Accelerating the computation of FLAPW methods on heterogeneous architectures

TL;DR

This paper demonstrates how re-engineering legacy FLEUR code enables efficient use of heterogeneous architectures like GPUs and Xeon Phis, achieving over 70% of peak performance and significant speedups.

Contribution

The paper presents a modular redesign of FLEUR that allows it to exploit heterogeneous architectures effectively, surpassing vendor libraries in performance.

Findings

Achieves over 70% of architecture peak performance.

Outperforms Nvidia and Intel libraries.

Attains 5x speedup on supercomputer JURECA.

Abstract

Legacy codes in computational science and engineering have been very successful in providing essential functionality to researchers. However, they are not capable of exploiting the massive parallelism provided by emerging heterogeneous architectures. The lack of portable performance and scalability puts them at high risk: either they evolve or they are doomed to disappear. One example of legacy code which would heavily benefit from a modern design is FLEUR, a software for electronic structure calculations. In previous work, the computational bottleneck of FLEUR was partially re-engineered to have a modular design that relies on standard building blocks, namely BLAS and LAPACK. In this paper, we demonstrate how the initial redesign enables the portability to heterogeneous architectures. More specifically, we study different approaches to port the code to architectures consisting of multi-core CPUs equipped with one or more coprocessors such as Nvidia GPUs and Intel Xeon Phis. Our final code attains over 70\% of the architectures' peak performance, and outperforms Nvidia's and Intel's libraries. Finally, on JURECA, the supercomputer where FLEUR is often executed, the code takes advantage of the full power of the computing nodes, attaining $5\times$ speedup over the sole use of the CPUs.