Taking Lessons Learned from a Proxy Application to a Full Application for SNAP and PARTISN

Journal Article · 09 June 2017 · Procedia Computer Science

DOI: https://doi.org/10.1016/j.procs.2017.05.243 · OSTI ID:1418763

Womeldorff, Geoffrey Alan  ^[1]; Payne, Joshua Estes ^[1]; Bergen, Benjamin Karl ^[1]

---

1. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)

SNAP is a proxy application which simulates the computational motion of a neutral particle transport code, PARTISN. Here in this work, we have adapted parts of SNAP separately; we have re-implemented the iterative shell of SNAP in the task-model runtime Legion, showing an improvement to the original schedule, and we have created multiple Kokkos implementations of the computational kernel of SNAP, displaying similar performance to the native Fortran. We then translate our Kokkos experiments in SNAP to PARTISN, necessitating engineering development, regression testing, and further thought.

• Research Organization: Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
• Sponsoring Organization: USDOE
• Grant/Contract Number: AC52-06NA25396
• OSTI ID: 1418763
• Report Number(s): LA-UR-16-29442
• Journal Information: Procedia Computer Science, Vol. 108; Conference: International Conference on Computational Science 2017, Zurich (Switzerland), 12-14 Jun 2017; ISSN 1877-0509
• Publisher: ElsevierCopyright Statement
• Country of Publication: United States
• Language: English