Translating the Grid: How a Translational Approach Shaped the Development of Grid Computing

TL;DR

This paper advocates for a translational approach in computer science, illustrating how it shaped the development of grid computing and offering lessons for future translational initiatives.

Contribution

It introduces the concept of translational computer science and analyzes how this approach influenced the development of grid computing and the Globus Toolkit.

Findings

Translational framing clarifies the development of grid computing.

A translational approach accelerates technology adoption.

Lessons learned can guide future translational computer science efforts.

Abstract

A growing gap between progress in biological knowledge and improved health outcomes inspired the new discipline of translational medicine, in which the application of new knowledge is an explicit part of a research plan. Abramson and Parashar argue that a similar gap between complex computational technologies and ever-more-challenging applications demands an analogous discipline of translational computer science, in which the deliberate movement of research results into large-scale practice becomes a central research focus rather than an afterthought. We revisit from this perspective the development and application of grid computing from the mid-1990s onwards, and find that a translational framing is useful for understanding the technology's development and impact. We discuss how the development of grid computing infrastructure, and the Globus Toolkit, in particular, benefited from a translational approach. We identify lessons learned that can be applied to other translational computer science initiatives.