1 / 29

Adaptive Display Power Management for Mobile Games

Adaptive Display Power Management for Mobile Games. Bhojan Anand ‡, Karthik Thirugnanam †, Jeena Sebastian‡, Pravein G. Kannan ‡, Akhihebbal L. Ananda ‡, Mun Choon Chan‡ and Rajesh Krishna Balan † ‡ National University of Singapore (NUS) and † Singapore Management University (SMU).

clint
Download Presentation

Adaptive Display Power Management for Mobile Games

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Adaptive Display Power Management for Mobile Games BhojanAnand‡, KarthikThirugnanam†, Jeena Sebastian‡, Pravein G. Kannan‡, Akhihebbal L. Ananda‡, MunChoon Chan‡ and Rajesh Krishna Balan† ‡ National University of Singapore (NUS) and † Singapore Management University (SMU)

  2. Key problem and Solution • Problem: Display draws significant phone power • Key Challenge: No loss in end user experience Display 45-50% Network 35-40% CPU 4-15% Measured on HTC Magic while streaming a Youtube Video

  3. Key problem and Solution • Dynamically adjust image brightness and LCD display backlight levels • 50-70% display power savings with no significant user experience impact

  4. Talk Outline Key problem and Solution Background System Design Evaluation Discussion/Future Work

  5. Background - LCD Displays • LCD displays have two components: • Power consumed mostly by the Backlight • Thus brightening the image, and darkening the backlight saves power.  • LCD Panel - Filters light based on image to be displayed • Backlight - Provides light, and consumes power

  6. Background: Saving Display Power • Method 1: Naively dim the display • Creates visible artifacts (flicker, brightness loss, etc) • Especially noticeable in high frame rate applications

  7. Background: Saving Display Power • Method 2: Compensate with increased brightness • Linearly apply same transform to entire image • Leads to saturated images

  8. Background: Saving Display Power • Method 2: Compensate with increased brightness • Non linear approaches prevent saturation but cause contrast loss • Our solution uses this approach intelligently

  9. Non Linear Gamma Correction • Gamma Correction, or gamma, is a tone mapping function used to brighten scenes • Very Low Saturation relative to linear • Low computational overhead Before After: Gamma 2

  10. Effect of Gamma on Image Quality Image after Gamma Increase (gamma=2) Original Image after Gamma Increase andbacklight reduction

  11. Test Applications • Games are popular and resource intensive • Extremely high frame rates • Flicker and brightness changes very noticeable to users •  We use two representative games • Quake III – Commercial First Person Shooting (FPS) game  • Planeshift – Massively Multiplayer Role Playing Game (MMORPG)

  12. Talk Outline Key problem and Solution Background System Design Evaluation Discussion/Future Work

  13. System Design: Key Challenges • Ultimate goal: Save significant power with no loss in end user experience • Challenge 1: Understanding the relationship between the backlight intensity, gamma, image brightness, and the power consumed • Challenge 2: Identifying human thresholds for brightness compensation • Challenge 3: Dynamically applying the solution

  14. Challenge 1: Backlight vs Power • Relationship found to be linear.  • No other major contributing factors Laptop (W500) HTC Hero HTC Magic

  15. Challenge 1: Backlight vs Gamma • Perceived brightness kept constant • Non linear compensation necessary • Useful gamma range is 1 to 4

  16. Challenge 2: Human Thresholds • Obtained via small user study • 5 postgraduate students • Each user shown a range of images • Covered a full range of brightness • For each image, users had to boost gamma to obtain two quality thresholds • Described in next slide • Tool provided boosted gamma at .1 intervals with automatic backlight compensation

  17. Challenge 2: Two Thresholds • Conservative: Image quality comparable to original • Aggressive: Image quality is affected but acceptable

  18. Challenge 3: Runtime Algorithm Start Calculate Average Brightness of last X Samples. Is there a change? No Yes Mode + Brightness -> Gamma & Backlight Leave Settings as it is Sleep Thread for Y ms

  19. Evaluation Methodology • Test platform • Most of the evaluation on Laptop • Prototype Mobile implementation available (demo) • Objective Analytical Experiments • Power measurements  • Measured power saved in different modes • Perceived User Impact • Large scale user study (60 users) with Quake III • Measured perceived quality loss in different modes

  20. Evaluation: Three Test Modes Two bounding modes tested but omitted for simplicity Aggressive Conservative Unmodified

  21. Evaluation: Power Savings • A recorded trace used to measure power

  22. User Study Methodology • Large Scale User study • 60 Singapore Management University undergrads. • 34 Male and 26 Female students with differing background and game experiences • Participants trained on an unmodified version of the game • They then played the 3 different versions of the game • Play order randomized with recalibration at every step

  23. Evaluation: User Study Results • Users rated each version by 6 criteria • Covered different quality dimensions Strongly Agree = Good Neutral = Bad Strongly Disagree =

  24. Evaluation: Aggressive vs Conservative • Difference between Aggressive and Conservative significant

  25. Evaluation: Power vs Perception • Difference betw. Conservative and Default

  26. Evaluation: Conclusions • Conservative (Dynamic Conservative) • High Quality • Perceived quality comparable to default. • Significant Savings – 49% • Aggressive (Dynamic Aggressive) • High Power Saving – 68% • Acceptable Quality

  27. Discussion • OLED Displays • Do not use Backlight • Power consumption depends on displayed content • Algorithm needs to be rethought • Other Limitations & Future Work • Initial User studies were small scale, and in a controlled environment • Power Measurements could be more accurate, esp for mobile phone • Evaluation of mobile implementation

  28. Contributions • General systematic approach to save power on LCD screens • Identified key parameters determining the quality vs power savings tradeoff • Implemented and tested with 60 end users • System achieves significant power savings with minimal overhead and quality loss

  29. Thank you Any Questions

More Related