Home  |  Publications  |  Google Scholar  |  GitHub  |  Project

Distributed In-network Computing

In-network computing offloads server-based applications to programmable devices. However, network devices are very resource-constrained compared to servers. This project aims to scale in-network computing algorithms further via distributed deployment. This project can also be used as an extension of the in-network ML project.

Research has focused on enabling on-device functionality, with limited consideration to distributed in-network computing. This paper explores the applicability of distributed computing to in-network computing and presents DINC, a framework enabling distributed in-network computing, generating deployment strategies, overcoming resource constraints and providing functionality guarantees across a network.

We introduce MUTA; a novel in-network multi-task learning solution. MUTA enables executing multiple inference tasks concurrently in the data-plane, without exhausting available resources.

We introduce MUTA, a novel in-network multi-task learning framework that enables concurrent inference of multiple tasks in the data-plane, without exhausting available resources. MUTA enhances scalability by supporting distributed deployment, where different layers of a multi-task model can be offloaded across multiple switches.