In-Network Computation is a Dumb Idea Whose Time Has Come

Amedeo Sapio, Ibrahim Abdelaziz, Abdulla Aldilaijan, Marco Canini, Panos Kalnis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

57 Scopus citations

Abstract

Programmable data plane hardware creates new opportunities for infusing intelligence into the network. This raises a fundamental question: what kinds of computation should be delegated to the network? In this paper, we discuss the opportunities and challenges for co-designing data center distributed systems with their network layer. We believe that the time has finally come for offloading part of their computation to execute in-network. However, in-network computation tasks must be judiciously crafted to match the limitations of the network machine architecture of programmable devices. With the help of our experiments on machine learning and graph analytics workloads, we identify that aggregation functions raise opportunities to exploit the limited computation power of networking hardware to lessen network congestion and improve the overall application performance. Moreover, as a proof-of-concept, we propose DAIET, a system that performs in-network data aggregation. Experimental results with an initial prototype show a large data reduction ratio (86.9%-89.3%) and a similar decrease in the workers' computation time.
Original languageEnglish (US)
Title of host publicationProceedings of the 16th ACM Workshop on Hot Topics in Networks - HotNets-XVI
PublisherAssociation for Computing Machinery (ACM)
Pages150-156
Number of pages7
ISBN (Print)9781450355698
DOIs
StatePublished - Nov 27 2017

Fingerprint Dive into the research topics of 'In-Network Computation is a Dumb Idea Whose Time Has Come'. Together they form a unique fingerprint.

Cite this