Hierarchical Coded Matrix Multiplication

TL;DR

This paper introduces hierarchical coded computing methods that leverage all nodes, including slow stragglers, to improve distributed matrix multiplication efficiency, achieving significant reductions in expected completion time.

Contribution

It develops a unified framework and three new hierarchical coded computing techniques that utilize partial work from all nodes, enhancing robustness and efficiency in distributed systems.

Findings

Achieves up to 66% reduction in expected finishing time in theoretical models.

Realizes 27% improvement in Amazon EC2 experiments with simulated stragglers.

Unifies existing methods within a cuboid partitioning framework.

Abstract

In distributed computing systems slow working nodes, known as stragglers, can greatly extend finishing times. Coded computing is a technique that enables straggler-resistant computation. Most coded computing techniques presented to date provide robustness by ensuring that the time to finish depends only on a set of the fastest nodes. However, while stragglers do compute less work than non-stragglers, in real-world commercial cloud computing systems (e.g., Amazon's Elastic Compute Cloud (EC2)) the distinction is often a soft one. In this paper, we develop hierarchical coded computing that exploits the work completed by all nodes, both fast and slow, automatically integrating the potential contribution of each. We first present a conceptual framework to represent the division of work amongst nodes in coded matrix multiplication as a cuboid partitioning problem. This framework allows us to unify existing methods and motivates new techniques. We then develop three methods of hierarchical coded computing that we term bit-interleaved coded computation (BICC), multilevel coded computation (MLCC), and hybrid hierarchical coded computation (HHCC). In this paradigm, each worker is tasked with completing a sequence (a hierarchy) of ordered subtasks. The sequence of subtasks, and the complexity of each, is designed so that partial work completed by stragglers can be used, rather than ignored. We note that our methods can be used in conjunction with any coded computing method. We illustrate this by showing how we can use our methods to accelerate all previously developed coded computing techniques by enabling them to exploit stragglers. Under a widely studied statistical model of completion time, our approach realizes a $66\%$ improvement in the expected finishing time. On Amazon EC2, the gain was $27\%$ when stragglers are simulated.