Millimeter wave wireless network on chip using deep reinforcement learning

Suraj Jog; Zikun Liu; Antonio Franques; Vimuth Fernando; Haitham Hassanieh; Sergi Abadal; Josep Torrellas

doi:10.1145/3405837.3411396

Millimeter wave wireless network on chip using deep reinforcement learning

Suraj Jog, Zikun Liu, Antonio Franques, Vimuth Fernando, Haitham Hassanieh, Sergi Abadal, Josep Torrellas

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

Abstract

Wireless Network-on-Chip (NoC) has emerged as a promising solution to scale chip multi-core processors to hundreds of cores. However, traditional medium access protocols fall short here since the traffic patterns on wireless NoCs tend to be very dynamic and can change drastically across different cores, different time intervals and different applications. In this work, we present NeuMAC, a unified approach that combines networking, architecture and AI to generate highly adaptive medium access protocols that can learn and optimize for the structure, correlations and statistics of the traffic patterns on the NoC. Our results show that NeuMAC can quickly adapt to NoC traffic to provide significant gains in terms of latency and overall execution time, improving the execution time by up to 1.69X - 3.74X.

Original language	English (US)
Title of host publication	Proceedings of the SIGCOMM 2020 Poster and Demo Sessions, SIGCOMM 2020
Publisher	Association for Computing Machinery
Pages	70-72
Number of pages	3
ISBN (Electronic)	9781450380485
DOIs	https://doi.org/10.1145/3405837.3411396
State	Published - Aug 10 2020
Event	2020 Annual Conference of the ACM Special Interest Group on Data Communication on the Applications, Technologies, Architectures, and Protocols for Computer Communication, SIGCOMM 2020 - Virtual, Online, United States Duration: Aug 10 2020 → Aug 14 2020

Publication series

Name	Proceedings of the SIGCOMM 2020 Poster and Demo Sessions, SIGCOMM 2020

Conference

Conference	2020 Annual Conference of the ACM Special Interest Group on Data Communication on the Applications, Technologies, Architectures, and Protocols for Computer Communication, SIGCOMM 2020
Country/Territory	United States
City	Virtual, Online
Period	8/10/20 → 8/14/20

Keywords

Deep reinforcement learning
Millimeter wave
Wireless network-on-chip

ASJC Scopus subject areas

Computer Networks and Communications
Hardware and Architecture
Electrical and Electronic Engineering

Online availability

10.1145/3405837.3411396

Library availability

Discover UIUC Full Text

Cite this

Jog, S., Liu, Z., Franques, A., Fernando, V., Hassanieh, H., Abadal, S., & Torrellas, J. (2020). Millimeter wave wireless network on chip using deep reinforcement learning. In Proceedings of the SIGCOMM 2020 Poster and Demo Sessions, SIGCOMM 2020 (pp. 70-72). (Proceedings of the SIGCOMM 2020 Poster and Demo Sessions, SIGCOMM 2020). Association for Computing Machinery. https://doi.org/10.1145/3405837.3411396

Millimeter wave wireless network on chip using deep reinforcement learning. / Jog, Suraj; Liu, Zikun; Franques, Antonio et al.
Proceedings of the SIGCOMM 2020 Poster and Demo Sessions, SIGCOMM 2020. Association for Computing Machinery, 2020. p. 70-72 (Proceedings of the SIGCOMM 2020 Poster and Demo Sessions, SIGCOMM 2020).

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

Jog, S, Liu, Z, Franques, A, Fernando, V, Hassanieh, H, Abadal, S & Torrellas, J 2020, Millimeter wave wireless network on chip using deep reinforcement learning. in Proceedings of the SIGCOMM 2020 Poster and Demo Sessions, SIGCOMM 2020. Proceedings of the SIGCOMM 2020 Poster and Demo Sessions, SIGCOMM 2020, Association for Computing Machinery, pp. 70-72, 2020 Annual Conference of the ACM Special Interest Group on Data Communication on the Applications, Technologies, Architectures, and Protocols for Computer Communication, SIGCOMM 2020, Virtual, Online, United States, 8/10/20. https://doi.org/10.1145/3405837.3411396

Jog S, Liu Z, Franques A, Fernando V, Hassanieh H, Abadal S et al. Millimeter wave wireless network on chip using deep reinforcement learning. In Proceedings of the SIGCOMM 2020 Poster and Demo Sessions, SIGCOMM 2020. Association for Computing Machinery. 2020. p. 70-72. (Proceedings of the SIGCOMM 2020 Poster and Demo Sessions, SIGCOMM 2020). doi: 10.1145/3405837.3411396

@inproceedings{18f63b3a76fb42889100c4faa5adf64d,

title = "Millimeter wave wireless network on chip using deep reinforcement learning",

abstract = "Wireless Network-on-Chip (NoC) has emerged as a promising solution to scale chip multi-core processors to hundreds of cores. However, traditional medium access protocols fall short here since the traffic patterns on wireless NoCs tend to be very dynamic and can change drastically across different cores, different time intervals and different applications. In this work, we present NeuMAC, a unified approach that combines networking, architecture and AI to generate highly adaptive medium access protocols that can learn and optimize for the structure, correlations and statistics of the traffic patterns on the NoC. Our results show that NeuMAC can quickly adapt to NoC traffic to provide significant gains in terms of latency and overall execution time, improving the execution time by up to 1.69X - 3.74X.",

keywords = "Deep reinforcement learning, Millimeter wave, Wireless network-on-chip",

author = "Suraj Jog and Zikun Liu and Antonio Franques and Vimuth Fernando and Haitham Hassanieh and Sergi Abadal and Josep Torrellas",

note = "Publisher Copyright: {\textcopyright} 2020 Owner/Author.; 2020 Annual Conference of the ACM Special Interest Group on Data Communication on the Applications, Technologies, Architectures, and Protocols for Computer Communication, SIGCOMM 2020 ; Conference date: 10-08-2020 Through 14-08-2020",

year = "2020",

month = aug,

day = "10",

doi = "10.1145/3405837.3411396",

language = "English (US)",

series = "Proceedings of the SIGCOMM 2020 Poster and Demo Sessions, SIGCOMM 2020",

publisher = "Association for Computing Machinery",

pages = "70--72",

booktitle = "Proceedings of the SIGCOMM 2020 Poster and Demo Sessions, SIGCOMM 2020",

address = "United States",

}

TY - GEN

T1 - Millimeter wave wireless network on chip using deep reinforcement learning

AU - Jog, Suraj

AU - Liu, Zikun

AU - Franques, Antonio

AU - Fernando, Vimuth

AU - Hassanieh, Haitham

AU - Abadal, Sergi

AU - Torrellas, Josep

PY - 2020/8/10

Y1 - 2020/8/10

N2 - Wireless Network-on-Chip (NoC) has emerged as a promising solution to scale chip multi-core processors to hundreds of cores. However, traditional medium access protocols fall short here since the traffic patterns on wireless NoCs tend to be very dynamic and can change drastically across different cores, different time intervals and different applications. In this work, we present NeuMAC, a unified approach that combines networking, architecture and AI to generate highly adaptive medium access protocols that can learn and optimize for the structure, correlations and statistics of the traffic patterns on the NoC. Our results show that NeuMAC can quickly adapt to NoC traffic to provide significant gains in terms of latency and overall execution time, improving the execution time by up to 1.69X - 3.74X.

AB - Wireless Network-on-Chip (NoC) has emerged as a promising solution to scale chip multi-core processors to hundreds of cores. However, traditional medium access protocols fall short here since the traffic patterns on wireless NoCs tend to be very dynamic and can change drastically across different cores, different time intervals and different applications. In this work, we present NeuMAC, a unified approach that combines networking, architecture and AI to generate highly adaptive medium access protocols that can learn and optimize for the structure, correlations and statistics of the traffic patterns on the NoC. Our results show that NeuMAC can quickly adapt to NoC traffic to provide significant gains in terms of latency and overall execution time, improving the execution time by up to 1.69X - 3.74X.

KW - Deep reinforcement learning

KW - Millimeter wave

KW - Wireless network-on-chip

UR - http://www.scopus.com/inward/record.url?scp=85115674956&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85115674956&partnerID=8YFLogxK

U2 - 10.1145/3405837.3411396

DO - 10.1145/3405837.3411396

M3 - Conference contribution

AN - SCOPUS:85115674956

T3 - Proceedings of the SIGCOMM 2020 Poster and Demo Sessions, SIGCOMM 2020

SP - 70

EP - 72

BT - Proceedings of the SIGCOMM 2020 Poster and Demo Sessions, SIGCOMM 2020

PB - Association for Computing Machinery

T2 - 2020 Annual Conference of the ACM Special Interest Group on Data Communication on the Applications, Technologies, Architectures, and Protocols for Computer Communication, SIGCOMM 2020

Y2 - 10 August 2020 through 14 August 2020

ER -

Millimeter wave wireless network on chip using deep reinforcement learning

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this