Monte Carlo integration on GPU

TL;DR

This paper demonstrates that GPU acceleration significantly speeds up Monte Carlo integration, achieving over 50 times faster computation than CPU-based methods while maintaining accuracy.

Contribution

The paper introduces GPU parallelization of VEGAS and BASES Monte Carlo programs, greatly enhancing computation speed for high-energy physics applications.

Findings

GPU programs are about 50 times faster than C implementations.

GPU programs are more than 60 times faster than original FORTRAN programs.

Integrated results are consistent across CPU and GPU implementations.

Abstract

We use a graphics processing unit (GPU) for fast computations of Monte Carlo integrations. Two widely used Monte Carlo integration programs, VEGAS and BASES, are parallelized on GPU. By using $W^{+}$ plus multi-gluon production processes at LHC, we test integrated cross sections and execution time for programs in FORTRAN and C on CPU and those on GPU. Integrated results agree with each other within statistical errors. Execution time of programs on GPU run about 50 times faster than those in C, and more than 60 times faster than the original FORTRAN programs.