A Lightweight Approach to Performance Portability with targetDP

TL;DR

targetDP is a lightweight abstraction layer enabling grid-based applications to achieve performance portability across diverse data-parallel hardware architectures, demonstrated on fluid dynamics and lattice QCD applications with scalable results.

Contribution

The paper introduces targetDP, a novel platform-agnostic abstraction layer that simplifies achieving performance portability for grid-based applications on various hardware architectures.

Findings

Single source code achieves portable performance across architectures.

Performance scales effectively on large supercomputers with MPI integration.

Demonstrated success on fluid dynamics and lattice QCD applications.

Abstract

Leading HPC systems achieve their status through use of highly parallel devices such as NVIDIA GPUs or Intel Xeon Phi many-core CPUs. The concept of performance portability across such architectures, as well as traditional CPUs, is vital for the application programmer. In this paper we describe targetDP, a lightweight abstraction layer which allows grid-based applications to target data parallel hardware in a platform agnostic manner. We demonstrate the effectiveness of our pragmatic approach by presenting performance results for a complex fluid application (with which the model was co-designed), plus a separate lattice QCD particle physics code. For each application, a single source code base is seen to achieve portable performance, as assessed within the context of the Roofline model. TargetDP can be combined with MPI to allow use on systems containing multiple nodes: we demonstrate this through provision of scaling results on traditional and GPU-accelerated large scale supercomputers.