@inproceedings{8af1954361814e1ba51aca8ffc98a391,
title = "Multi-core acceleration of chemical kinetics for simulation and prediction",
abstract = "This work implements a computationally expensive chemical kinetics kernel from a large-scale community atmospheric model on three multi-core platforms: NVIDIA GPUs using CUDA, the Cell Broadband Engine, and Intel Quad-Core Xeon CPUs. A comparative performance analysis for each platform in double and single precision on coarse and fine grids is presented. Platform-specific design and optimization is discussed in a mechanism-agnostic way, permitting the optimization of many chemical mechanisms. The implementation of a three-stage Rosenbrock solver for SIMD architectures is discussed. When used as a template mechanism in the the Kinetic PreProcessor, the multi-core implementation enables the automatic optimization and porting of many chemical mechanisms on a variety of multi-core platforms. Speedups of 5.5x in single precision and 2.7x in double precision are observed when compared to eight Xeon cores. Compared to the serial implementation, the maximum observed speedup is 41.1x in single precision.",
keywords = "Atmospheric modeling, Cell broadband engine, Chemical kinetics, Kinetic pre-processor, Multi-core, NVIDIA CUDA, Open-MP",
author = "Linford, \{John C.\} and John Michalakes and Manish Vachharajani and Adrian Sandu",
year = "2009",
month = nov,
day = "14",
doi = "10.1145/1654059.1654067",
language = "English",
isbn = "9781605587448",
series = "Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis, SC '09",
publisher = "Association for Computing Machinery (ACM)",
booktitle = "Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis, SC '09",
address = "United States",
note = "International Conference on High Performance Computing Networking, Storage and Analysis, SC 2009 ; Conference date: 14-11-2009 Through 20-11-2009",
}