Contextual configuration adjuster for graphics

1. An electronic processing system, comprising:

a graphics subsystem to run a graphics application;

persistent storage media communicatively coupled to the graphics subsystem;

memory communicatively coupled to the graphics subsystem;

a display communicatively coupled to the graphics subsystem;

a contextual configuration adjuster communicatively coupled to the graphics subsystem to adjust a configuration of the graphics subsystem based on contextual information;

a profiler to determine profile information for the graphics application that is run by the graphics subsystem; and

a neural network trainer to train a neural network to develop a configuration decision network for the graphics application based on the profile information.

2. The system of claim 1 , wherein the contextual configuration adjuster comprises a context engine to determine the contextual information.

3. The system of claim 2 , further comprising:

a recommendation engine communicatively coupled to the context engine to determine a recommendation based on the contextual information.

4. The system of claim 3 , wherein the contextual configuration adjuster is further to adjust the configuration of the graphics subsystem based at least in part on the recommendation from the recommendation engine.

5. The system of claim 1 , further comprising:

a sense engine communicatively coupled to the contextual configuration adjuster to sense contextual data.

6. The system of claim 1 , wherein after the neural network is trained, the neural network provides a decision tree to be used during runtime to determine a machine configuration.

7. The system of claim 1 , wherein the contextual configuration adjuster is further to adjust the configuration of the graphics subsystem based on the configuration decision network.

8. A graphics apparatus, comprising:

a context engine to determine contextual information;

a recommendation engine communicatively coupled to the context engine to determine a recommendation based on the contextual information; and

a configuration engine communicatively coupled to the recommendation engine to adjust a configuration of a graphics operation based on the recommendation,

wherein the context engine includes a profiler to determine profile information for a graphics application, the graphics application being run by a graphics subsystem, and

wherein the recommendation engine includes a neural network trainer to train a neural network to develop a configuration decision network for the graphics application based on the profile information.

9. The apparatus of claim 8 , wherein the contextual information includes one or more of user, content, location, biometric, time, temperature, power, environmental, schedule, habit, and configuration settings for a prior frame, wherein the recommendation includes one or more of a power setting, a performance setting, a high performance mode, a balanced performance mode, a low power mode, a game mode, a movie mode, and a configuration setting for a subsequent frame, and wherein the graphics operation includes one or more of a resolution, a frame rate, a color precision, and a sampling rate.

10. The apparatus of claim 8 , wherein the context engine comprises:

a sense engine to sense contextual data, wherein the context engine is further to determine the contextual information based on the sensed contextual data.

11. The apparatus of claim 10 , wherein the sensed contextual data includes one or more of a brightness of the environment, a temperature of the environment, machine vision information of the environment, movement information of the user, biometric information of the user, gesture information of the user, facial information of the user, and machine vision information of the user.

12. The apparatus of claim 8 , wherein the recommendation engine comprises a recommendation store to store one or more recommendations in association with saved contextual information, wherein the recommendation engine is further to:

compare the contextual information from the context engine with the saved contextual information; and

retrieve a stored recommendation associated with saved contextual information based on the comparison.

13. The apparatus of claim 8 , wherein the recommendation engine further comprises a configuration decision network to:

input the contextual information; and

output a recommended configuration,

wherein the recommendation engine is to determine the recommendation based on the recommended configuration from the configuration decision network.

14. The apparatus of claim 8 , wherein the recommendation is based on a predicted user preference for the configuration of a graphics operation.

15. The apparatus of claim 8 , wherein the configuration engine is further to adjust the configuration of the graphics operation based on the configuration decision network.

16. The apparatus of claim 8 , wherein after the neural network is trained, the neural network provides a decision tree to be used during runtime to determine a machine configuration.

17. A method of configuring graphics, comprising:

determining contextual information;

determining a recommendation based on the contextual information;

adjusting a configuration of a graphics operation based on the recommendation;

determining profile information for a graphics application, the graphics application being run by a graphics subsystem;

training a neural network to develop a configuration decision network for the graphics application based on the profile information; and

adjusting the configuration of the graphics operation based on the configuration decision network.

18. The method of claim 17 , further comprising:

after the training the neural network, providing a decision tree to be used during runtime to determine a machine configuration.

19. The method of claim 17 , wherein the contextual information includes one or more of user, content, location, biometric, time, temperature, power, environmental, schedule, habit, and configuration settings for a prior frame, wherein the recommendation includes one or more of a power setting, a performance setting, a high performance mode, a balanced performance mode, a low power mode, a game mode, a movie mode, and a configuration setting for a subsequent frame, and wherein the graphics operation includes one or more of a resolution, a frame rate, a color precision, and a sampling rate.

20. The method of claim 17 , further comprising:

sensing contextual data; and

determining the contextual information based on the sensed contextual data.

21. The method of claim 20 , wherein the sensed contextual data includes one or more of a brightness of the environment, a temperature of the environment, machine vision information of the environment, movement information of the user, biometric information of the user, gesture information of the user, facial information of the user, and machine vision information of the user.

22. The method of claim 17 , further comprising:

storing one or more recommendations in association with saved contextual information;

comparing the contextual information with the saved contextual information; and

retrieving a stored recommendation associated with saved contextual information based on the comparison.

23. The method of claim 17 , further comprising:

loading the configuration decision network;

inputting the contextual information into the configuration decision network;

outputting a recommended configuration from the configuration decision network; and

determining the recommendation based on the recommended configuration from the configuration decision network.

24. The method of claim 17 , further comprising:

predicting a user preference for the configuration of a graphics operation.