Accelerating Computational Fluid Dynamics on the IBM Blue Gene/P Supercomputer

• Pascal Vezolle University of Southern California
• Jerry Heyman University of Southern California
• Bruce D'Amora IBM T.J. Watson Research Center
• Gordon Braudaway IBM T.J. Watson Research Center
• Karen Magerlein IBM T.J. Watson Research Center
• John Magerlein IBM T.J. Watson Research Center
• Yvan Fournier Electricité de France, R&D

Resumo

Computational Fluid Dynamics (CFD) is an increasingly important application domain for computational scientists. In this paper, we propose and analyze optimizations necessary to run CFD simulations consisting of multi-billion-cell mesh models on large processor systems. Our investigation leverages the general industrial Navier-Stokes open-source CFD application, Code_Saturne, developed by Electricité de France (EDF). Our work considers emerging processor features such as many-core, Symmetric Multi-threading (SMT), Single Instruction Multiple Data (SIMD), Transactional Memory, and Thread Level Speculation. Initially, we have targeted per-node performance improvements by reconstructing the code and data layouts to optimally use multiple threads. We present a general loop transformation that will enable the compiler to generate OpenMP threads effectively with minimal impact to overall code structure. A renumbering scheme for mesh faces is proposed to enhance thread-level parallelism and generally improve data locality. Performance results on IBM Blue Gene/P supercomputer and Intel Xeon Westmere cluster are included.

Palavras-chave: Instruction sets, Computational fluid dynamics, Sparse matrices, Bandwidth, Parallel processing, Computational modeling, Memory management