Protean is an energy efficient and heterogeneous platform for adaptive and hardware accelerated battery free computing. We develop a modular “plug-and-play” hardware platform, SuperSensor, with a reconfigurable energy storage circuit that powers a 32-bit ARM-based microcontroller with a convolutional neural network accelerator. An adaptive task-based runtime system, Chameleon, provides intermittency-proof execution of machine learning tasks across heterogeneous processing elements. The runtime automatically scales and dispatches these tasks based on incoming energy, current state, and programmer annotations. A code generator, Metamorph, automates conversion of ML models to intermittent safe execution across heterogeneous compute elements.
SuperSensor is a modular plug-and-play hardware design that supports four distinct modules—harvesters boards, sensors…
Chameleon leverages the capability of the hardware for scalable, inference-focused intermittent computing. Chameleon…
Runtime systems cannot do everything, and developing multiple tiers of a single application can be challenging.…