Multivariate Gaussian Random Number Generator Targeting Specific Resource Utilization in an FPGA
Financial applications are one of many fields where a multivariate Gaussian random number generator plays a key role in performing computationally extensive simulations. Recent technological advances and today’s requirements have led to the migration of the traditional software based multivariate Gaussian random number generator to a hardware based model. Field Programmable Gate Arrays (FPGA) are normally used as a target device due to their fine grain parallelism and reconfigurability. As well as the ability to achieve designs with high throughput it is also desirable to produce designs with the flexibility to control the resource usage in order to meet given resource constraints. This paper proposes an algorithm for a multivariate Gaussian random number generator implementation in an FPGA given a set of resources to be utilized. Experiments demonstrate the proposed algorithm’s capability of producing a design that meets any given resource constraints.
KeywordsMultivariate Gaussian Distribution Random Numbers FPGA Resource Constraint
Unable to display preview. Download preview PDF.
- 3.Glasserman, P., Heidelberger, P., Shahabuddin, P.: Variance reduction techniques for value-at-risk with heavy-tailed risk factors. In: Proceedings of the 32nd conference on Winter simulation, pp. 604–609 (2000), Society for Computer Simulation International, San Diego, CA, USA (2000)Google Scholar
- 4.Thomas, D.B., Luk, W.: Sampling from the multivariate gaussian distribution using reconfigurable hardware. In: Proceedings IEEE International Symposium on Field-Programmable Custom Computing Machines, pp. 3–12 (2007)Google Scholar
- 7.Graybill, F.A.: Introduction to Matrices with Applications in Statistics, Wadsworth, Belmont, CA (1969)Google Scholar
- 9.Zhang, G., Leong, P.H., Lee, D.-U., Villasenor, J.D., Cheung, R.C., Luk, W.: Ziggurat-based hardware gaussian random number generator. In: Proceedings IEEE International Conference on Field Programmable Logic and Applications, pp. 275–280 (2005)Google Scholar
- 14.Xilinx, Virtex-4 family overview, 2007. [Online]. Available: http://www.xilinx.com/support/documentation/data_sheets/ds112.pdf.
- 17.Bouganis, C.-S., Constantinides, G.A., Cheung, P.Y.K.: A novel 2d filter design methodology for heterogeneous devices. In: Proceedings of the 13th Annual IEEE Symposium on Field-Programmable Custom Computing Machines, pp. 13–22. IEEE Computer Society Press, Washington DC, USA (2005)CrossRefGoogle Scholar