The Application of Cloud Computing to Astronomy: A Study of Cost and Performance

TL;DR

This study compares cloud computing and traditional high-performance computing for scientific data processing, demonstrating that cloud services like Amazon EC2 can offer better performance and value for certain applications, especially processor- and memory-bound tasks.

Contribution

It provides empirical evidence on the performance and cost benefits of using cloud computing for scientific workflows, highlighting its suitability for generating large-scale astronomical data products.

Findings

Cloud offers better performance for processor- and memory-limited applications.

Cloud is less suitable for I/O-bound applications.

An example demonstrates cloud's effectiveness in generating astronomical data products.

Abstract

Cloud computing is a powerful new technology that is widely used in the business world. Recently, we have been investigating the benefits it offers to scientific computing. We have used three workflow applications to compare the performance of processing data on the Amazon EC2 cloud with the performance on the Abe high-performance cluster at the National Center for Supercomputing Applications (NCSA). We show that the Amazon EC2 cloud offers better performance and value for processor- and memory-limited applications than for I/O-bound applications. We provide an example of how the cloud is well suited to the generation of a science product: an atlas of periodograms for the 210,000 light curves released by the NASA Kepler Mission. This atlas will support the identification of periodic signals, including those due to transiting exoplanets, in the Kepler data sets.