Skip to content
EMiT: Emerging Technology Conference
  •  Themes
  •  Organisers
  •  EMiT History
    • EMiT 2019 (Huddersfield, UK)
      • EMiT 2019: Programme & Presentations
      • EMiT 2019: Image Gallery
      • EMiT 2019: Organising Committee
    • EMiT@CIUK 2017 (Manchester, UK)
      • EMiT@CIUK 2017: Programme & Presentations
      • EMiT@CIUK 2017: Gallery
    • EMiT 2016 (Barcelona, Spain)
      • EMiT 2016: Programme & Presentations
      • EMiT 2016: Gallery
      • EMiT 2016: Organising Committee
    • EMiT 2015 (Manchester, UK)
      • EMiT 2015: Programme & Presentations
      • EMiT 2015: Gallery
      • EMiT 2015: Organising Committee
    • EMiT 2014 (Manchester, UK)
      • EMiT 2014: Programme & Presentations
      • EMiT 2014: Organising Committee
  •  Contact
Generic selectors
Exact matches only
Search in title
Search in content

Are you getting the wrong answer, but fast? – Challenges for reproducible research in HPC

Invited Keynote

Prof. Lorena Barba, George Washington University, USA

On undertaking a full replication study of a previous publication by our own research group, we learned some new lessons about reproducible computational research. The previous study used an in-house code to solve the Navier-Stokes equations for flow around an object, using GPU hardware. As is common in CFD applications, we rely on an external library for solving linear systems of equations, in this case, the NVIDIA Cusp library. We later did a code re-write of the CFD solver in a distributed parallel setting, on CPU hardware. This version uses the PETSc library for solving linear systems of equations. In addition, we used two open-source CFD libraries: OpenFOAM and IBAMR (from New York University). Apart from the many things that can go wrong with discretization meshes and boundary conditions, we found that simply using a different version of an external library can lead to different results, for example. In view of this exercise, we tightened our reproducibility practices even more. Open data and code are the  minimum requirement; we also require a fully automated workflow, systematic records of dependencies, environment and system, and only scripted visualizations (no GUI manipulation). We must also raise awareness of numerical non-reproducibility of parallel software and include this topic as part of the training of HPC researchers.

Signup to EMiT Mailing List

Copyright (c) The EMiT: Emerging Technology Conference
Theme by Colorlib Powered by WordPress
Share