The performances of R GPU implementations of the GMRES method

TL;DR

This paper presents a GPU implementation of the GMRES iterative method for solving linear systems in R, demonstrating performance improvements over single-threaded CPU versions using various GPU packages.

Contribution

The paper introduces a GPU-based GMRES implementation in R and compares its performance across different GPU packages and frameworks.

Findings

GPU implementation outperforms single-threaded CPU version

Performance varies depending on GPU package used

GPU acceleration significantly reduces computation time

Abstract

Although the performance of commodity computers has improved drastically with the introduction of multicore processors and GPU computing, the standard R distribution is still based on single-threaded model of computation, using only a small fraction of the computational power available now for most desktops and laptops. Modern statistical software packages rely on high performance implementations of the linear algebra routines there are at the core of several important leading edge statistical methods. In this paper we present a GPU implementation of the GMRES iterative method for solving linear systems. We compare the performance of this implementation with a pure single threaded version of the CPU. We also investigate the performance of our implementation using different GPU packages available now for R such as gmatrix, gputools or gpuR which are based on CUDA or OpenCL frameworks.