (PS) Sampler0 (VS+PS)

11. CPU perf Descriptor sets  Table with resource references to bind to graphics or compute pipeline Image  Example 2: Reuse static set with nesting ‒ Reduce update time & memory usage Memory Static descriptor set Sampler Link Dynamic descriptor set  Replaces traditional resource stage binding ‒ Major performance & flexibility advantage ‒ Closer to how the hardware works Constants (VS) Link VertexBuffer (VS) Texture0 (VS+PS) Texture1 (PS) Texture2 (PS) Texture3 (PS)  App managed - lots of strategies possible! ‒ Tiny vs huge sets ‒ Single vs multiple ‒ Static vs semi-static vs dynamic Texture4 (PS) Sampler0 (VS+PS) Sampler1 (PS)

12. CPU perf Monolithic pipelines  Shader stages & select graphics state combined into single object ‒ No runtime compilation or patching needed! ‒ Significantly less runtime overhead to use Pipeline state  Supports parallel building & caching ‒ Fast loading times  Usage & management up to the app ‒ Static vs dynamic creation ‒ Amount of pipelines ‒ State usage IA DB VS HS DS Tessellator GS RS PS CB
1
3. CPU perf Command buffers  Issue pipelined graphics & compute commands into a command buffer ‒ Bind graphics state, descriptor sets, pipeline ‒ Draw calls ‒ Render targets ‒ Clears ‒ Memory transfers ‒ NOT: resource mapping  Fully independent objects ‒ Create multiple every frame ‒ Or pre-build up front and reuse

14. CPU perf DX/GL parallelism CPU 0 CPU 1 CPU 2 Game Game Game Render Render Driver Render  Automatically extracts parallelism out of most apps   Doesn’t scale beyond 2-3 cores   Additional latency   Driver thread often bottleneck – can collide app threads  Render

15. CPU perf Parallel dispatch with Mantle CPU 0 Game Game Game CPU 1 Render Render Render CPU 2 Render Render Render CPU 3 Render Render Render CPU 4 Render Render Render  App can go fully wide with its rendering – minimal latency   Close to linear scaling with CPU cores   No driver threads – no overhead – no contention   Frostbite’s approach on all consoles – and on PC with Mantle! 

16. GPU performance

17. GPU perf GPU optimizations  Thanks to improved CPU performance – CPU will rarely be a bottleneck for the GPU ‒ CPU could help GPU more: ‒ Less brute force rendering ‒ Improve culling  Resource states ‒ Gives driver a lot more knowledge & flexibility ‒ Apps can avoid expensive/redundant transitions, such as surface decompression  Expose existing GPU functionality  Shader pipeline object – driver optimizations ‒ Can optimize with pipeline state knowledge ‒ Can optimize across all shader stages ‒ Quad & Rect-lists ‒ HW-specific MSAA & depth data access ‒ Programmable sample patterns ‒ And more..
1
8. GPU perf Queues  Modern GPUs are heterogeneous machines with multiple engines Graphics ‒ Graphics pipeline ‒ Compute pipeline(s) ‒ DMA transfer ‒ Video encode/decode ‒ More…  Mantle exposes queues for the engines + synchronization primitives Compute DMA ... Queues GPU

19. GPU perf Queues Graphics Compute DMA ... Queues GPU

20. GPU perf Queue use cases  Async DMA transfers ‒ Copy resources in parallel with graphics or compute Copy DMA Graphics Render Other render Use copy

21. GPU perf Queue use cases  Async DMA transfers ‒ Copy resources in parallel with graphics or compute  Async compute together with graphics ‒ ALU heavy compute work at the same time as memory/ROP bound work to utilize idle units Compute Graphics GBuffer Non-shadowed lighting Shadowmap 0 Shadowmap 1 Final lighting

22. GPU perf Queue use cases  Async DMA transfers  Multiple compute kernels collaborating ‒ Copy resources in parallel with graphics or compute ‒ Can be faster than über-kernel ‒ Example: Compute geometry backend & compute rasterizer  Async compute together with graphics ‒ ALU heavy compute work at the same time as memory/ROP bound work to utilize idle units Compute 0 Compute 1 Graphics Compute Geometry Compute Rasterizer Ordinary Rendering

23. GPU perf Queue use cases  Async DMA transfers  Multiple compute kernels collaborating ‒ Copy resources in parallel with graphics or compute ‒ Can be faster than über-kernel ‒ Example: Compute geometry backend & compute rasterizer  Async compute together with graphics ‒ ALU heavy compute work at the same time as memory/ROP bound work to utilize idle units Compute Graphics Process0 Process1 Draw0  Compute as frontend for graphics pipeline ‒ Compute runs asynchronously ahead and prepares& optimizes geometry for graphics pipeline Process0 Draw1 Draw2

24. GPU perf Queue use cases  Async DMA transfers  Multiple compute kernels collaborating ‒ Copy resources in parallel with graphics or compute ‒ Can be faster than über-kernel ‒ Example: Compute geometry backend & compute rasterizer  Async compute together with graphics ‒ ALU heavy compute work at the same time as memory/ROP bound work to utilize idle units  Compute as frontend for graphics pipeline ‒ Compute runs asynchronously ahead and prepares& optimizes geometry for graphics pipeline  Game engines will build large GPU job graphs ‒ Move away from single sequential submission ‒ Just as we already have done on CPU

25. Programmability

26. Programmability Explicit Multi-GPU  Explicit control of GPU queues and synchronization, finally! ‒ Implement your own Alternate-Frame-Rendering ‒ Or something more exotic..  Use case: Workstation rendering with 4-8 GPUs ‒ Super high-quality rendering & simulation ‒ Load balance graphics & compute job graphs across GPUs ‒ 20-40 TFlops in a single machine!  Use case: Low-latency rendering ‒ Important for VR and competitive games ‒ Latency optimized GPU job graph scheduling ‒ VR: Simultaneously drive 2 GPUs (1 per eye)

27. Programmability New mechanisms  Command buffer predication & flow control ‒ GPU affecting/skipping submitted commands ‒ Go beyond DrawIndirect / DispatchIndirect ‒ Advanced variable workloads ‒ Advanced culling optimizations  Write occlusion query results into GPU buffer ‒ No CPU roundtrip needed ‒ Can drive predicated rendering ‒ Or use results directly in shaders (lens flares)
2
8. Programmability Bindless resources  Mantle supports bindless resources ‒ Shaders can select resources to use instead of static binding from CPU ‒ Extension of the descriptor set support  Examples ‒ Performance optimizations – less data to update ‒ Logic & data structures that live fully on the GPU ‒ Scene culling & rendering ‒ Material representations  Key component that will open up a lot of opportunities! ‒ Deferred shading ‒ Raytracing

29. Platforms

30. Platforms Today  Mantle gives us strong benefits on Windows today ‒ Console-like performance & programmability on both Windows 7 and Windows 8 ‒ For us, well worth the dev time!  DX & GL are the industry standards ‒ Needed for platforms that do not support Mantle ‒ Needed by devs who do not want/need more control ‒ Have to have fallback paths for GL/DX, but not limit oneself to it  Mantle and PlayStation 4 will drive our future Frostbite designs & optimizations ‒ PS4 graphics API has great programmability & performance as well ‒ Share concepts, methods & optimization strategies

31. Platforms Linux & Mac  Want to see Mantle on Linux and Mac! ‒ Would enable support for our full engine & rendering ‒ Significantly easier to do efficient renderer with Mantle than with OpenGL  Use cases: ‒ Workstations ‒ R&D ‒ Not limited by WDDM ‒ Games ‒ Mantle + SteamOS = powerful combination!

32. Platforms Mobile  Mobile architectures are getting closer in capabilities to desktop GPUs  Want graphics API that allows apps to fully utilize the hardware ‒ Power efficient ‒ High performance ‒ Programmable  Major opportunity with Mantle – leap frog GL4, DX11 ‒ For mobile SoC vendors ‒ For Google and Apple

33. Platforms Multi-vendor?  Mantle is designed to be a thin hardware abstraction ‒ Not tied to AMD’s GCN architecture ‒ Forward compatible ‒ Extensions for architecture- and platform-specific functionality  Mantle would be a much more efficient graphics API for other vendors as well ‒ Most Mantle functionality can be supported on today’s modern GPUs  Want to see future version of Mantle supported on all platforms and on all modern GPUs! ‒ Become an active industry standard with IHVs and ISVs collaborating ‒ Enable us developers to innovate with great performance & programmability everywhere

34. Frostbite Battlefield 4  Mantle support is in development ‒ Core renderer (closer to PS4 than DX11) ‒ Implement all rendering techniques used in BF4 (many!) ‒ CPU optimizations (parallel dispatch, descriptor sets) ‒ GPU optimizations (minimize transitions, MSAA) ‒ R&D for advanced GPU optimizations ‒ Memory management ‒ Multi-GPU support ‒ ~2 months of work  Update targeting late December

35. Frostbite Plants vs Zombies: Garden Warfare  Very different rendering compared to BF4   Frostbite Mantle renderer will work out of the box  Focus on APU performance

36. Frostbite Future  All Frostbite games designed with Mantle ‒ 15 games in development across all of EA  Advanced Mantle rendering & use cases ‒ Lots of exciting R&D opportunities!  Want multi-vendor & multi-platform support!
 
Last edited:
Nintendesert said:
Ultimately not just AMD but hopefully all of PC gaming. The cheaper PC gaming can become the bigger the market is and hopefully it means more developer focus vs. consoles. That's the hope with Intel's IGP and these AMD APUs. I don't think any of us would use either, but if that means less crappy console ports all the better. I'm really interested to see what Mantle will do.
Click to expand...

Amd stated the goals for mantle like this:

1. More ports
2. Quality ports

Then the rest like quality and speed.

Mantle obviously adresses whats absolutely most important for the developers.
 
AMD paid DICE, so again, actual data from an uninterested party will hold more weight when the time comes. Be very wary of anyone who claims it is awesome or worthless for now.
 
Mantle would be incredible if game makers could create a game once and have it run on Windows/Mac/Linux without anything else needing to be done.

That would be the biggest improvement, especially if performance was on par for all of them.

But Nvidia needs to be part of it first... It would be great for everyone if they could at least do a Mantle/PhysX tradeoff.
 
Haserath said:
But Nvidia needs to be part of it first... It would be great for everyone if they could at least do a Mantle/PhysX tradeoff.
Click to expand...

That would be nice but my guess is it's unlikely. I think you can predict pretty well how Nvidia will react to something if you just imagine it as an extension of JHH's ego.
 
Last edited:
OCGuy said:
AMD paid DICE, so again, actual data from an uninterested party will hold more weight when the time comes. Be very wary of anyone who claims it is awesome or worthless for now.
Click to expand...

There is also the story of DICE actually going around presenting the idea of new API to Intel, NVIDIA and AMD and AMD being the only one picking it up.
 
OCGuy said:
Exactly. So they as well as AMD have a financial interest in its success.
Click to expand...

except you have 4 games coming out with Mantle support and only 2 of those are from EA. So I guess AMD has bucket loads of money to pay of each one of those devs. Including Oxide.
 
Skurge said:
except you have 4 games coming out with Mantle support and only 2 of those are from EA. So I guess AMD has bucket loads of money to pay of each one of those devs. Including Oxide.
Click to expand...

I know you're being sarcastic, but some people might not know that.

Oxide has already gone on the record as approaching AMD first about something like Mantle, not the other way around. So it's not just AMD pushing Mantle, it's also some developers.

That said, AMD must get the support of the big engines to really make a dent in the marketplace. Frostbite is a nice start, but Unreal is the most popular engine. If AMD can get Unreal on board, then most likely everyone else will fall into line and Mantle will enjoy pretty broad support. Even if AMD doesn't get Unreal on board, some developers may tack it on anyway, sort of like how anti-aliasing is not natively supported under Unreal 3 but some game devs tack it on themselves.
 
Last edited:
And if AMD does need to pay studios, so what?

If the performance gains that have been claimed for Mantle are true, paying to get Mantle incorporated into the major engines will be money well spent

AMD wouldn't be the first company to have to pay for their tech to be adopted, I don't see why there should be so much fuss about it
 
Last edited:
Spjut said:
And if AMD does need to pay studios, so what?

If the performance gains that have been claimed for Mantle are true, paying to get Mantle incorporated into the major engines will be money well spent

AMD wouldn't be the first company to have to pay for their tech to be adopted, I don't see why there should be so much fuss about it
Click to expand...

That is called a "strawman" argument, because nobody said it was wrong for AMD to pay DICE to put in the hours for Mantle's launch.

I brought up the money changing hands, because someone posted a DICE quote to back up an AMD quote to show how Mantle would perform.
 
blastingcap said:
I know you're being sarcastic, but some people might not know that.

Oxide has already gone on the record as approaching AMD first about something like Mantle, not the other way around. So it's not just AMD pushing Mantle, it's also some developers.

That said, AMD must get the support of the big engines to really make a dent in the marketplace. Frostbite is a nice start, but Unreal is the most popular engine. If AMD can get Unreal on board, then most likely everyone else will fall into line and Mantle will enjoy pretty broad support. Even if AMD doesn't get Unreal on board, some developers may tack it on anyway, sort of like how anti-aliasing is not natively supported under Unreal 3 but some game devs tack it on themselves.
Click to expand...

I believe Nixxes's Thief is on Unreal Engine and they are supporting mantle.
 
desprado said:
Wow Mantle with Unreal Engine 3 are joking.Do u really Mantle with Unreal Engine 3 yes 4 makes sense but EPIC has very close relationship with Nvidia.

He said to realistic it could get 20%.
Click to expand...

When Nixxes adds it to Thief, if it runs even 20% faster than DX, do you think everyone will be content just using DX for their projects on UnReal 3 engine? Or do you think it's popularity might suffer?
 
3DVagabond said:
When Nixxes adds it to Thief, if it runs even 20% faster than DX, do you think everyone will be content just using DX for their projects on UnReal 3 engine? Or do you think it's popularity might suffer?
Click to expand...

Engine like Crytek,Frostbite and UE4 make some sense with performance of 20% gain makes sense but really UE3 is that demanding that u need to push Mantle on 2007 graphic engine.
 
Status
Not open for further replies.

TRENDING THREADS

Back
Top