Cucheb: A GPU implementation of the filtered Lanczos procedure

TL;DR

Cucheb is a GPU-accelerated software package that significantly speeds up the filtered Lanczos method for large sparse eigenvalue problems, especially useful in electronic structure calculations.

Contribution

The paper introduces Cucheb, a GPU implementation of the filtered Lanczos procedure, achieving over tenfold speedup compared to CPU versions.

Findings

GPU implementation reduces computation time by over 10 times.

Effective for eigenvalue problems in electronic structure calculations.

Demonstrates the advantage of GPU acceleration for spectral transformations.

Abstract

This paper describes the software package Cucheb, a GPU implementation of the filtered Lanczos procedure for the solution of large sparse symmetric eigenvalue problems. The filtered Lanczos procedure uses a carefully chosen polynomial spectral transformation to accelerate convergence of the Lanczos method when computing eigenvalues within a desired interval. This method has proven particularly effective for eigenvalue problems that arise in electronic structure calculations and density functional theory. We compare our implementation against an equivalent CPU implementation and show that using the GPU can reduce the computation time by more than a factor of 10.