Imperial College London
Portrait Picture

Professor Hamed Haddadi

Faculty of Engineering, Department of Computing

Professor of Human-Centred Systems
 
 
 
//

Contact

 

h.haddadi Website

 
 
//

Location

 

2Translation & Innovation Hub BuildingWhite City Campus

//

Summary

 

Publications

Citation

BibTex format

@unpublished{Siracusano:2020,
author = {Siracusano, G and Galea, S and Sanvito, D and Malekzadeh, M and Haddadi, H and Antichi, G and Bifulco, R},
publisher = {arXiv},
title = {Running neural networks on the NIC},
url = {http://arxiv.org/abs/2009.02353v1},
year = {2020}
}
Download

RIS format (EndNote, RefMan)

TY  - UNPB
AB  - In this paper we show that the data plane of commodity programmable (NetworkInterface Cards) NICs can run neural network inference tasks required by packetmonitoring applications, with low overhead. This is particularly important asthe data transfer costs to the host system and dedicated machine learningaccelerators, e.g., GPUs, can be more expensive than the processing taskitself. We design and implement our system -- N3IC -- on two different NICs andwe show that it can greatly benefit three different network monitoring usecases that require machine learning inference as first-class-primitive. N3ICcan perform inference for millions of network flows per second, whileforwarding traffic at 40Gb/s. Compared to an equivalent solution implemented ona general purpose CPU, N3IC can provide 100x lower processing latency, with1.5x increase in throughput.
AU  - Siracusano,G
AU  - Galea,S
AU  - Sanvito,D
AU  - Malekzadeh,M
AU  - Haddadi,H
AU  - Antichi,G
AU  - Bifulco,R
PB  - arXiv
PY  - 2020///
TI  - Running neural networks on the NIC
UR  - http://arxiv.org/abs/2009.02353v1
UR  - http://hdl.handle.net/10044/1/82882
ER  -
Download