Pseudo-Random Number Generators for Vector Processors and Multicore Processors

Research output: Contribution to journalJournal articleResearchpeer-review

1204 Downloads (Pure)

Abstract

Large scale Monte Carlo applications need a good 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. The requirements for such a generator are discussed. New ways of avoiding overlapping subsequences by combining two generators are proposed. Some fundamental philosophical problems in proving independence of random streams are discussed. Remedies for hitherto ignored quantization errors are offered. An open source C++ implementation is provided for a generator that meets these needs.
Original languageEnglish
Article number23
JournalJournal of Modern Applied Statistical Methods
Volume14
Issue number1
Pages (from-to)308-334
ISSN1538-9472
Publication statusPublished - 2015

Keywords

  • Random number generation
  • SIMD
  • Vector processors
  • Multiprocessors
  • Parallel generation
  • Combination of generators
  • Quantization errors
  • Theoretical proofs
  • Philosophy of science

Cite this