Automatic Tuning of Interactive Perception Applications
This addresses the challenge of expert-dependent tuning for interactive applications, though it is incremental as it builds on existing runtime systems.
The paper tackles the problem of tuning parameters in interactive perception applications to meet latency and fidelity constraints, achieving 90% of optimal fidelity by exploring only 3% of the parameter space.
Interactive applications incorporating high-data rate sensing and computer vision are becoming possible due to novel runtime systems and the use of parallel computation resources. To allow interactive use, such applications require careful tuning of multiple application parameters to meet required fidelity and latency bounds. This is a nontrivial task, often requiring expert knowledge, which becomes intractable as resources and application load characteristics change. This paper describes a method for automatic performance tuning that learns application characteristics and effects of tunable parameters online, and constructs models that are used to maximize fidelity for a given latency constraint. The paper shows that accurate latency models can be learned online, knowledge of application structure can be used to reduce the complexity of the learning task, and operating points can be found that achieve 90% of the optimal fidelity by exploring the parameter space only 3% of the time.