High Performance Computing Facility Operational Assessment 2022: Oak Ridge Leadership Computing Facility
Abstract
The Oak Ridge Leadership Computing Facility (OLCF) was established to accelerate scientific discovery by providing world-leading computational performance and advanced data infrastructure. As a US Department of Energy (DOE) Office of Science user facility, the OLCF has managed the successful deployment and operation of a succession of leadership-class resources dedicated to open science. In addition to these resources, the OLCF staff continually strive to develop innovative processes and technologies, improve security, and empower users through allocation management and comprehensive user support and training. These efforts support the advancement of science by the OLCF users and benefit high-performance computing (HPC) facilities around the world. In calendar year (CY) 2022, the OLCF supported 1,681 users and 570 projects and exceeded all targets for user satisfaction. The facility received an average satisfaction score of 4.6 out of 5 on the annual user survey, and 96% of respondents reported a high satisfaction rate with the OLCF overall. Of the 3,212 user tickets submitted in CY 2022, OLCF staff resolved 97% within 3 business days. The facility also introduced several new services for users this year, including weekly virtual office hours with subject matter experts from ORNL and vendor partners; new views in MyOLCF that allow users to analyze allocation and compute usage for a project; the ability to build and run containers on Summit; and improved data visualization support and training resources.
Related Papers
- → Negatively buoyant CO2‐hydrate composite for ocean carbon sequestration(2003)31 cited
- → Electrostatic spraying of nonconductive fluids into conductive fluids(1994)30 cited
- → 27. Viability of an Airborne Electromagnetic System for Mapping of Shallow Buried Metals(2005)9 cited
- → Effect of Processing Parameters on Densification and Mechanical Properties of Gas-Pressure Sintered Silicon Nitride(2008)4 cited
- → Local Crystallography for Quantitative Analysis of Atomically Resolved Images(2016)