VMT19937: A SIMD-Friendly Pseudo Random Number Generator based on Mersenne Twister 19937

TL;DR

This paper presents a SIMD-optimized pseudo-random number generator based on Mersenne Twister 19937, achieving faster performance while maintaining statistical quality by leveraging parallel vectorization techniques.

Contribution

The authors develop a SIMD-friendly variant of MT19937 that combines multiple streams with jump-ahead transformations for efficient parallel random number generation.

Findings

Achieves linear scaling of throughput with SIMD register width.

Maintains the statistical properties and period of MT19937.

Provides significant speed improvements on modern CPUs with larger SIMD registers.

Abstract

Many simulation applications require the generation of long sequences of pseudo-random numbers. Linear recurrences modulo 2 are commonly used as the fundamental building block for constructing pseudo-random number generators with extended periods and excellent statistical properties. These generators consist of a lengthy binary state vector that evolves iteratively through linear transformations. One widely accepted pseudo-random generator in this category is the Mersenne twister 19937 (MT19937), proposed by Matsumoto and Nishimura, which has been implemented in numerous software libraries and numerical packages. The MT19937's popularity stems from its favorable distribution properties and the simplicity and speed of its algorithm. The linear transformation responsible for evolving the binary state vector can be expressed as a concise set of elementary bit manipulations. However, this transformation does not fully utilize the potential for parallelization through SIMD instructions available on modern hardware, limiting further speed enhancements. This paper introduces a new SIMD-friendly random number generator, which maintains the same statistical properties and period as the MT19937. It combines the random streams of multiple MT19937 instances with state vectors de-phased via jump-ahead transformations, then polls each instance in a round-robin fashion. By evolving their vector states simultaneously, the new generator achieves perfect vectorization, fully leveraging on SIMD hardware capabilities. Comprehensive test results demonstrate that the throughput of the new generator scales approximately linearly with the width of the SIMD registers used. This provides significant speed improvements, especially on modern CPUs equipped with larger SIMD registers, and allows for efficient generation of random numbers for various simulation applications.