TY - GEN
T1 - Poster Abstract
T2 - 15th Annual ACM/IEEE International Conference on Cyber-Physical Systems, ICCPS 2024
AU - Xu, Shengjie
AU - Hobbs, Clara
AU - Song, Yukai
AU - Ghosh, Bineet
AU - Aktar, Sharmin
AU - Yang, Lei
AU - Sheng, Yi
AU - Jiang, Weiwen
AU - Hu, Jingtong
AU - Duggirala, Parasara Sridhar
AU - Chakraborty, Samarjit
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - Neural networks (NNs) are now widely used for perception processing in autonomous systems. Data from sensors like cameras and lidars, after being processed by NNs, feed control algorithms that form the core of autonomy-related functions. Such NNs are implemented on graphics processing units (GPUs) and modern GPUs can be partitioned into multiple virtual machines, each implementing a separate NN. Given an autonomous system with multiple NNs, how should each NN be sized and the GPU implementing them be optimally partitioned? In this work, we study multiple GPU partitioning techniques with the goal of optimal and safe system-level control performance.
AB - Neural networks (NNs) are now widely used for perception processing in autonomous systems. Data from sensors like cameras and lidars, after being processed by NNs, feed control algorithms that form the core of autonomy-related functions. Such NNs are implemented on graphics processing units (GPUs) and modern GPUs can be partitioned into multiple virtual machines, each implementing a separate NN. Given an autonomous system with multiple NNs, how should each NN be sized and the GPU implementing them be optimally partitioned? In this work, we study multiple GPU partitioning techniques with the goal of optimal and safe system-level control performance.
KW - autonomous systems
KW - learning-enabled cyber-physical systems
KW - neural architecture sizing
KW - reachability
KW - uncertainty
UR - https://www.scopus.com/pages/publications/85198513909
U2 - 10.1109/ICCPS61052.2024.00040
DO - 10.1109/ICCPS61052.2024.00040
M3 - Conference contribution
AN - SCOPUS:85198513909
T3 - Proceedings - 15th ACM/IEEE International Conference on Cyber-Physical Systems, ICCPS 2024
SP - 289
EP - 290
BT - Proceedings - 15th ACM/IEEE International Conference on Cyber-Physical Systems, ICCPS 2024
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 13 May 2024 through 16 May 2024
ER -