Pseudo-random number generators for Monte Carlo simulations on ATI Graphics Processing Units

@article{Demchik2011PseudorandomNG,
  title={Pseudo-random number generators for Monte Carlo simulations on ATI Graphics Processing Units},
  author={Vadim Demchik},
  journal={Comput. Phys. Commun.},
  year={2011},
  volume={182},
  pages={692-705}
}
  • V. Demchik
  • Published 9 March 2010
  • Computer Science, Physics
  • Comput. Phys. Commun.

Figures and Tables from this paper

Pseudorandom Numbers Generation for Monte Carlo Simulations on GPUs: OpenCL Approach
  • V. Demchik
  • Computer Science
    Numerical Computations with GPUs
  • 2014
General principles of pseudorandom numbers production for Monte Carlo simulations on GPUs are discussed by creating an OpenCL open-source library of pseudorandom number generators PRNGCL. The library
GPU optimized Pseudo Random Number Generator for MCNP
TLDR
An effective implementation of the 48bit PRNG algorithm proposed in MPI version of MCNP on GPU is presented and experimental results show that the performance speedup of one NVIDIA M2050 GPU with full double precision floating operations is up to 11-fold factor compared with the parallel implementation on one multi-core Intel Xeon X5670.
GPU Accelerated Scalable Parallel Random Number Generators
TLDR
An application of Pi calculation using Monte Carlo methods is presented, with results showing that this code can integrate to computational science applications.
Random number generators for massively parallel simulations on GPU
TLDR
A broad review of existing CUDA variants of random-number generators is provided and the CUDA implementation of a new massively parallel high-quality, high-performance generator with a small memory load overhead is presented.
JMASM Algorithms and Code Pseudo-Random Number Generators for Vector Processors and Multicore Processors
TLDR
An open source C++ implementation is provided for a pseudo-random number generator capable of utilizing both the vector processing capabilities and multiprocessing capabilities of modern computers in order to get the maximum performance.
Implementation of a RANLUX Based Pseudo-Random Number Generator in FPGA Using VHDL and Impulse C
TLDR
The authors introduce the world's first implementation of the RANLUX algorithm on an FPGA platform for high performance computing purposes, and has an extremely low power demand, which makes it perfect for use in environment friendly and energy-efficient supercomputing solutions and embedded systems.
Memory efficient lagged-Fibonacci random number generators for GPU supercomputing
TLDR
This paper discusses the implementation of memory efficient, integer, cycle-split, additive and multiplicative LFGs for both CUDA and OpenCL, and discusses portability and reproducibility between CPUs and GPUs.
An On-Demand Fast Parallel Pseudo Random Number Generator with Applications
TLDR
This paper investigates a CPU+GPU hybrid technique to create an efficient PRNG that can produce random numbers on demand as opposed to a onetime generation and applies it to design a list ranking algorithm and a Monte Carlo simulation which shows the high quality of the generator.
Shub on the GPU A performance comparison between a CPU bound and a GPU bound
TLDR
The results showed that using the floating-point data type would yield greater performance for a multi-precision number system on the GPU compared to using the integer data type.
...
...

References

SHOWING 1-10 OF 79 REFERENCES
Monte Carlo simulations on Graphics Processing Units
TLDR
An analysis of both CAL programming model and the efficiency of the corresponding simulation algorithms on GPU shows significant performance speed-up of these algorithms in comparison with serial execution.
Random Number Generators for Parallel Computers
TLDR
This work presents a review of the most commonly-used random number generators for parallel computers, and evaluates each generator based on theoretical knowledge and empirical tests, and provides recommendations for using random number generator on parallel computers.
A fast high quality pseudo random number generator for nVidia CUDA
TLDR
Newer nVidia G80 and Tesla hardware support double precision, which allows a much simpler C++ implementation of Park-Miller random numbers, which provides a four fold speed up compared to an earlier GPU implementation.
A portable high-quality random number generator for lattice field theory simulations
Generalized Feedback Shift Register Pseudorandom Number Algorithm
TLDR
The generalized feedback shift register pseudorandom number algorithm has several advantages over all other pseudor random number generators, including an arbitrarily long period independent of the word size of the computer on which it is implemented and the “same” floating-point pseudOrandom number sequence is obtained on any machine.
Random number generation and Quasi-Monte Carlo methods
  • H. Niederreiter
  • Computer Science, Mathematics
    CBMS-NSF regional conference series in applied mathematics
  • 1992
TLDR
This chapter discusses Monte Carlo methods and Quasi-Monte Carlo methods for optimization, which are used for numerical integration, and their applications in random numbers and pseudorandom numbers.
...
...