Computer Laboratory

The Case For In-Network Computing On Demand

Authors: Yuta Tokusashi, Huynh Tu Dang, Fernando Pedone, Robert Soule and Noa Zilberman

Abstract

Programmable network hardware can run services traditionally deployed on servers, resulting in orders-of-magnitude improvements in performance. Yet, despite these performance improvements, network operators remain skeptical of in-network computing. The conventional wisdom is that the operational costs from increased power consumption outweigh any performance benefits. Unless in-network computing can justify its costs, it will be disregarded as yet another academic exercise.

Links

The paper
Repository
Experimental Results