Evaluating Kernels on Xeon Phi to accelerate GYSELA application

Abstract : This work describes the challenges presented by porting parts of the 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 some generic micro-benchmark on Phi versus Intel Sandy Bridge. Several interpolation kernels useful for the gysela application are analyzed and the performances 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 peak 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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [5 references]  Display  Hide  Download

https://hal-cea.archives-ouvertes.fr/cea-01305499
Contributor : Julien Bigot <>
Submitted on : Thursday, April 21, 2016 - 10:55:58 AM
Last modification on : Thursday, February 7, 2019 - 4:16:52 PM
Long-term archiving on : Friday, July 22, 2016 - 11:30:52 AM

File

proc165313.pdf
Publisher files allowed on an open archive

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Collections

Citation

Guillaume Latu, Matthieu Haefele, Julien Bigot, Virginie Grandgirard, Thomas Cartier-Michaud, et al.. Evaluating Kernels on Xeon Phi to accelerate GYSELA application. ESAIM: PROCEEDINGS AND SURVEYS, Jul 2014, CIRM – Centre International de Rencontres Mathématiques, Marseille, France. pp.211-231, ⟨10.1051/proc/201653013⟩. ⟨cea-01305499⟩

Share

Metrics

Record views

745

Files downloads

215