Random numbers for parallel computers: Requirements and methods, with emphasis on GPUs

详细信息    查看全文

• 作者：Pierre L&rsquo ; Ecuyer^a ; ^b ; ^{lecuyer@iro.umontreal.ca} ; David Munger^a ; Boris Oreshkin^a ; Richard Simard^a
• 关键词：Random number generators ; Multiple streams ; Parallel computing ; Simulation ; Monte Carlo
• 刊名：Mathematics and Computers in Simulation
• 出版年：2017
• 出版时间：May 2017
• 年：2017
• 卷：135
• 期：Complete
• 页码：3-17
• 全文大小：328 K
• 卷排序：135

文摘

We examine the requirements and the available methods and software to provide (or imitate) uniform random numbers in parallel computing environments. In this context, for the great majority of applications, independent streams of random numbers are required, each being computed on a single processing element at a time. Sometimes, thousands or even millions of such streams are needed. We explain how they can be produced and managed. We devote particular attention to multiple streams for GPU devices.