Towards achieving performance portability using directives for accelerators

M. Graham Lopez; Veronica Vergara Larrea; Wayne Joubert; Oscar Hernandez; Azzam Haidar; Stanimire Tomov; Jack Dongarra

doi:10.1109/WACCPD.2016.006

Towards achieving performance portability using directives for accelerators

M. Graham Lopez, Veronica Vergara Larrea, Wayne Joubert, Oscar Hernandez, Azzam Haidar, Stanimire Tomov, Jack Dongarra

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

19 Scopus citations

Abstract

In this paper we explore the performance portability of directives provided by OpenMP 4 and OpenACC to program various types of node architectures with attached accelerators, both self-hosted multicore and offload multicore/GPU. Our goal is to examine how successful OpenACC and the newer offload features of OpenMP 4.5 are for moving codes between architectures, how much tuning might be required and what lessons we can learn from this experience. To do this, we use examples of algorithms with varying computational intensities for our evaluation, as both compute and data access efficiency are important considerations for overall application performance. We implement these kernels using various methods provided by newer OpenACC and OpenMP implementations, and we evaluate their performance on various platforms including both X86-64 with attached NVIDIA GPUs, self-hosted Intel Xeon Phi KNL, as well as an X86-64 host system with Intel Xeon Phi coprocessors. In this paper, we explain what factors affected the performance portability such as how to pick the right programming model, its programming style, its availability on different platforms, and how well compilers can optimize and target to multiple platforms.

Original language	English
Title of host publication	Proceedings of WACCPD 2016
Subtitle of host publication	3rd Workshop on Accelerator Programming using Directives - Held in conjunction with SC 2016: The International Conference for High Performance Computing, Networking, Storage and Analysis
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	13-24
Number of pages	12
ISBN (Electronic)	9781509061525
DOIs	https://doi.org/10.1109/WACCPD.2016.006
State	Published - Jan 30 2017
Event	3rd Workshop on Accelerator Programming using Directives, WACCPD 2016 - Salt Lake City, United States Duration: Nov 14 2016 → …

Publication series

Name	Proceedings of WACCPD 2016: 3rd Workshop on Accelerator Programming using Directives - Held in conjunction with SC 2016: The International Conference for High Performance Computing, Networking, Storage and Analysis

Conference

Conference	3rd Workshop on Accelerator Programming using Directives, WACCPD 2016
Country/Territory	United States
City	Salt Lake City
Period	11/14/16 → …

Funding

This material is based upon work supported by the U.S. Department of Energy, Office of Science, Office of Advanced Scientific Computing Research, under contract number DEAC05-00OR22725.

Access to Document

10.1109/WACCPD.2016.006

Cite this

Lopez, M. G., Larrea, V. V., Joubert, W., Hernandez, O., Haidar, A., Tomov, S., & Dongarra, J. (2017). Towards achieving performance portability using directives for accelerators. In Proceedings of WACCPD 2016: 3rd Workshop on Accelerator Programming using Directives - Held in conjunction with SC 2016: The International Conference for High Performance Computing, Networking, Storage and Analysis (pp. 13-24). Article 7836577 (Proceedings of WACCPD 2016: 3rd Workshop on Accelerator Programming using Directives - Held in conjunction with SC 2016: The International Conference for High Performance Computing, Networking, Storage and Analysis). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WACCPD.2016.006

Lopez, M. Graham ; Larrea, Veronica Vergara ; Joubert, Wayne et al. / Towards achieving performance portability using directives for accelerators. Proceedings of WACCPD 2016: 3rd Workshop on Accelerator Programming using Directives - Held in conjunction with SC 2016: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 13-24 (Proceedings of WACCPD 2016: 3rd Workshop on Accelerator Programming using Directives - Held in conjunction with SC 2016: The International Conference for High Performance Computing, Networking, Storage and Analysis).

@inproceedings{17fac950eb1b4a14b223105ad527167f,

title = "Towards achieving performance portability using directives for accelerators",

abstract = "In this paper we explore the performance portability of directives provided by OpenMP 4 and OpenACC to program various types of node architectures with attached accelerators, both self-hosted multicore and offload multicore/GPU. Our goal is to examine how successful OpenACC and the newer offload features of OpenMP 4.5 are for moving codes between architectures, how much tuning might be required and what lessons we can learn from this experience. To do this, we use examples of algorithms with varying computational intensities for our evaluation, as both compute and data access efficiency are important considerations for overall application performance. We implement these kernels using various methods provided by newer OpenACC and OpenMP implementations, and we evaluate their performance on various platforms including both X86-64 with attached NVIDIA GPUs, self-hosted Intel Xeon Phi KNL, as well as an X86-64 host system with Intel Xeon Phi coprocessors. In this paper, we explain what factors affected the performance portability such as how to pick the right programming model, its programming style, its availability on different platforms, and how well compilers can optimize and target to multiple platforms.",

author = "Lopez, {M. Graham} and Larrea, {Veronica Vergara} and Wayne Joubert and Oscar Hernandez and Azzam Haidar and Stanimire Tomov and Jack Dongarra",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 3rd Workshop on Accelerator Programming using Directives, WACCPD 2016 ; Conference date: 14-11-2016",

year = "2017",

month = jan,

day = "30",

doi = "10.1109/WACCPD.2016.006",

language = "English",

series = "Proceedings of WACCPD 2016: 3rd Workshop on Accelerator Programming using Directives - Held in conjunction with SC 2016: The International Conference for High Performance Computing, Networking, Storage and Analysis",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "13--24",

booktitle = "Proceedings of WACCPD 2016",

}

Lopez, MG, Larrea, VV, Joubert, W, Hernandez, O, Haidar, A, Tomov, S & Dongarra, J 2017, Towards achieving performance portability using directives for accelerators. in Proceedings of WACCPD 2016: 3rd Workshop on Accelerator Programming using Directives - Held in conjunction with SC 2016: The International Conference for High Performance Computing, Networking, Storage and Analysis., 7836577, Proceedings of WACCPD 2016: 3rd Workshop on Accelerator Programming using Directives - Held in conjunction with SC 2016: The International Conference for High Performance Computing, Networking, Storage and Analysis, Institute of Electrical and Electronics Engineers Inc., pp. 13-24, 3rd Workshop on Accelerator Programming using Directives, WACCPD 2016, Salt Lake City, United States, 11/14/16. https://doi.org/10.1109/WACCPD.2016.006

Towards achieving performance portability using directives for accelerators. / Lopez, M. Graham; Larrea, Veronica Vergara; Joubert, Wayne et al.
Proceedings of WACCPD 2016: 3rd Workshop on Accelerator Programming using Directives - Held in conjunction with SC 2016: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc., 2017. p. 13-24 7836577 (Proceedings of WACCPD 2016: 3rd Workshop on Accelerator Programming using Directives - Held in conjunction with SC 2016: The International Conference for High Performance Computing, Networking, Storage and Analysis).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Towards achieving performance portability using directives for accelerators

AU - Lopez, M. Graham

AU - Larrea, Veronica Vergara

AU - Joubert, Wayne

AU - Hernandez, Oscar

AU - Haidar, Azzam

AU - Tomov, Stanimire

AU - Dongarra, Jack

PY - 2017/1/30

Y1 - 2017/1/30

N2 - In this paper we explore the performance portability of directives provided by OpenMP 4 and OpenACC to program various types of node architectures with attached accelerators, both self-hosted multicore and offload multicore/GPU. Our goal is to examine how successful OpenACC and the newer offload features of OpenMP 4.5 are for moving codes between architectures, how much tuning might be required and what lessons we can learn from this experience. To do this, we use examples of algorithms with varying computational intensities for our evaluation, as both compute and data access efficiency are important considerations for overall application performance. We implement these kernels using various methods provided by newer OpenACC and OpenMP implementations, and we evaluate their performance on various platforms including both X86-64 with attached NVIDIA GPUs, self-hosted Intel Xeon Phi KNL, as well as an X86-64 host system with Intel Xeon Phi coprocessors. In this paper, we explain what factors affected the performance portability such as how to pick the right programming model, its programming style, its availability on different platforms, and how well compilers can optimize and target to multiple platforms.

AB - In this paper we explore the performance portability of directives provided by OpenMP 4 and OpenACC to program various types of node architectures with attached accelerators, both self-hosted multicore and offload multicore/GPU. Our goal is to examine how successful OpenACC and the newer offload features of OpenMP 4.5 are for moving codes between architectures, how much tuning might be required and what lessons we can learn from this experience. To do this, we use examples of algorithms with varying computational intensities for our evaluation, as both compute and data access efficiency are important considerations for overall application performance. We implement these kernels using various methods provided by newer OpenACC and OpenMP implementations, and we evaluate their performance on various platforms including both X86-64 with attached NVIDIA GPUs, self-hosted Intel Xeon Phi KNL, as well as an X86-64 host system with Intel Xeon Phi coprocessors. In this paper, we explain what factors affected the performance portability such as how to pick the right programming model, its programming style, its availability on different platforms, and how well compilers can optimize and target to multiple platforms.

UR - http://www.scopus.com/inward/record.url?scp=85015203631&partnerID=8YFLogxK

U2 - 10.1109/WACCPD.2016.006

DO - 10.1109/WACCPD.2016.006

M3 - Conference contribution

AN - SCOPUS:85015203631

T3 - Proceedings of WACCPD 2016: 3rd Workshop on Accelerator Programming using Directives - Held in conjunction with SC 2016: The International Conference for High Performance Computing, Networking, Storage and Analysis

SP - 13

EP - 24

BT - Proceedings of WACCPD 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 3rd Workshop on Accelerator Programming using Directives, WACCPD 2016

Y2 - 14 November 2016

ER -

Lopez MG, Larrea VV, Joubert W, Hernandez O, Haidar A, Tomov S et al. Towards achieving performance portability using directives for accelerators. In Proceedings of WACCPD 2016: 3rd Workshop on Accelerator Programming using Directives - Held in conjunction with SC 2016: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc. 2017. p. 13-24. 7836577. (Proceedings of WACCPD 2016: 3rd Workshop on Accelerator Programming using Directives - Held in conjunction with SC 2016: The International Conference for High Performance Computing, Networking, Storage and Analysis). doi: 10.1109/WACCPD.2016.006

Towards achieving performance portability using directives for accelerators

Abstract

Publication series

Conference

Funding

Access to Document

Other files and links

Fingerprint

Cite this