Abstract
This paper presents an FPGA implementation of a calculation module for a finite sum of the exponential products (orbital function). The module is composed of several specially designed floating-point modules which are, fully pipelined and optimized for high speed performance. The hardware implementation revealed significant speed-up for the finite sum of the exponential products calculation ranging from 2.5x to 20x in comparison to the CPU. The orbital function is a computationally critical part of the Hartree-Fock algorithm. The presented approach aims to increase the performance of the part of the quantum chemistry computational system by employing FPGA-based accelerator. Several issues are addressed such as an identification of proper code fragments, porting a part of the Hartree-Fock algorithm to FPGA, data precision adjustment and data transfer overheads. The authors’ intention was also to make hardware application of the orbital function universal and easily attachable to different systems.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Underwood, K.D., Hemmert, K.S., Ulmer, C.: Architectures and APIs: assessing requirements for delivering FPGA performance to applications. In: Proceedings of the 2006 ACM/IEEE Conference on Supercomputing, SC 2006, Tampa, Florida, November 11-17, p. 111. ACM, New York (2006)
Silicon Graphics, Inc. Reconfigurable Application-Specific Computing User’s Guide, Ver. 005, SGI (January 2007)
Gothandaraman, A., Peterson, G., Warren, G., Hinde, R., Harrison, R.: FPGA acceleration of a quantum Monte Carlo application. Parallel Computing 34(4-5), 278–291 (2008)
Gothandaraman, A., Warren, G.L., Peterson, G.D., Harrison, R.J.: Reconfigurable accelerator for quantum Monte Carlo simulations in N-body systems. In: Proceedings of the 2006 ACM/IEEE Conference on Supercomputing, SC 2006, Tampa, Florida, November 11-17, p. 177. ACM, New York (2006)
Mazur, G., Makowski, M.: Development and Optimization of Computational Chemistry Algorithms. In: KDM 2008, Zakopane, Poland (March 2008)
Wielgosz, M., Jamro, E., Wiatr, K.: Highly Efficient Structure of 64-Bit Exponential Function Implemented in FPGAs. In: Woods, R., Compton, K., Bouganis, C., Diniz, P.C. (eds.) ARC 2008. LNCS, vol. 4943, pp. 274–279. Springer, Heidelberg (2008)
Jamro, E., Wielgosz, M., Wiatr, K.: FPGA implementation of 64-bit exponential function for HPC. In: FPL Proceedings, FPL Netherlands, August 27-29 (2007)
Omondi, A.R.: Computer Arithmetic Systems. Prentice Hall, Cambridge (1994)
Xilinx Virtex-4 Family Overview, http://www.xilinx.com/support/documentation/data_sheets/ds112.pdf
Parhi, K.K., Chung, J.G., Lee, K.C., Cho, K.J.: Low-error fixed-width modified booth multiplier, US Patent: 957244
SGI Altix 4700, http://www.sgi.com/products/servers/altix/4000/
Ramdas, T., Egan, G.K., Abramson, D., Baldridge, K.: Converting massive TLP to DLP: a special-purpose processor for molecular orbital computations. In: Proceedings of the 4th International Conference on Computing Frontiers, CF 2007, Ischia, Italy, May 7-9, pp. 267–276. ACM, New York (2007)
Kandaswamy, M., Kandemir, M., Choudhary, A., Bernholdt, D.: Optimization and Evaluation of Hartree-Fock Application’s I/O with PASSION. In: Proceedings of the ACM/IEEE Conference on Supercomputing (SC), November 1997, pp. 31–50 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wielgosz, M., Jamro, E., Wiatr, K. (2010). Hardware Implementation of the Exponent Based Computational Core for an Exchange-Correlation Potential Matrix Generation. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Wasniewski, J. (eds) Parallel Processing and Applied Mathematics. PPAM 2009. Lecture Notes in Computer Science, vol 6067. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-14390-8_13
Download citation
DOI: https://doi.org/10.1007/978-3-642-14390-8_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-14389-2
Online ISBN: 978-3-642-14390-8
eBook Packages: Computer ScienceComputer Science (R0)