Publications

Results 1–25 of 46

Search results

Jump to search filters

Simulation of Low-Rm physics in complex geometries on GPUs with LGR

Zwick, David Z.; Ibanez-Granados, Daniel A.

Efficient modeling of low magnetic Reynolds number (low-Rm) magnetohydrodynamics is often challenging and requires the implementation of innovative techniques to avoid key barriers experienced with prior approaches. We detail a new paradigm for first-principles simulation of the solution to the low-Rm governing equations in complex geometries. As a result of a number of innovative numerical advances, the next-generation GPU (graphics processing unit) accelerated physics code LGR has been successfully applied to the modeling of exploding wire problems.

More Details
TYPE SAND Report YEAR 2021
DOIOSTI

Kokkos 3: Programming Model Extensions for the Exascale Era

IEEE Transactions on Parallel and Distributed Systems

Trott, Christian R.; Lebrun-Grandie, Damien; Arndt, Daniel; Ciesko, Jan; Dang, Vinh Q.; Ellingwood, Nathan D.; Gayatri, Rahulkumar; Harvey, Evan C.; Hollman, Daisy S.; Ibanez-Granados, Daniel A.; Liber, Nevin; Madsen, Jonathan; Miles, Jeff S.; Poliakoff, David Z.; Powell, Amy J.; Rajamanickam, Sivasankaran R.; Simberg, Mikael; Sunderland, Dan; Turcksin, Bruno; Wilke, Jeremiah

As the push towards exascale hardware has increased the diversity of system architectures, performance portability has become a critical aspect for scientific software. We describe the Kokkos Performance Portable Programming Model that allows developers to write single source applications for diverse high performance computing architectures. Kokkos provides key abstractions for both the compute and memory hierarchy of modern hardware. Here, we describe the novel abstractions that have been added to Kokkos recently such as hierarchical parallelism, containers, task graphs, and arbitrary-sized atomic operations. We demonstrate the performance of these new features with reproducible benchmarks on CPUs and GPUs.

More Details
TYPE Journal Article YEAR 2021
DOIOSTI

An error estimation driven adaptive tetrahedral workflow for full engineering models

Foulk III, James W.; Granzow, Brian N.; Mota, Alejandro M.; Ibanez-Granados, Daniel A.

Tetrahedral finite element workflows have the potential to drastically reduce time to solution for computational solid mechanics simulations when compared to traditional hexahedral finite element analogues. A recently developed, higher-order composite tetrahedral element has shown promise in the space of incompressible computational plasticity. Mesh adaptivity has the potential to increase solution accuracy and increase solution robustness. In this work, we demonstrate an initial strategy to perform conformal mesh adaptivity for this higher-order composite tetrahedral element using well-established mesh modification operations for linear tetrahedra. We propose potential extensions to improve this initial strategy in terms of robustness and accuracy.

More Details
TYPE SAND Report YEAR 2019
DOIOSTI

STPR 04 Milestone 6 Report

Trott, Christian R.; Ibanez-Granados, Daniel A.; Ellingwood, Nathan D.; Bova, S.W.; Labreche, Duane A.

This report documents the completion of milestone STPRO4-6 Kokkos Support for ASC applications and libraries. The team provided consultation and support for numerous ASC code projects including Sandias SPARC, EMPIRE, Aria, GEMMA, Alexa, Trilinos, LAMMPS and nimbleSM. Over the year more than 350 Kokkos github issues were resolved, with over 220 requiring fixes and enhancements to the code base. Resolving these requests, with many of them issued by ASC code teams, provided applications with the necessary capabilities in Kokkos to be successful.

More Details
TYPE Other Report YEAR 2018
DOIOSTI
Results 1–25 of 46
Results 1–25 of 46