Parallel Sparse Matrix Solver on the GPU Applied to Simulation of Electrical Machines

TL;DR

This paper demonstrates how implementing a conjugate gradient sparse matrix solver on GPUs significantly accelerates the simulation of electrical machines by leveraging parallelism in CSR and CSC formats.

Contribution

It introduces a GPU-based parallel implementation of the conjugate gradient method for sparse matrices in electrical machine simulations, enhancing computational speed.

Findings

GPU implementation outperforms CPU in speed.

Parallel sparse matrix solving is effective for Maxwell's equations.

CSR and CSC formats are suitable for GPU acceleration.

Abstract

Nowadays, several industrial applications are being ported to parallel architectures. In fact, these platforms allow acquire more performance for system modelling and simulation. In the electric machines area, there are many problems which need speed-up on their solution. This paper examines the parallelism of sparse matrix solver on the graphics processors. More specifically, we implement the conjugate gradient technique with input matrix stored in CSR, and Symmetric CSR and CSC formats. This method is one of the most efficient iterative methods available for solving the finite-element basis functions of Maxwell's equations. The GPU (Graphics Processing Unit), which is used for its implementation, provides mechanisms to parallel the algorithm. Thus, it increases significantly the computation speed in relation to serial code on CPU based systems.