Odessa

TLDR

Resource constrained mobile devices need to leverage computation on nearby servers to run responsive applications that recognize objects, people, or gestures from real‑time video. The study develops Odessa, a lightweight runtime that automatically and adaptively decides which computations to offload and how to parallelize across mobile devices and servers for interactive perception applications. Odessa uses an incremental greedy strategy that partitions tasks between device and server, evaluated on three interactive perceptual applications. Evaluation shows Odessa’s greedy strategy converges to near‑optimal partitioning, yielding over 3× performance gains versus expert‑suggested splits and remaining robust across diverse networks, devices, and application inputs.

Abstract

Resource constrained mobile devices need to leverage computation on nearby servers to run responsive applications that recognize objects, people, or gestures from real-time video. The two key questions that impact performance are what computation to offload, and how to structure the parallelism across the mobile device and server. To answer these questions, we develop and evaluate three interactive perceptual applications. We find that offloading and parallelism choices should be dynamic, even for a given application, as performance depends on scene complexity as well as environmental factors such as the network and device capabilities. To this end we develop Odessa, a novel, lightweight, runtime that automatically and adaptively makes offloading and parallelism decisions for mobile interactive perception applications. Our evaluation shows that the incremental greedy strategy of Odessa converges to an operating point that is close to an ideal offline partitioning. It provides more than a 3x improvement in application performance over partitioning suggested by domain experts. Odessa works well across a variety of execution environments, and is agile to changes in the network, device and application inputs.