Fast and Green Computing with Graphics Processing Units for solving Sparse Linear Systems

TL;DR

This paper evaluates GPU-based algorithms for solving sparse linear systems, focusing on energy efficiency and performance, and compares a new implementation with the Cusp library using real-world data.

Contribution

It introduces an energy-aware analysis of GPU algorithms for sparse linear algebra and presents a robust, energy-efficient implementation for solving gravity equations.

Findings

Our implementation outperforms Cusp in energy efficiency.

The analysis confirms the robustness of the proposed GPU algorithms.

Energy consumption is a critical factor in high-performance sparse computations.

Abstract

In this paper, we aim to introduce a new perspective when comparing highly parallelized algorithms on GPU: the energy consumption of the GPU. We give an analysis of the performance of linear algebra operations, including addition of vectors, element-wise product, dot product and sparse matrix-vector product, in order to validate our experimental protocol. We also analyze their uses within conjugate gradient method for solving the gravity equations on Graphics Processing Unit (GPU). Cusp library is considered and compared to our own implementation with a set of real matrices arrising from the Chicxulub crater and obtained by the finite element discretization of the gravity equations. The experiments demonstrate the performance and robustness of our implementation in terms of energy efficiency.