Sharing Incentives and Fair Division for Multiprocessors

Abstract

The trend in datacenter computing is toward large, shared hardware platforms, which poses two challenges to architects: sharing fairly and sharing multiple resources. Drawing on economic game theory, the authors rethink fairness in computer architecture and propose Resource Elasticity Fairness to find fair allocations that ensure sharing incentives, envy-freeness, Pareto efficiency, and strategy proofness in large systems.