Toward Resilient Algorithms and Applications

TL;DR

This paper explores four approaches to designing resilient algorithms capable of maintaining performance despite hardware failures, addressing concerns about the sustainability of reliable digital machine models in high performance computing.

Contribution

It introduces four novel strategies for creating algorithms that are resilient to failures, aiming to improve robustness in high performance computing environments.

Findings

Proposes four approaches for resilient algorithm development

Addresses challenges of maintaining reliability in digital models

Contributes to sustainable high performance computing

Abstract

Over the past decade, the high performance computing community has become increasingly concerned that preserving the reliable, digital machine model will become too costly or infeasible. In this paper we discuss four approaches for developing new algorithms that are resilient to hard and soft failures.