ThundeRiNG: Generating Multiple Independent Random Number Sequences on FPGAs

TL;DR

ThundeRiNG is a resource-efficient FPGA system that generates multiple independent high-quality random number sequences at extremely high throughput, significantly outperforming GPU-based solutions in speed and power efficiency.

Contribution

It introduces a novel decorrelator and state sharing mechanism to efficiently generate multiple independent random sequences on FPGAs, ensuring statistical independence with minimal resource use.

Findings

Passes TestU01 statistical tests for randomness.

Achieves 655 billion random numbers per second throughput.

Provides up to 9.15x speedup and 26.63x power efficiency over GPU implementations.

Abstract

In this paper, we propose ThundeRiNG, a resource-efficient and high-throughput system for generating multiple independent sequences of random numbers (MISRN) on FPGAs. Generating MISRN can be a time-consuming step in many applications such as numeric computation and approximate computing. Despite that decades of studies on generating a single sequence of random numbers on FPGAs have achieved very high throughput and high quality of randomness, existing MISRN approaches either suffer from heavy resource consumption or fail to achieve statistical independence among sequences. In contrast, ThundeRiNG resolves the dependence by using a resource-efficient decorrelator among multiple sequences, guaranteeing a high statistical quality of randomness. Moreover, ThundeRiNG develops a novel state sharing among a massive number of pseudo-random number generator instances on FPGAs. The experimental results show that ThundeRiNG successfully passes the widely used statistical test, TestU01, only consumes a constant number of DSPs (less than 1\% of the FPGA resource capacity) for generating any number of sequences, and achieves a throughput of 655 billion random numbers per second. Compared to the state-of-the-art GPU library, ThundeRiNG demonstrates a $10.62\times$ speedup on MISRN and delivers up to $9.15\times$ performance and $26.63\times$ power efficiency improvement on two applications ($\pi$ estimation and Monte Carlo option pricing). This work is open-sourced on Github at https://github.com/Xtra-Computing/ThundeRiNG