Adaptive loading-aware system management for balancing power and performance
A computing system performs balanced power management based on requirements of graphics scenes in a video game. Based on the requirements of the graphics scenes, the system selects one or more performance metrics to reduce in real-time, where the performance metrics are indicators of video game quality. The system compares estimated power consumption with a power budget after reducing the one or more performance metrics. Based on the requirements of the graphics scenes, the system further selects one or more quality enhancers to activate in real-time while keeping the estimated power consumption within the power budget. Each quality enhancer enhances the video game with respect to a performance metric. The system then displays the video game enhanced by the one or more quality enhancers.
1. A method for balanced power management in a computing system, comprising:
selecting, based on requirements of graphics scenes in a video game, one or more performance metrics to reduce in real-time, wherein the performance metrics are indicators of video game quality;
comparing estimated power consumption with a power budget after reducing the one or more performance metrics;
selecting, based on the requirements of the graphics scenes, one or more quality enhancers to activate in real-time while keeping the estimated power consumption within the power budget, wherein each quality enhancer enhances the video game with respect to a performance metric, and wherein the selecting further comprises:
predicting, based on one or more power models, power consumption of the computing system with the one or more quality enhancers activated; and
activating the one or more quality enhancers when predicted power consumption is within the power budget; and
displaying the video game enhanced by the one or more quality enhancers.
2. The method of claim 1 , wherein the performance metrics provided by the computing system include at least resolution, frame rate, and picture quality of the video game.
3. The method of claim 1 , wherein the quality enhancers provided by the computing system include one or more of: an artificial intelligence (AI) super-resolution (SR) engine to enhance resolution, and a motion estimation motion compensation (MEMC) engine to increase frame rate, and a picture quality (PQ) engine to increase a picture quality level.
4. The method of claim 1 , wherein the requirements of graphics scenes include priorities of the performance metrics provided by the computing system.
5. The method of claim 1 , wherein selecting the one or more performance metrics is based on present loading of each of a plurality of processors in the computing system and predicted loading of each processor with the one or more performance metrics reduced.
6. The method of claim 1 , wherein selecting the one or more quality enhancers is based on present loading of each of a plurality of processors in the computing system and predicted loading of each processor with the one or more quality enhancers activated.
7. The method of claim 1 , further comprising:
dynamically adjusting the power budget based on temperatures sensed in the computing system; and
determining which quality enhances to turn on or off based on the adjusted power budget and the estimated power consumption.
8. The method of claim 1 , further comprising:
after reducing the one or more performance metrics, dynamically lowering operating frequency of one or more processors in the computing system to reduce power consumption to within the power budget.
9. The method of claim 1 , further comprising:
if the estimated power consumption exceeds the power budget after reducing frame per second (FPS) and resolution of the video game, performing variable-rate shading (VRS) on the video game.
10. The method of claim 1 , further comprising:
selecting a combination of performance metrics to adjust when there is a power budget surplus; and
based on at least the requirements of the graphics scenes, determining which quality enhancers to turn on or off without exceeding the power budget.
11. The method of claim 1 , further comprising:
selecting a combination of performance metrics to adjust and quality enhancers to turn on or off based on a whitelist that is set up for each graphics scene and each of a plurality of functions used in rendering the graphics scene.
12. A system operative to perform balanced power management, comprising:
a plurality of processors;
balance manager circuitry coupled to the processors to:
select, based on requirements of graphics scenes in a video game, one or more performance metrics to reduce in real-time, wherein the performance metrics are indicators of video game quality;
compare estimated power consumption with a power budget after reduction of the one or more performance metrics; and
select, based on the requirements of the graphics scenes, one or more quality enhancers to activate in real-time, wherein each quality enhancer enhances the video game with respect to a performance metric, and wherein when selecting the one or more quality enhancers, the balance manager circuitry is further operative to;
predict, based on one or more power models, power consumption of the computing system with the one or more quality enhancers activated; and
activating the one or more quality enhancers when predicted power consumption is within the power budget; and
a display to display the video game enhanced by the one or more quality enhancers.
13. The system of claim 12 , wherein the performance metrics provided by the system include at least resolution, frame rate, and picture quality of the video game.
14. The system of claim 12 , wherein the quality enhancers provided by the system include one or more of: an artificial intelligence (AI) super-resolution (SR) engine to enhance resolution, and a motion estimation motion compensation (MEMC) engine to increase frame rate, and a picture quality (PQ) engine to increase a picture quality level.
15. The system of claim 12 , wherein the requirements of graphics scenes include priorities of the performance metrics provided by the system.
16. The system of claim 12 , wherein the balance manager circuitry is operative to select the one or more quality enhancers based on present loading of each processor and predicted loading of each processor with the one or more quality enhancers activated.
17. The system of claim 12 , wherein the balance manager circuitry is operative to perform variable-rate shading (VRS) on the video game if the estimated power consumption exceeds the power budget after reducing frame per second (FPS) and resolution of the video game.
18. The system of claim 12 , wherein the balance manager circuitry is operative to:
select a combination of performance metrics to adjust when there is a power budget surplus; and
based on at least the requirements of the graphics scenes, determine which quality enhancers to turn on or off without exceeding the power budget.