This tutorial will introduce the fundamental whys and hows of data management for research computing, with an emphasis on making effective use of TACC’s diverse storage resources to ensure the usability and reusability of your data. Basic topics will be covered in detail, including the different types of file systems available in typical high-performance computing environments, the different types of data used and generated in typical research computing workflows, and preparation of data to ensure that research outputs are shareable and reusable.

Newer data analysis-focused architectures, such as Wrangler, will be briefly introduced and their differences from common high-performance computing systems described. Advanced topics to be introduced will include use of databases in research computing, concepts of metadata, resources for web-based sharing of data, and permanent address systems suitable for referencing your data in publications.

We will also briefly describe the XSEDE data resource ecosystem and provide some introductory information to assist XSEDE users in identifying and making use of the national-scale cyberinfrastructure for research data management.