• Skip to main content
  • Skip to after header navigation
  • Skip to site footer
ERN: Emerging Researchers National Conference in STEM

ERN: Emerging Researchers National Conference in STEM

  • About
    • About AAAS
    • About the NSF
    • About the Conference
    • Partners/Supporters
    • Project Team
  • Conference
  • Abstracts
    • Undergraduate Abstract Locator
    • Graduate Abstract Locator
    • Abstract Submission Process
    • Presentation Schedules
    • Abstract Submission Guidelines
    • Presentation Guidelines
  • Travel Awards
  • Resources
    • Award Winners
    • Code of Conduct-AAAS Meetings
    • Code of Conduct-ERN Conference
    • Conference Agenda
    • Conference Materials
    • Conference Program Books
    • ERN Photo Galleries
    • Events | Opportunities
    • Exhibitor Info
    • HBCU-UP/CREST PI/PD Meeting
    • In the News
    • NSF Harassment Policy
    • Plenary Session Videos
    • Professional Development
    • Science Careers Handbook
    • Additional Resources
    • Archives
  • Engage
    • Webinars
    • ERN 10-Year Anniversary Videos
    • Plenary Session Videos
  • Contact Us
  • Login

Analysis of Mixed Precision Iterative Refinement Method

Graduate #46
Discipline: Computer Sciences and Information Management
Subcategory: Computer Science & Information Systems

Janica Gordon - Southern University and A&M College
Co-Author(s): Daniel Osei-Kuffuor, Lawrence Livermore National Lab; Jeffrey Hittinger, Lawrence Livermore National Lab



Assume that there is a technique that would accelerate a linear solver and reduce the energy consumption by cutting the overall computation time. The performance of 32-bit operations is often at least twice as fast as the performance of 64-bit operations. By using a combination of 32-bit and 64-bit floating point arithmetic, the performance of many linear algebra algorithms can be significantly enhanced while maintaining the 64-bit accuracy of the resulting solution. A code was designed and implemented for the mixed precision iterative refinement algorithm using the LU factorization with the use of the single precision and double precision. Single precision, double precision, and mixed precision iterative refinement were compared and analyzed.

Not Submitted

Funder Acknowledgement(s): Mr. Daniel Osei-Kuffuor, Lawrence Livermore National Laboratory Jeffrey Kittinger, Lawrence Livermore National Laboratory CCMS, Lawrence Livermore National Laboratory Southern University and A&M College

Faculty Advisor: Daniel Osei-Kuffuor, oseikuffuor1@llnl.gov

Role: I did all of the research in the project with the help of my mentor.

Sidebar

Abstract Locators

  • Undergraduate Abstract Locator
  • Graduate Abstract Locator

This material is based upon work supported by the National Science Foundation (NSF) under Grant No. DUE-1930047. Any opinions, findings, interpretations, conclusions or recommendations expressed in this material are those of its authors and do not represent the views of the AAAS Board of Directors, the Council of AAAS, AAAS’ membership or the National Science Foundation.

AAAS

1200 New York Ave, NW
Washington,DC 20005
202-326-6400
Contact Us
About Us

  • LinkedIn
  • Facebook
  • Instagram
  • Twitter
  • YouTube

The World’s Largest General Scientific Society

Useful Links

  • Membership
  • Careers at AAAS
  • Privacy Policy
  • Terms of Use

Focus Areas

  • Science Education
  • Science Diplomacy
  • Public Engagement
  • Careers in STEM

Focus Areas

  • Shaping Science Policy
  • Advocacy for Evidence
  • R&D Budget Analysis
  • Human Rights, Ethics & Law

© 2023 American Association for the Advancement of Science