thumbnail

Advanced Research Computing

General Information Product 248
By: , , , and 
https://doi.org/10.3133/gip248

Links

 

Providing high performance computing (HPC) capabilities and expertise to scientists for the acceleration of science

Helping Scientists

User Support

  • • Training workshops

  • • Consultations

  • • Day-to-day technical

Computer Science Research

  • • Research and apply advances in technologies and computational methods to accomplish organizational goals

Collaborate and Contribute

  • • Cultivate partnerships

  • • Contribute to the broader high performance and scientific computing communities

Machine Access

  • • Provide researchers access to in-house, partner, and cloud HPC resources to U.S. Geological Survey (USGS) scientists

High-Performance Computing Systems

General Purpose HPC

  • • User friendly

  • • 18,544 central processing unit (CPU) cores

  • • 36,864 hyperthreads

  • • 55,296 CUDA cores

  • • About 590 teraflop per second (TFLOP/s)

Flagship System

  • • Large-scale models

  • • CPU only

  • • 232 nodes

  • • 9,280 CPU cores

  • • 18,560 hyperthreads

  • • 448 TFLOP/s

Exploratory System

  • • Machine learning (ML) and deep learning (DL) and analytics

  • • Integrated software

  • • 22 nodes

  • • 792 CPU cores

  • • 122,800 CUDA cores

  • • 15,360 tensor cores

HPC in the Cloud

  • • Custom environments

  • • On demand

  • • Scalable

  • • CPU and graphics processing unit (GPU)

  • • More than 680 software applications

Science Enabled by High-Performace Computing

More than 700 million compute hours since 2019

Advanced Research Computing is part of the USGS Science Analytics and Synthesis program, which serves under the USGS Core Science Systems Mission Area. Our goal is to provide and facilitate access to HPC capabilities and offer expertise to USGS scientists to accelerate and expand scientific discovery.

  • • We provide training, consulting, and access to HPC resources.

  • • We promote best practices through webinars, trainings, and other resources such as our online community of practice.

  • • We participate in USGS policy activities to align our work with bureau requirements.

  • • We keep up with the ever-changing supercomputing ecosystem by conducting research; the results of which can be applied to improving approaches to USGS HPC practices.

Training Opportunities

Introduction to HPC, R for HPC, Python for HPC, Deep Learning, and Advanced Scheduling. On-site training at science centers is available as requested.

HPC Supports Science in All USGS Mission Areas

  • • Core Science Systems—Land change monitoring, LANDFIRE

  • • Ecosystems—Environmental deoxyribonucleic acid (eDNA), habitat modeling, and invasive species detection using ML models

  • • Energy and Minerals—Analysis of electromagnetic data for identification of critical minerals and economic value of pollinators

  • • Natural Hazards—Lava flow, landslide modeling, wildfire, and active emergency response support

  • • Water Resources—Water availability assessments, flood mapping, and drought

For more information, email hpc@usgs.gov or visit https://www.usgs.gov/hpc

Disclaimers

Any use of trade, firm, or product names is for descriptive purposes only and does not imply endorsement by the U.S. Government.

Although this information product, for the most part, is in the public domain, it also may contain copyrighted materials as noted in the text. Permission to reproduce copyrighted items must be secured from the copyright owner.

Suggested Citation

Colasuonno, L.T., Uribe, R.D., Gordon, J., and Falgout, J.T., 2025, Advanced Research Computing (ver. 1.1, March 2025): U.S. Geological Survey General Information Product 248, https://doi.org/10.3133/gip248.

ISSN: 2332-354X (online)

ISSN: 2332-3531 (print)

Publication type Report
Publication Subtype USGS Numbered Series
Title Advanced Research Computing
Series title General Information Product
Series number 248
DOI 10.3133/gip248
Edition Version 1.0: February 12, 2025; Version 1.1: March 12, 2025
Publication Date February 12, 2025
Year Published 2025
Language English
Publisher U.S. Geological Survey
Publisher location Reston VA
Contributing office(s) Advanced Research Computing (ARC), Science Analytics and Synthesis
Description 2 p.
Online Only (Y/N) N
Additional publication details