1. The Small batch (and Other) solutions in Mantle API
Guennadi Riguer – Mantle Chief Architect

2. Small batch performance
Problems
Abstraction level
Small batch performance
Platform efficiency

3. Wrong Abstraction Level
Unpredictable big black box
Current situation: neither fast nor simple
Too high to be fast, too low to be simple

4. Small Batch Performance
10K
100K
Most games today
Really optimized games
Where you want to be (Mantle target)

5. Texture atlases & arrays
Previous Solutions
Geometry instancing
Geometry shaders
Texture atlases & arrays
Uber-shaders
Command recorders …

6. Why They Failed? Development and content creation limitations
Trading driver overhead for engine performance
Trading CPU performance for GPU overhead

7. Empower developers to do what they want
What is Mantle?
Lower level API
Focus on performance
Empower developers to do what they want

8. Predictable performance
Why Mantle?
Better performance
Predictable performance
Developer control

9. Key Features

10. Execution Model GPU Queues Application . . . Graphics Compute DMA
App thread

11. Execution Model GPU Queues Application . . . Graphics Compute DMA
App thread

12. Execution Model GPU Application Queues . . . Graphics Compute DMA
App thread
Queues

13. Execution Model Queues Application GPU . . . Graphics Compute DMA
App thread
Graphics
Compute
DMA
GPU
. . .

14. Memory & Resources Application controls memory
Application handles hazards
Generalized resources

15. Pre-build & Pre-validate
Pipelines
Resource binding
Multi-use command buffers

16. Platform Considerations
APUs & SOCs are here
No longer CPU vs. GPU
Race to low power

17. Power Efficiency - StarSwarm
FPS
Power (W)
FPS/W
The selection of resolutions and settings was made to create both CPU and GPU limited cases for completeness of the produced results.
Starswarm using RTS running on APU 3.5GHz, 4GB 2133MHz RAM, A88X-Pro M/B

18. Power Efficiency - Games
FPS
Power (W)
FPS/W
The selection of resolutions and settings was made to create both CPU and GPU limited cases for completeness of the produced results.
Battlefield 4 BrokenFlightDeck MEDIUM settings and SSAO enabled running on APU 3.5GHz, 4GB 2133MHz RAM, A88X-Pro M/B
Thief built-in benchmark running on same hardware with low settings at 720x480 and normal settings at 720p

19. Lessons Learned

20. Think Outside the Box Don’t just make something faster
…avoid doing it completely
Design API and driver together

21. New Driver Design Even a bit of sync kills many-core performance
“Thick” driver = cache pollution
“Make it the application’s problem” 

22. The whole is greater than the sum of its parts
Lots of Little Things…
The whole is greater than the sum of its parts

23. Future HW Considerations
HW small batch, anyone?
Command processing bottlenecks
More operations/batches in flight

24. Applications must "do the right thing“
Challenges
Programming is harder
Ecosystem must change
Applications must "do the right thing“

25. Summary Mantle fixes abstraction level
Mantle improves platform efficiency
Mantle leads industry transformation

26. Questions?

27. Disclaimer & Attribution
The information presented in this document is for informational purposes only and may contain technical inaccuracies, omissions and typographical errors. The information contained herein is subject to change and may be rendered inaccurate for many reasons, including but not limited to product and roadmap changes, component and motherboard version changes, new model and/or product releases, product differences between differing manufacturers, software changes, BIOS flashes, firmware upgrades, or the like. AMD assumes no obligation to update or otherwise correct or revise this information. However, AMD reserves the right to revise this information and to make changes from time to time to the content hereof without obligation of AMD to notify any person of such revisions or changes. AMD MAKES NO REPRESENTATIONS OR WARRANTIES WITH RESPECT TO THE CONTENTS HEREOF AND ASSUMES NO RESPONSIBILITY FOR ANY INACCURACIES, ERRORS OR OMISSIONS THAT MAY APPEAR IN THIS INFORMATION. AMD SPECIFICALLY DISCLAIMS ANY IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR ANY PARTICULAR PURPOSE. IN NO EVENT WILL AMD BE LIABLE TO ANY PERSON FOR ANY DIRECT, INDIRECT, SPECIAL OR OTHER CONSEQUENTIAL DAMAGES ARISING FROM THE USE OF ANY INFORMATION CONTAINED HEREIN, EVEN IF AMD IS EXPRESSLY ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. ATTRIBUTION © 2014 Advanced Micro Devices, Inc. All rights reserved. AMD, the AMD Arrow logo and combinations thereof are trademarks of Advanced Micro Devices, Inc. in the United States and/or other jurisdictions. DirectX is a registered trademark of Microsoft Corporation.