The Community for Technology Leaders
Green Image
Issue No. 01 - January (2011 vol. 22)
ISSN: 1045-9219
pp: 119-131
John C. Linford , Virginia Polytechnic Institute and State University, Blacksburg
John Michalakes , National Center for Atmospheric Research, Boulder
Manish Vachharajani , University of Colorado, Boulder
Adrian Sandu , Virginia Polytechnic Institute and State University, Blacksburg
This work presents the Kinetics PreProcessor: Accelerated (KPPA), a general analysis and code generation tool that achieves significantly reduced time-to-solution for chemical kinetics kernels on three multicore platforms: NVIDIA GPUs using CUDA, the Cell Broadband Engine, and Intel Quad-Core Xeon CPUs. A comparative performance analysis of chemical kernels from WRF-Chem and the Community Multiscale Air Quality Model (CMAQ) is presented for each platform in double and single precision on coarse and fine grids. We introduce the multicore architecture parameterization that KPPA uses to generate a chemical kernel for these platforms and describe a code generation system that produces highly tuned platform-specific code. Compared to state-of-the-art serial implementations, speedups exceeding 25{\times} are regularly observed, with a maximum observed speedup of 41.1{\times} in single precision.
KPPA, multicore, NVIDIA CUDA, Cell Broadband Engine, OpenMP, chemical kinetics, atmospheric modeling, Kinetics PreProcessor, WRF-Chem, CMAQ.

J. C. Linford, A. Sandu, M. Vachharajani and J. Michalakes, "Automatic Generation of Multicore Chemical Kernels," in IEEE Transactions on Parallel & Distributed Systems, vol. 22, no. , pp. 119-131, 2010.
92 ms
(Ver 3.3 (11022016))