Year: 2025
Type: article
Abstract: Perception processing in cyber-physical systems (CPS) is now almost exclusively done using Deep Neural Networks (DNNs). Here, camera, radar and LiDAR data – in autonomous vehicles or robots – is fed into DNNs that detect surrounding obstacles and distances to them. These results are used by controllers to compute appropriate actuation signals. But a CPS typically has multiple state components, where each of them might be estimated using a different camera, radar or lidar and an associated DNN. Hence, an emerging problem is to implement multiple DNNs on a resource-constrained graphics processing unit (GPU). While many GPUs from NVIDIA and AMD allow them to be split into multiple virtual GPUs, there is little work on how to partition them, and therefore size the corresponding DNNs, when they are a part of the same CPS. In contrast to the existing practice of focusing on the inference accuracy of individual DNNs in isolation, we propose a system-level safety-driven DNN sizing (and hence GPU partitioning) scheme for vehicular CPS. Our main technical contribution is a detailed experimental evaluation of this DNN sizing approach and an empirical validation of the formal technique behind it.
Source: IEEE Embedded Systems Letters
Authors: Tingan Zhu, Mier Li, Bineet Ghosh, Samarjit Chakraborty, Parasara Sridhar Duggirala
Language: English
Topic: Real-Time Systems Scheduling
Subfield: Hardware and Architecture
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: CPS: Medium: GOALI: Design Automation for Automotive Cyber-Physical Systems, POSE: Phase II: An Open-Source Ecosystem for Scenic, Collaborative Research: HCC: Medium: Deep Learning-Based Tracking of Eyes and Lens Shape from Purkinje Images for Holographic Augmented Reality Glasses, G8388232761
OpenAlex ID: W4412939879