Computation Offloading Decisions for Reducing Completion Time

TL;DR

This paper investigates when computation offloading can effectively reduce task completion time by deriving a key inequality relating system parameters and computational intensity, guiding offloading decisions.

Contribution

It introduces a novel inequality linking system parameters and computational intensity, aiding in identifying when offloading improves performance.

Findings

Derived an inequality (Eq. 4) relating system parameters to computational intensity.

Provided a method to determine which computations benefit from offloading.

Discussed system requirements for effective computation offloading.

Abstract

We analyze the conditions in which offloading computation reduces completion time. We extend the existing literature by deriving an inequality (Eq. 4) that relates computation offloading system parameters to the bits per instruction ratio of a computational job. This ratio is the inverse of the arithmetic intensity. We then discuss how this inequality can be used to determine the computations that can benefit from offloading as well as the computation offloading systems required to make offloading beneficial for particular computations.