Title :
On the fast generation of long-period pseudorandom number sequences
Author :
Dalal, Ishaan L. ; Harwayne-Gidansky, Jared ; Stefan, Deian
Author_Institution :
Dept. of Electr. Eng., Advancement of Sci. & Art, New York, NY
Abstract :
Monte Carlo simulations and other scientific applications that depend on random numbers are increasingly implemented in parallel configurations in programmable hardware. High-quality pseudo-random number generators (PRNGs), such as the Mersenne Twister, are based on binary linear recurrence equations. They have extremely long periods (more than 21024 numbers generated before the entire sequence repeats) and well-proven statistical properties. Many software implementations of such dasialong-periodpsila PRNGs exist, but hardware implementations are rare. We develop optimized, resource-efficient parallel architectures for long-period PRNGs that generate multiple independent streams by exploiting the underlying algorithm as well as hardware-specific architectural features.
Keywords :
Monte Carlo methods; field programmable gate arrays; parallel algorithms; parallel architectures; random number generation; random sequences; FPGA; Monte Carlo simulation; Ziggurat algorithm; binary linear recurrence equations; field-programmable gate array; high-quality pseudo-random number generators; long-period pseudorandom number sequences; programmable hardware; resource-efficient parallel architectures; two-parallelized 32-bit Mersenne twister; Application software; Difference equations; Field programmable gate arrays; Hardware; Parallel architectures; Programmable logic arrays; Random number generation; Signal processing algorithms; Testing; Throughput; Field Programmable gate arrays; Parallel algorithms; Parallel architectures; Random Number Generation;
Conference_Titel :
Systems, Applications and Technology Conference, 2008 IEEE Long Island
Conference_Location :
Farmingdale, NY
Print_ISBN :
978-1-4244-1731-5
Electronic_ISBN :
978-1-4244-1732-2
DOI :
10.1109/LISAT.2008.4638953
