Results 1  10
of
19
SPRNG: A Scalable Library for Pseudorandom Number Generation
"... In this article we present background, rationale, and a description of the Scalable Parallel Random
Number Generators (SPRNG) library. We begin by presenting some methods for parallel pseudorandom number generation. We will focus on methods based on parameterization, meaning that we will not conside ..."
Abstract

Cited by 38 (6 self)
 Add to MetaCart
(Show Context)
In this article we present background, rationale, and a description of the Scalable Parallel Random
Number Generators (SPRNG) library. We begin by presenting some methods for parallel pseudorandom number generation. We will focus on methods based on parameterization, meaning that we will not consider splitting methods such as the leapfrog or blocking methods. We describe in detail
parameterized versions of the following pseudorandom number generators: (i) linear congruential
generators, (ii) shiftregister generators, and (iii) laggedFibonacci generators. We briey describe
the methods, detail some advantages and disadvantages of each method, and recount results from
number theory that impact our understanding of their quality in parallel applications.
SPRNG was designed around the uniform implementation of dierent families of parameterized random number
generators. We then present a short description of
SPRNG. The description contained within this
document is meant only to outline the rationale behind and the capabilities of SPRNG. Much more
information, including examples and detailed documentation aimed at helping users with putting
and using SPRNG on scalable systems is available at the URL:
http://sprng.cs.fsu.edu/RNG. In this description of SPRNG we discuss the random number generator library as well as the suite of
tests of randomness that is an integral part of SPRNG. Random number tools for parallel Monte
Carlo applications must be subjected to classical as well as new types of empirical tests of ran
domness to eliminate generators that show defects when used in scalable environments.
Theory, Techniques, And Experiments In Solving Recurrences In Computer Programs
, 1997
"... ... work. In the sixth chapter, we consider the application of these same techniques focused on obtaining parallelism in outer timestepping loops. In the final chapter, we draw this work to a conclusion and discuss future directions in parallelizing compiler technology. ..."
Abstract

Cited by 16 (2 self)
 Add to MetaCart
... work. In the sixth chapter, we consider the application of these same techniques focused on obtaining parallelism in outer timestepping loops. In the final chapter, we draw this work to a conclusion and discuss future directions in parallelizing compiler technology.
Random Number Generation and Simulation on Vector and Parallel Computers
 LECTURE NOTES IN COMPUTER SCIENCE 1470
, 1998
"... Pseudorandom numbers are often required for simulations performed on parallel computers. The requirements for parallel random number generators are more stringent than those for sequential random number generators. As well as passing the usual sequential tests on each processor, a parallel rand ..."
Abstract

Cited by 14 (10 self)
 Add to MetaCart
Pseudorandom numbers are often required for simulations performed on parallel computers. The requirements for parallel random number generators are more stringent than those for sequential random number generators. As well as passing the usual sequential tests on each processor, a parallel random number generator must give dierent, independent sequences on each processor. We consider the requirements for a good parallel random number generator, and discuss generators for the uniform and normal distributions. We also describe a new class of generators for the normal distribution (based on a proposal by Wallace). These
Parameterizing parallel multiplicative laggedfibonacci generators
 Parallel Computing
, 2004
"... ..."
(Show Context)
Some Methods Of Parallel Pseudorandom Number Generation
 in Proceedings of the IMA Workshop on Algorithms for Parallel Processing
, 1997
"... . We detail several methods used in the production of pseudorandom numbers for scalable systems. We will focus on methods based on parameterization, meaning that we will not consider splitting methods. We describe parameterized versions of the following pseudorandom number generation: 1. linear cong ..."
Abstract

Cited by 10 (1 self)
 Add to MetaCart
(Show Context)
. We detail several methods used in the production of pseudorandom numbers for scalable systems. We will focus on methods based on parameterization, meaning that we will not consider splitting methods. We describe parameterized versions of the following pseudorandom number generation: 1. linear congruential generators 2. linear matrix generators 3. shiftregister generators 4. laggedFibonacci generators 5. inversive congruential generators We briefly describe the methods, detail some advantages and disadvantages of each method and recount results from number theory that impact our understanding of their quality in parallel applications. Several of these methods are currently part of scalable library for pseudorandom number generation, called the SPRNG package available at the URL: www.ncsa.uiuc.edu/Apps/CMP/RNG. Key words. pseudorandom number generation, parallel computing, linear congruential, laggedFibonacci, inversive congruential, shiftregister AMS(MOS) subject classifications....
Fast and reliable random number generators for scientific computing
 PROC. PARA'04 WORKSHOP ON THE STATEOFTHEART INSCIENTIFIC COMPUTING
, 2004
"... Fast and reliable pseudorandom number generators are required for simulation and other applications in Scientific Computing. We outline the requirements for good uniform random number generators, and describe a class of generators having very fast vector/parallel implementations with excellent sta ..."
Abstract

Cited by 6 (2 self)
 Add to MetaCart
Fast and reliable pseudorandom number generators are required for simulation and other applications in Scientific Computing. We outline the requirements for good uniform random number generators, and describe a class of generators having very fast vector/parallel implementations with excellent statistical properties. We also discuss the problem of initialising random number generators, and consider how to combine two or more generators to give a better (though usually slower) generator.
Hardware acceleration of parallel laggedFibonacci pseudo random number generation
 in Proc. of Proc. of Engineering of Reconfigurable Systems and Algorithms
, 2006
"... (SPRNG) library is widely used to generate random numbers in Monte Carlo simulations due to the good statistical properties of both its serial and parallel random number streams. In this paper, we suggest an efficient hardware architecture for the Parallel Additive LaggedFibonacci Generator (PALFG) ..."
Abstract

Cited by 5 (2 self)
 Add to MetaCart
(Show Context)
(SPRNG) library is widely used to generate random numbers in Monte Carlo simulations due to the good statistical properties of both its serial and parallel random number streams. In this paper, we suggest an efficient hardware architecture for the Parallel Additive LaggedFibonacci Generator (PALFG) provided by the SPRNG library. This design has been implemented on a VirtexII Pro FPGA device and runs at a clock speed of 125 MHz while delivering one 31bit random number per clock. Compared to the SPRNG software algorithm executing on a Pentium 4 workstation, a single instance of our design offers a 2.3fold performance improvement and appears to be 50 times more efficient. I.
Analyzing Streams of Pseudorandom Numbers for Parallel Monte Carlo Integration
, 1997
"... The quality of parallel substreams of pseudorandom numbers obtained from linear congruential generators as it is measured by the spectral test depends in a very sensitive and irregular way on the step size which is used. On the other hand, discrepancy estimates show that explicit inversive congruent ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
The quality of parallel substreams of pseudorandom numbers obtained from linear congruential generators as it is measured by the spectral test depends in a very sensitive and irregular way on the step size which is used. On the other hand, discrepancy estimates show that explicit inversive congruential pseudorandom number generators behave stable with respect to subsequences. The results of a sample Monte Carlo integration show the impact of these different theoretical findings on the reliability of the integration results.