Astrophysical Supercomputing with GPUs: Critical Decisions for Early Adopters*

Abstract General-purpose computing on graphics processing units (GPGPU) is dramatically changing the landscape of high performance computing in astronomy. In this paper, we identify and investigate several key decision areas, with a goal of simplifying the early adoption of GPGPU in astronomy. We consider the merits of OpenCL as an open standard in order to reduce risks associated with coding in a native, vendor-specific programming environment, and present a GPU programming philosophy based on using brute force solutions. We assert that effective use of new GPU-based supercomputing facilities will require a change in approach from astronomers. This will likely include improved programming training, an increased need for software development best practice through the use of profiling and related optimisation tools, and a greater reliance on third-party code libraries. As with any new technology, those willing to take the risks and make the investment of time and effort to become early adopters of GPGPU in astronomy, stand to reap great benefits.

[1]  John A. Nelder,et al.  A Simplex Method for Function Minimization , 1965, Comput. J..

[2]  Donald S. Fussell,et al.  On the power of the frame buffer , 1988, TOGS.

[3]  S. Aarseth.  From NBODY1 to NBODY6: The Growth of an Industry , 1999 .

[4]  H. Liu,et al.  Conference on Measurement and modeling of computer systems , 2001 .

[5]  Suresh Venkatasubramanian.  The Graphics Card as a Streaming Computer , 2003, ArXiv.

[6]  Roberto Scopigno,et al.  Computer Graphics forum , 2003, Computer Graphics Forum.

[7]  Stanimire Tomov,et al.  Benchmarking and implementation of probability-based simulations on programmable graphics cards , 2003, Comput. Graph..

[8]  Simon Portegies Zwart,et al.  High-performance direct gravitational N-body simulations on graphics processing units , 2007, astro-ph/0702058.

[9]  Hubert Nguyen,et al.  GPU Gems 3 , 2007 .

[10]  Eric Darve,et al.  N-Body Simulations on GPUs , 2007, ArXiv.

[11]  Tsuyoshi Hamada,et al.  The Chamomile Scheme: An Optimized Algorithm for N-body simulations on Programmable Graphics Processing Units , 2007 .

[12]  Naga K. Govindaraju,et al.  A Survey of General‐Purpose Computation on Graphics Hardware , 2007 .

[13]  Robert G. Belleman,et al.  High Performance Direct Gravitational N-body Simulations on Graphics Processing Units , 2007, ArXiv.

[14]  Kevin Skadron,et al.  A performance study of general-purpose applications on graphics processors using CUDA , 2008, J. Parallel Distributed Comput..

[15]  Gerard Lemson,et al.  GPU-Based Interactive Visualization of Billion Point Cosmological Simulations , 2008, ArXiv.

[16]  Hsi-Yu Schive,et al.  Graphic-card cluster for astrophysics (GraCCA) - Performance tests , 2007, 0707.2991.

[17]  Planet Migration through a Self-Gravitating Planetesimal Disk , 2008, 0809.2855.

[18]  Cambridge,et al.  GPUs for data processing in the MWA , 2009 .

[19]  Mehdi Amini,et al.  A Particle-Mesh Integrator for Galactic Dynamics Powered by GPGPUs , 2009, ICCS.

[20]  Eric B. Ford,et al.  Parallel algorithm for solving Kepler’s equation on Graphics Processing Units: Application to analysis of Doppler exoplanet searches , 2008, 0812.2976.

[21]  Eduardo Pinheiro,et al.  DRAM errors in the wild: a large-scale field study , 2009, SIGMETRICS '09.

[22]  Simon Portegies Zwart,et al.  SAPPORO: A way to turn your graphics cards into a GRAPE-6 , 2009, ArXiv.

[23]  Elsevier Sdol,et al.  Journal of Parallel and Distributed Computing , 2009 .

[24]  Christopher M. Bishop,et al.  The Fourth Paradigm: Data-Intensive Scientific Discovery , 2009 .

[25]  Christopher J. Fluke,et al.  Analysing Astronomy Algorithms for GPUs and Beyond , 2010, ArXiv.

[26]  Firas Hamze,et al.  A Performance Comparison of CUDA and OpenCL , 2010, ArXiv.

[27]  B. R. Barsdell,et al.  Computational advances in gravitational microlensing: A comparison of CPU, GPU, and parallel, large data codes , 2010, 1005.5198.

[28]  Gaurav Khanna,et al.  Numerical modeling of gravitational wave sources accelerated by OpenCL , 2010, Comput. Phys. Commun..

[29]  Volker Weinberg,et al.  RapidMind: Portability across Architectures and Its Limitations , 2010, Facing the Multicore-Challenge.

[30]  R. Teyssier,et al.  REIONIZATION SIMULATIONS POWERED BY GRAPHICS PROCESSING UNITS. I. ON THE STRUCTURE OF THE ULTRAVIOLET RADIATION FIELD , 2010, 1004.2503.

[31]  Christopher J. Fluke,et al.  Teraflop per second gravitational lensing ray-shooting using graphics processing units , 2009, 0905.2453.