Published In

SIGDOC '24: Proceedings of the 42nd ACM International Conference on Design of Communication

Document Type

Conference Proceeding

Publication Date

10-2024

Subjects

Applied computing

Abstract

When the Aurora supercomputer launches at Argonne National Laboratory it will operate at the exascale and be one of the fastest supercomputers in the world. We have been invited by Argonne to do field work to understand both the day-to-day processes that maintain supercomputing (e.g. user documentation, government reporting, user testing) and the sociotechnical national imaginaries [11], –in particular the increasingly tense global competition between the US and China in the supercomputing race–that shaped the development of Aurora. This article proposes our work-in-progress methodological approach that accounts for both higher-level imaginaries and the everyday practices of supercomputing. We also describe how our project plan is designed to answer multiple research questions: 1. What kind of new science will be possible when Aurora comes fully online? 2. What political, economic, technological, human and ideological resources has it required to build the supercomputer, bring it online, and to keep it running? 3. What does answering these questions tell us about the state of science in the US, the geopolitical race for computing power and the discursive and material infrastructures [5,19] required for success?

Rights

This work is licensed under a Creative Commons Attribution International 4.0 License. © 2024 Copyright held by the owner/author(s).

DOI

10.1145/3641237.3691653

Persistent Identifier

https://archives.pdx.edu/ds/psu/42698

Share

COinS