Hybrid CPU-GPU generation of the Hamiltonian and Overlap matrices in FLAPW methods

TL;DR

This paper demonstrates how integrating high-performance libraries and porting to GPU-accelerated architectures significantly improves the speed and scalability of the FLEUR electronic structure calculation code.

Contribution

It presents a systematic approach to modernize legacy ab initio code for heterogeneous architectures, achieving substantial performance gains.

Findings

Speedups of up to 5x on GPU-accelerated nodes

Between 7.5x and 12.5x overall speedup over original code

Effective use of high-performance libraries enables portability and scalability

Abstract

In this paper we focus on the integration of high-performance numerical libraries in ab initio codes and the portability of performance and scalability. The target of our work is FLEUR, a software for electronic structure calculations developed in the Forschungszentrum J\"ulich over the course of two decades. The presented work follows up on a previous effort to modernize legacy code by re-engineering and rewriting it in terms of highly optimized libraries. We illustrate how this initial effort to get efficient and portable shared-memory code enables fast porting of the code to emerging heterogeneous architectures. More specifically, we port the code to nodes equipped with multiple GPUs. We divide our study in two parts. First, we show considerable speedups attained by minor and relatively straightforward code changes to off-load parts of the computation to the GPUs. Then, we identify further possible improvements to achieve even higher performance and scalability. On a system consisting of 16-cores and 2 GPUs, we observe speedups of up to 5x with respect to our optimized shared-memory code, which in turn means between 7.5x and 12.5x speedup with respect to the original FLEUR code.