Publications

Results 76–100 of 214

Search results

Jump to search filters

HOMMEXX 1.0: A performance-portable atmospheric dynamical core for the Energy Exascale Earth System Model

Geoscientific Model Development

Bertagna, Luca; Deakin, Michael; Guba, Oksana; Sunderland, Daniel; Bradley, Andrew M.; Tezaur, Irina K.; Taylor, Mark A.; Salinger, Andrew G.

We present an architecture-portable and performant implementation of the atmospheric dynamical core (High-Order Methods Modeling Environment, HOMME) of the Energy Exascale Earth System Model (E3SM). The original Fortran implementation is highly performant and scalable on conventional architectures using the Message Passing Interface (MPI) and Open MultiProcessor (OpenMP) programming models. We rewrite the model in C++ and use the Kokkos library to express on-node parallelism in a largely architecture-independent implementation. Kokkos provides an abstraction of a compute node or device, layout-polymorphic multidimensional arrays, and parallel execution constructs. The new implementation achieves the same or better performance on conventional multicore computers and is portable to GPUs. We present performance data for the original and new implementations on multiple platforms, on up to 5400 compute nodes, and study several aspects of the single-and multi-node performance characteristics of the new implementation on conventional CPU (e.g., Intel Xeon), many core CPU (e.g., Intel Xeon Phi Knights Landing), and Nvidia V100 GPU.

More Details

Toward performance portability of the Albany finite element analysis code using the Kokkos library

International Journal of High Performance Computing Applications

Demeshko, Irina; Watkins, Jerry E.; Tezaur, Irina K.; Guba, Oksana; Spotz, William S.; Salinger, Andrew G.; Pawlowski, Roger; Heroux, Michael A.

Performance portability on heterogeneous high-performance computing (HPC) systems is a major challenge faced today by code developers: parallel code needs to be executed correctly as well as with high performance on machines with different architectures, operating systems, and software libraries. The finite element method (FEM) is a popular and flexible method for discretizing partial differential equations arising in a wide variety of scientific, engineering, and industrial applications that require HPC. This article presents some preliminary results pertaining to our development of a performance portable implementation of the FEM-based Albany code. Performance portability is achieved using the Kokkos library. We present performance results for the Aeras global atmosphere dynamical core module in Albany. Numerical experiments show that our single code implementation gives reasonable performance across three multicore/many-core architectures: NVIDIA General Processing Units (GPU’s), Intel Xeon Phis, and multicore CPUs.

More Details

MPAS-Albany Land Ice (MALI): A variable-resolution ice sheet model for Earth system modeling using Voronoi grids

Geoscientific Model Development

Hoffman, Matthew J.; Perego, Mauro; Price, Stephen F.; Lipscomb, William H.; Zhang, Tong; Jacobsen, Douglas; Tezaur, Irina K.; Salinger, Andrew G.; Tuminaro, Raymond S.; Bertagna, Luca

We introduce MPAS-Albany Land Ice (MALI) v6.0, a new variable-resolution land ice model that uses unstructured Voronoi grids on a plane or sphere. MALI is built using the Model for Prediction Across Scales (MPAS) framework for developing variable-resolution Earth system model components and the Albany multi-physics code base for the solution of coupled systems of partial differential equations, which itself makes use of Trilinos solver libraries. MALI includes a three-dimensional first-order momentum balance solver (Blatter-Pattyn) by linking to the Albany-LI ice sheet velocity solver and an explicit shallow ice velocity solver. The evolution of ice geometry and tracers is handled through an explicit first-order horizontal advection scheme with vertical remapping. The evolution of ice temperature is treated using operator splitting of vertical diffusion and horizontal advection and can be configured to use either a temperature or enthalpy formulation. MALI includes a mass-conserving subglacial hydrology model that supports distributed and/or channelized drainage and can optionally be coupled to ice dynamics. Options for calving include eigencalving, which assumes that the calving rate is proportional to extensional strain rates. MALI is evaluated against commonly used exact solutions and community benchmark experiments and shows the expected accuracy. Results for the MISMIP3d benchmark experiments with MALI's Blatter-Pattyn solver fall between published results from Stokes and L1L2 models as expected. We use the model to simulate a semi-realistic Antarctic ice sheet problem following the initMIP protocol and using 2 km resolution in marine ice sheet regions. MALI is the glacier component of the Energy Exascale Earth System Model (E3SM) version 1, and we describe current and planned coupling to other E3SM components.

.

More Details

ASC ATDM Level 2 Milestone #6358: Assess Status of Next Generation Components and Physics Models in EMPIRE

Bettencourt, Matthew T.; Kramer, Richard M.J.; Cartwright, Keith L.; Phillips, Edward; Ober, Curtis C.; Pawlowski, Roger; Swan, Matthew S.; Tezaur, Irina K.; Phipps, Eric T.; Conde, Sidafa; Cyr, Eric C.; Ulmer, Craig; Kordenbrock, Todd; Levy, Scott; Templet, Gary J.; Hu, Jonathan J.; Lin, Paul T.; Glusa, Christian; Siefert, Christopher; Glass, Micheal W.

This report documents the outcome from the ASC ATDM Level 2 Milestone 6358: Assess Status of Next Generation Components and Physics Models in EMPIRE. This Milestone is an assessment of the EMPIRE (ElectroMagnetic Plasma In Realistic Environments) application and three software components. The assessment focuses on the electromagnetic and electrostatic particle-in-cell solutions for EMPIRE and its associated solver, time integration, and checkpoint-restart components. This information provides a clear understanding of the current status of the EMPIRE application and will help to guide future work in FY19 in order to ready the application for the ASC ATDM L1 Milestone in FY20. It is clear from this assessment that performance of the linear solver will have to be a focus in FY19.

More Details
Results 76–100 of 214
Results 76–100 of 214
Top