High Performance Implementation of Boris Particle Pusher on DPC++. A First Look at oneAPI

TL;DR

This paper explores porting the computationally intensive Boris particle pusher algorithm to the oneAPI framework, demonstrating minimal performance loss on CPUs and effective execution on Intel GPUs, thus supporting portable high-performance supercomputing applications.

Contribution

The paper presents a successful port of Boris particle pusher to oneAPI, showing minimal performance degradation and broad hardware compatibility for supercomputer simulations.

Findings

DPC++ port is ~10% slower on CPUs compared to optimized C++

Code runs effectively on Intel GPUs without specific optimizations

Porting effort is straightforward, enabling hardware-agnostic development

Abstract

New hardware architectures open up immense opportunities for supercomputer simulations. However, programming techniques for different architectures vary significantly, which leads to the necessity of developing and supporting multiple code versions, each being optimized for specific hardware features. The oneAPI framework, recently introduced by Intel, contains a set of programming tools for the development of portable codes that can be compiled and fine-tuned for CPUs, GPUs, FPGAs, and accelerators. In this paper, we report on the experience of porting the implementation of Boris particle pusher to oneAPI. Boris particle pusher is one of the most demanding computational stages of the Particle-in-Cell method, which, in particular, is used for supercomputer simulations of laser-plasma interactions. We show how to adapt the C++ implementation of the particle push algorithm from the Hi-Chi project to the DPC++ programming language and report the performance of the code on high-end Intel CPUs (Xeon Platinum 8260L) and Intel GPUs (P630 and Iris Xe Max). It turned out that our C++ code can be easily ported to DPC++. We found that on CPUs the resulting DPC++ code is only ~10% on average inferior to the optimized C++ code. Moreover, the code is compiled and run on new Intel GPUs without any specific optimizations and shows the expected performance, taking into account the parameters of the hardware.