SPHERE: A Multi-SoC Architecture for Next-Generation Cyber-Physical Systems Based on Heterogeneous Platforms

被引:13
作者
Biondi, Alessandro [1 ]
Casini, Daniel [1 ]
Cicero, Giorgiomaria [1 ]
Borgioli, Niccolo [1 ]
Buttazzo, Giorgio [1 ]
Patti, Gaetano [2 ]
Leonardi, Luca [2 ]
Lo Bello, Lucia [2 ]
Solieri, Marco [3 ]
Burgio, Paolo [3 ]
Olmedo, Ignacio Sanudo [3 ]
Ruocco, Angelo [3 ]
Palazzi, Luca [3 ]
Bertogna, Marko [3 ]
Cilardo, Alessandro [4 ]
Mazzocca, Nicola [4 ]
Mazzeo, Antonino [4 ]
机构
[1] Scuola Super Sant Anna, I-56127 Pisa, Italy
[2] Univ Catania, I-95124 Catania, Italy
[3] Univ Modena & Reggio Emilia, I-41121 Modena, Italy
[4] Univ Naples Federico II, I-80138 Naples, Italy
关键词
Virtual machine monitors; Field programmable gate arrays; Real-time systems; Virtualization; Linux; Switches; Safety; Cyber-physical systems; embedded systems; real-time systems; hypervisor; FPGA; SCHEDULABILITY ANALYSIS; NETWORKS;
D O I
10.1109/ACCESS.2021.3080842
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper presents SPHERE, a project aimed at the realization of an integrated framework to abstract the hardware complexity of interconnected, modern system-on-chips (SoC) and simplify the management of their heterogeneous computational resources. The SPHERE framework leverages hypervisor technology to virtualize computational resources and isolate the behavior of different subsystems running on the same platform, while providing safety, security, and real-time communication mechanisms. The main challenges addressed by SPHERE are discussed in the paper along with a set of new technologies developed in the context of the project. They include isolation mechanisms for mixed-criticality applications, predictable I/O virtualization, the management of time-sensitive networks with heterogeneous traffic flows, and the management of field-programmable gate arrays (FPGA) to provide efficient implementations for cryptography modules, as well as hardware acceleration for deep neural networks. The SPHERE architecture is validated through an autonomous driving use-case.
引用
收藏
页码:75446 / 75459
页数:14
相关论文
共 36 条
[1]   Towards Dynamic and Partial Reconfigurable Hardware Architectures for Cryptographic Algorithms on Embedded Devices [J].
Alkamil, Arkan ;
Perera, Darshika G. .
IEEE ACCESS, 2020, 8 :221720-221742
[2]  
[Anonymous], 2020, ZYNQ ULTRASCALEC MPS
[3]   Schedulability analysis of Ethernet Audio Video Bridging networks with scheduled traffic support [J].
Ashjaei, Mohammad ;
Patti, Gaetano ;
Behnam, Moris ;
Nolte, Thomas ;
Alderisi, Giuliana ;
Lo Bello, Lucia .
REAL-TIME SYSTEMS, 2017, 53 (04) :526-577
[4]   Secure internal communication of a TrustZone-enabled heterogeneous SoC lightweight encryption [J].
Benhani, El Mehdi ;
Mancillas Lopez, Cuauhtemoc ;
Bossuet, Lilian .
2019 INTERNATIONAL CONFERENCE ON FIELD-PROGRAMMABLE TECHNOLOGY (ICFPT 2019), 2019, :239-242
[5]  
Biondi A, 2016, PROCEEDINGS OF 2016 IEEE REAL-TIME SYSTEMS SYMPOSIUM (RTSS), P1, DOI [10.1109/RTSS.2016.010, 10.1109/RTSS.2016.37]
[6]  
Casini D., 2021, P IEEE REAL TIM EMB P IEEE REAL TIM EMB
[7]   A Holistic Memory Contention Analysis for Parallel Real-Time Tasks under Partitioned Scheduling [J].
Casini, Daniel ;
Biondi, Alessandro ;
Nelissen, Geoffrey ;
Buttazzo, Giorgio .
2020 IEEE REAL-TIME AND EMBEDDED TECHNOLOGY AND APPLICATIONS SYMPOSIUM (RTAS 2020), 2020, :239-252
[8]   Scheduling Real-Time Communication in IEEE 802.1Qbv Time Sensitive Networks [J].
Craciunas, Silviu S. ;
Oliver, Ramon Serna ;
Chmelik, Martin ;
Steiner, Wilfried .
PROCEEDINGS OF THE 24TH INTERNATIONAL CONFERENCE ON REAL-TIME NETWORKS AND SYSTEMS PROCEEDINGS (RTNS 2016), 2016, :183-192
[9]  
Crespo A., 2010, Proceedings of the 2010 Eighth European Dependable Computing Conference (EDCC 2010), P67, DOI 10.1109/EDCC.2010.18
[10]   A Survey on Cache Management Mechanisms for Real-Time Embedded Systems [J].
Gracioli, Giovani ;
Alhammad, Ahmed ;
Mancuso, Renato ;
Froehlich, Antonio Augusto ;
Pellizzoni, Rodolfo .
ACM COMPUTING SURVEYS, 2015, 48 (02)