Performance Comparison for Scientific Computations on the Edge via Relative Performance

TL;DR

This paper introduces a measurement-based method called 'Relative performance analysis' to cluster algorithms into performance classes based on pairwise comparisons, aiding multi-metric algorithm selection in IoT scientific computations.

Contribution

It proposes a novel clustering methodology for algorithms based on pairwise performance comparisons, enabling multi-metric evaluation and selection.

Findings

Algorithms can be effectively clustered into performance classes.

The approach supports multi-metric algorithm selection.

Clustering simplifies choosing algorithms based on energy and other metrics.

Abstract

In a typical Internet-of-Things setting that involves scientific applications, a target computation can be evaluated in many different ways depending on the split of computations among various devices. On the one hand, different implementations (or algorithms)--equivalent from a mathematical perspective--might exhibit significant difference in terms of performance. On the other hand, some of the implementations are likely to show similar performance characteristics. In this paper, we focus on analyzing the performance of a given set of algorithms by clustering them into performance classes. To this end, we use a measurement-based approach to evaluate and score algorithms based on pair-wise comparisons; we refer to this approach as"Relative performance analysis". Each comparison yields one of three outcomes: one algorithm can be "better", "worse", or "equivalent" to another; those algorithms evaluating to have equivalent performance are merged into the same performance class. We show that our clustering methodology facilitates algorithm selection with respect to more than one metric; for instance, from the subset of equivalently fast algorithms, one could then select an algorithm that consumes the least energy on a certain device.