# STELLA: a domain-specific tool for structured grid methods in weather and climate models

Year: 2015, Pages: 1-12

DOI Bookmark: [10.1145/2807591.2807627](https://doi.ieeecomputersociety.org/10.1145/2807591.2807627)

#### Authors

[Tobias Gysi](/content/csdl/search/default?type=author&givenName=Tobias&surname=Gysi/index.html)

[Carlos Osuna](/content/csdl/search/default?type=author&givenName=Carlos&surname=Osuna/index.html)

[Oliver Fuhrer](/content/csdl/search/default?type=author&givenName=Oliver&surname=Fuhrer/index.html)

[Mauro Bianco](/content/csdl/search/default?type=author&givenName=Mauro&surname=Bianco/index.html)

[Thomas C. Schulthess](/content/csdl/search/default?type=author&givenName=Thomas%20C.&surname=Schulthess/index.html)

#### Abstract

Many high-performance computing applications solving partial differential equations (PDEs) can be attributed to the class of kernels using stencils on structured grids. Due to the disparity between floating point operation throughput and main memory bandwidth these codes typically achieve only a low fraction of peak performance. Unfortunately, stencil computation optimization techniques are often hardware dependent and lead to a significant increase in code complexity. We present a domain-specific tool, STELLA, which eases the burden of the application developer by separating the architecture dependent implementation strategy from the user-code and is targeted at multi- and manycore processors. On the example of a numerical weather prediction and regional climate model (COSMO) we demonstrate the usefulness of STELLA for a real-world production code. The dynamical core based on STELLA achieves a speedup factor of 1.8× (CPU) and 5.8× (GPU) with respect to the legacy code while reducing the complexity of the user code.

#### Similar Articles

- [Cross-Platform OpenCL Code and Performance Portability Investigated with a Climate and Weather Physics Model](/content/csdl/proceedings-article/icppw/2012/4795a126/12OmNAkWvFy/index.html)

- [DG-kernel: A Climate Benchmark on Accelerated and Conventional Architectures](/content/csdl/proceedings-article/xsw/2013/3691a051/12OmNB1eJBm/index.html)

- [GPU-enabled efficient executions of radiation calculations in climate modeling](/content/csdl/proceedings-article/hipc/2013/06799141/12OmNBaT628/index.html)

- [Application Centric Energy-Efficiency Study of Distributed Multi-Core and Hybrid CPU-GPU Systems](/content/csdl/proceedings-article/sc/2014/5500a819/12OmNBtl1tB/index.html)

- [Optimizing an MPI weather forecasting model via processor virtualization](/content/csdl/proceedings-article/hipc/2010/05713171/12OmNwp74qR/index.html)

- [Directive-Based Parallelization of the NIM Weather Model for GPUs](/content/csdl/proceedings-article/waccpd/2014/6753a055/12OmNy3AgzA/index.html)

- [Refactoring and Optimizing the Community Atmosphere Model (CAM) on the Sunway TaihuLight Supercomputer](/content/csdl/proceedings-article/sc/2016/8815a969/12OmNyrIav0/index.html)

- [Shared Memory and GPU Parallelization of an Operational Atmospheric Transport and Dispersion Application](/content/csdl/proceedings-article/ipdpsw/2019/555500a729/1c2bDdx84TK/index.html)

- [Accelerating Atmospheric Chemical Kinetics for Climate Simulations](/content/csdl/journal/td/2019/11/08723098/1dZjA0savzq/index.html)

- [ESiWACE: On European Infrastructure Efforts for Weather and Climate Modeling at Exascale](/content/csdl/proceedings-article/escience/2019/245100a498/1ike1oTsoZa/index.html)