Design Automation for Smart Factories

A paper titled Split-Et-Impera: A Framework for the Design of Distributed Deep Learning Applications, authored by Luigi Capogrosso, Federico Cunico, Michele Lora, Marco Cristani, Franco Fummi, and Davide Quaglia has been accepted at the 26th International Symposium on Design and Diagnostics of Electronic Circuits and Systems (DDECS 2023)

Many recent pattern recognition applications rely on complex distributed architectures in which sensing and computational nodes interact together through a communication network. Deep neural networks (DNNs) play an important role in this scenario, furnishing powerful decision mechanisms, at the price of a high computational effort. Consequently, powerful state-of- the-art DNNs frequently are split over various computational nodes, e.g., a first part stays on an embedded device and the rest on a server. Deciding where to split a DNN is a challenge in itself, making the design of deep learning applications even more complicated. Therefore, this paper proposes Split-Et-Impera, a novel and practical framework that i) determines the set of the best-split points of a neural network based on deep network interpretability principles without performing a tedious try-and- test approach, ii) performs a communication-aware simulation for the rapid evaluation of different neural network rearrangements, and iii) suggests the best match between the quality of service requirements of the application and the performance in terms of accuracy and latency time.

A pre-print of the paper is available here.