Abstract
Along with the scale expansion of high performance computing, accelerators are increasingly viewed as computer coprocessors that can provide significant computational performance at low price. Thus, research of mixed computer architecture is becoming popular. This paper presents a mixed configurable computer architecture which can run fast multipole method (FMM) algorithm of N-Body problem well. Each sub-procedure of FMM algorithm is implemented and tested on GPU, FPGA and CELL. FMM is optimized on the proposed configure scheme through decomposing its task flow. The probable solution for different task flow is also put forward. The conclusion is significant to the research on the mixed computer architecture of high performance computing.
This research is supported by Nation 863 Program under No. 2009AA012201- CFA2009SHDX01, Shanghai Leading Academic Discipline Project under No. J50103.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Cruz, F.A., Barba, L.A.: Characterization of the accuracy of the fast multipole method in particle simulations. Journal of Numerical Methods in Engineer (79), 1577–1604 (2009)
Spurzem, R., Berczik, P., Marcus, G., et al.: Accelerating astrophysical particle simulations with programmable hardware (FPGA and GPU). Computer Science - Research and Development (23), 231–239 (2009)
Che, S., Li, J., Sheaffer, J.W., et al.: Accelerating Compute -Intensive Applications with GPUs and FPGAs. In: Proc. of the IEEE Symposium on Application Specific Processors, SASP (June 2008)
Aubert, D., Amini, M., David, R.: A Particle-Mesh Integrator for Galactic Dynamics Powered by GPGPUs. In: Allen, G., Nabrzyski, J., Seidel, E., van Albada, G.D., Dongarra, J., Sloot, P.M.A. (eds.) ICCS 2009, Part I. LNCS, vol. 5544, pp. 874–883. Springer, Heidelberg (2009)
Hamada, T., Nitadori, K., Benkrid, K., et al.: A novel multiple-walk parallel algorithm for the Barnes–Hut treecode on GPUs – towards cost effective, high performance N-body simulation. Computer Science - Research and Development (24), 21–31 (2009)
Gumerov, N.A., Duraiswami, R.: Fast Multipole Methods on Graphics Processors. Journal of Computational Physics (227), 8290–8313 (2008)
Xu, K., Ding, D.Z., Fan, Z.H., et al.: Multilevel Fast Multipole Algorithm Enhanced by GPU parallel Technique for Electromagentic Scattering Problems. Microwave and Optical Technology Letters 52(3), 502–507 (2010)
Stokes, M.L.: A Brief Look at FPGAs, GPUs and Cell Processors. ITEA Journal (7), 9–11 (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag GmbH Berlin Heidelberg
About this chapter
Cite this chapter
Cao, M., Cao, Z. (2012). Configure Scheme of Mixed Computer Architecture for FMM Algorithm. In: Qian, Z., Cao, L., Su, W., Wang, T., Yang, H. (eds) Recent Advances in Computer Science and Information Engineering. Lecture Notes in Electrical Engineering, vol 125. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-25789-6_93
Download citation
DOI: https://doi.org/10.1007/978-3-642-25789-6_93
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-25788-9
Online ISBN: 978-3-642-25789-6
eBook Packages: EngineeringEngineering (R0)