Many-Core Real-Time Network-on-Chip I/O Systems for Reducing Contention and Enhancing Predictability

Zhe Jiang; Xiaotian Dai; Shuai Zhao; Ran Wei; Ian Gray

doi:10.1145/3576914.3587514

Many-Core Real-Time Network-on-Chip I/O Systems for Reducing Contention and Enhancing Predictability

Zhe Jiang, Xiaotian Dai, Shuai Zhao, Ran Wei, Ian Gray

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In safety-critical and high-integrity computing, it is important to guarantee both performance and time-predictability of I/O operations. However, with the continued growth of hardware and architectural complexity, satisfying such real-time requirements has become increasingly challenging because of complex I/O transaction paths and extensive hardware contention. This paper proposes a systematic framework with a novel I/O controller and a reconfigurable NoC, effectively optimising I/O transaction paths to encounter reduced contention. Moreover, we present a theoretical model and optimisation process to further improve real-time performance. The evaluations show that our approach outperforms state-of-the-art I/O processing techniques on a range of metrics.

Original language	English
Title of host publication	CPS-IoT Week '23
Subtitle of host publication	Proceedings of Cyber-Physical Systems and Internet of Things Week 2023
Publisher	ACM
Pages	227–233
Number of pages	7
ISBN (Print)	9798400700491
DOIs	https://doi.org/10.1145/3576914.3587514
Publication status	Published - 9 May 2023
Event	Cyber-Physical Systems and Internet of Things Week - San Antonio, United States Duration: 9 May 2023 → 12 May 2023 https://cps-iot-week2023.cs.utsa.edu/

Conference

Conference	Cyber-Physical Systems and Internet of Things Week
Abbreviated title	CPS-IoT Week '23
Country/Territory	United States
City	San Antonio
Period	9/05/23 → 12/05/23
Internet address	https://cps-iot-week2023.cs.utsa.edu/

Bibliographical note

Access to Document

10.1145/3576914.3587514Licence: CC BY

Many-Core Real-Time Network-on-Chip I/O Systems for Reducing Contention and Enhancing Predictability
© 2023 Copyright held by the owner/author(s).
Final published version, 1.05 MBLicence: CC BY

Cite this

@inproceedings{692c54dce2364f50be1a54e8330f44cb,

title = "Many-Core Real-Time Network-on-Chip I/O Systems for Reducing Contention and Enhancing Predictability",

abstract = "In safety-critical and high-integrity computing, it is important to guarantee both performance and time-predictability of I/O operations. However, with the continued growth of hardware and architectural complexity, satisfying such real-time requirements has become increasingly challenging because of complex I/O transaction paths and extensive hardware contention. This paper proposes a systematic framework with a novel I/O controller and a reconfigurable NoC, effectively optimising I/O transaction paths to encounter reduced contention. Moreover, we present a theoretical model and optimisation process to further improve real-time performance. The evaluations show that our approach outperforms state-of-the-art I/O processing techniques on a range of metrics. ",

author = "Zhe Jiang and Xiaotian Dai and Shuai Zhao and Ran Wei and Ian Gray",

note = "{\textcopyright} 2023 Copyright held by the owner/author(s).; Cyber-Physical Systems and Internet of Things Week, CPS-IoT Week '23 ; Conference date: 09-05-2023 Through 12-05-2023",

year = "2023",

month = may,

day = "9",

doi = "10.1145/3576914.3587514",

language = "English",

isbn = "9798400700491",

pages = "227–233",

booktitle = "CPS-IoT Week '23",

publisher = "ACM",

address = "United States",

url = "https://cps-iot-week2023.cs.utsa.edu/",

}

Jiang, Z, Dai, X, Zhao, S, Wei, R & Gray, I 2023, Many-Core Real-Time Network-on-Chip I/O Systems for Reducing Contention and Enhancing Predictability. in CPS-IoT Week '23: Proceedings of Cyber-Physical Systems and Internet of Things Week 2023. ACM, pp. 227–233, Cyber-Physical Systems and Internet of Things Week, San Antonio, United States, 9/05/23. https://doi.org/10.1145/3576914.3587514

TY - GEN

T1 - Many-Core Real-Time Network-on-Chip I/O Systems for Reducing Contention and Enhancing Predictability

AU - Jiang, Zhe

AU - Dai, Xiaotian

AU - Zhao, Shuai

AU - Wei, Ran

AU - Gray, Ian

PY - 2023/5/9

Y1 - 2023/5/9

N2 - In safety-critical and high-integrity computing, it is important to guarantee both performance and time-predictability of I/O operations. However, with the continued growth of hardware and architectural complexity, satisfying such real-time requirements has become increasingly challenging because of complex I/O transaction paths and extensive hardware contention. This paper proposes a systematic framework with a novel I/O controller and a reconfigurable NoC, effectively optimising I/O transaction paths to encounter reduced contention. Moreover, we present a theoretical model and optimisation process to further improve real-time performance. The evaluations show that our approach outperforms state-of-the-art I/O processing techniques on a range of metrics.

AB - In safety-critical and high-integrity computing, it is important to guarantee both performance and time-predictability of I/O operations. However, with the continued growth of hardware and architectural complexity, satisfying such real-time requirements has become increasingly challenging because of complex I/O transaction paths and extensive hardware contention. This paper proposes a systematic framework with a novel I/O controller and a reconfigurable NoC, effectively optimising I/O transaction paths to encounter reduced contention. Moreover, we present a theoretical model and optimisation process to further improve real-time performance. The evaluations show that our approach outperforms state-of-the-art I/O processing techniques on a range of metrics.

U2 - 10.1145/3576914.3587514

DO - 10.1145/3576914.3587514

M3 - Conference contribution

SN - 9798400700491

SP - 227

EP - 233

BT - CPS-IoT Week '23

PB - ACM

T2 - Cyber-Physical Systems and Internet of Things Week

Y2 - 9 May 2023 through 12 May 2023

ER -