An Analysis of HPC and Edge Architectures in the Cloud

TL;DR

This paper analyzes 396 real-world cloud architectures on AWS to understand the design, prevalence, and trends of HPC and edge components, providing insights into current industry practices.

Contribution

It offers a detailed characterization of HPC and edge architectures in the cloud, highlighting prevalent patterns and service usage from a large dataset.

Findings

HPC and edge components are increasingly integrated in cloud architectures.

AWS services usage varies significantly across architectures.

Architectural complexity correlates with the inclusion of machine learning services.

Abstract

We analyze a recently published dataset of 396 real-world cloud architectures deployed on AWS, from companies belonging to a wide range of industries. From this dataset, we identify those architectures that contain HPC or edge components and characterize their designs. Specifically, we investigate the prevalence and interplay of AWS services within these architectures, examine the types of storage systems employed, assess architectural complexity and the use of machine learning services, discuss the implications of our findings and how representative these results are of HPC and edge architectures in the cloud. This characterization provides valuable insights into current industry practices and trends in building robust and scalable HPC and edge solutions in the cloud continuum, and can be valuable for those seeking to better understand how these architectures are being built and to guide new research.