Evaluating kernels on Xeon Phi to accelerate Gysela application

TL;DR

This paper evaluates the performance of various kernels on the Intel Xeon Phi to optimize the Gysela application, highlighting challenges and improvements in execution time through vectorization and tuning techniques.

Contribution

It presents a detailed analysis of porting and optimizing Gysela kernels on Xeon Phi, demonstrating performance gains and challenges in reaching peak efficiency.

Findings

Memory-bound kernels doubled performance on Phi

Compute-bound kernels also accelerated significantly

Gysela execution time decreased on Sandy Bridge after optimization

Abstract

This work describes the challenges presented by porting parts ofthe Gysela code to the Intel Xeon Phi coprocessor, as well as techniques used for optimization, vectorization and tuning that can be applied to other applications. We evaluate the performance of somegeneric micro-benchmark on Phi versus Intel Sandy Bridge. Several interpolation kernels useful for the Gysela application are analyzed and the performance are shown. Some memory-bound and compute-bound kernels are accelerated by a factor 2 on the Phi device compared to Sandy architecture. Nevertheless, it is hard, if not impossible, to reach a large fraction of the peek performance on the Phi device,especially for real-life applications as Gysela. A collateral benefit of this optimization and tuning work is that the execution time of Gysela (using 4D advections) has decreased on a standard architecture such as Intel Sandy Bridge.