Evaluating Nonuniform Reduction in HIP and SYCL on GPUs

Zheming Jin; Jeffrey S. Vetter

doi:10.1109/DRBSD56682.2022.00010

Evaluating Nonuniform Reduction in HIP and SYCL on GPUs

Zheming Jin, Jeffrey S. Vetter

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

1 Scopus citations

Abstract

Motivated by maturing programming models and portability for heterogeneous computing, we describe the challenges posed by hardware architectures and programming models when migrating an optimized implementation of nonuniform reduction from CUDA to HIP and SYCL. We explain the migration experience, evaluate the performance of the reduction on GPU -based computing platforms, and provide feedback on improving portability for the development of the SYCL programming model.

Original language	English
Title of host publication	Proceedings of DRBSD-8 2022
Subtitle of host publication	8th International Workshop on Data Analysis and Reduction for Big Scientific Data, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	37-43
Number of pages	7
ISBN (Electronic)	9781665463379
DOIs	https://doi.org/10.1109/DRBSD56682.2022.00010
State	Published - 2022
Event	8th IEEE/ACM International Workshop on Data Analysis and Reduction for Big Scientific Data, DRBSD-8 2022 - Dallas, United States Duration: Nov 13 2022 → Nov 18 2022

Publication series

Name	Proceedings of DRBSD-8 2022: 8th International Workshop on Data Analysis and Reduction for Big Scientific Data, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis

Conference

Conference	8th IEEE/ACM International Workshop on Data Analysis and Reduction for Big Scientific Data, DRBSD-8 2022
Country/Territory	United States
City	Dallas
Period	11/13/22 → 11/18/22

Funding

ACKNOWLEDGMENT We appreciate the reviewers’ comments and suggestions. This research used resources of the Experimental Computing Lab at Oak Ridge National Laboratory. This research was supported by the US Department of Energy Advanced Scientific Computing Research program under Contract No. DE-AC05-00OR22725. Notice: This manuscript has been authored by UT-Battelle, LLC under Contract No. DE-AC05-00OR22725 with the U.S. Department of Energy. The publisher, by accepting the article for publication, acknowledges that the U.S. Government retains a non-exclusive, paid up, irrevocable, world-wide license to publish or reproduce the published form of the manuscript, or allow others to do so, for U.S. Government purposes. The DOE will provide public access to these results in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan). We appreciate the reviewers comments and suggestions. This research used resources of the Experimental Computing Lab at Oak Ridge National Laboratory. This research was supported by the US Department of Energy Advanced Scientific Computing Research program under Contract No. DE-AC05-00OR22725.

Keywords

Nonuniform reduction
heterogeneous computing
programming model

Access to Document

10.1109/DRBSD56682.2022.00010

Cite this

Jin, Z., & Vetter, J. S. (2022). Evaluating Nonuniform Reduction in HIP and SYCL on GPUs. In Proceedings of DRBSD-8 2022: 8th International Workshop on Data Analysis and Reduction for Big Scientific Data, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis (pp. 37-43). (Proceedings of DRBSD-8 2022: 8th International Workshop on Data Analysis and Reduction for Big Scientific Data, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DRBSD56682.2022.00010

Jin, Zheming ; Vetter, Jeffrey S. / Evaluating Nonuniform Reduction in HIP and SYCL on GPUs. Proceedings of DRBSD-8 2022: 8th International Workshop on Data Analysis and Reduction for Big Scientific Data, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 37-43 (Proceedings of DRBSD-8 2022: 8th International Workshop on Data Analysis and Reduction for Big Scientific Data, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis).

@inproceedings{c4033d5a3bf44a528ef7663eecc97d9c,

title = "Evaluating Nonuniform Reduction in HIP and SYCL on GPUs",

abstract = "Motivated by maturing programming models and portability for heterogeneous computing, we describe the challenges posed by hardware architectures and programming models when migrating an optimized implementation of nonuniform reduction from CUDA to HIP and SYCL. We explain the migration experience, evaluate the performance of the reduction on GPU -based computing platforms, and provide feedback on improving portability for the development of the SYCL programming model.",

keywords = "Nonuniform reduction, heterogeneous computing, programming model",

author = "Zheming Jin and Vetter, \{Jeffrey S.\}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 8th IEEE/ACM International Workshop on Data Analysis and Reduction for Big Scientific Data, DRBSD-8 2022 ; Conference date: 13-11-2022 Through 18-11-2022",

year = "2022",

doi = "10.1109/DRBSD56682.2022.00010",

language = "English",

series = "Proceedings of DRBSD-8 2022: 8th International Workshop on Data Analysis and Reduction for Big Scientific Data, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis",

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

pages = "37--43",

booktitle = "Proceedings of DRBSD-8 2022",

}

Jin, Z & Vetter, JS 2022, Evaluating Nonuniform Reduction in HIP and SYCL on GPUs. in Proceedings of DRBSD-8 2022: 8th International Workshop on Data Analysis and Reduction for Big Scientific Data, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis. Proceedings of DRBSD-8 2022: 8th International Workshop on Data Analysis and Reduction for Big Scientific Data, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis, Institute of Electrical and Electronics Engineers Inc., pp. 37-43, 8th IEEE/ACM International Workshop on Data Analysis and Reduction for Big Scientific Data, DRBSD-8 2022, Dallas, United States, 11/13/22. https://doi.org/10.1109/DRBSD56682.2022.00010

Evaluating Nonuniform Reduction in HIP and SYCL on GPUs. / Jin, Zheming; Vetter, Jeffrey S.
Proceedings of DRBSD-8 2022: 8th International Workshop on Data Analysis and Reduction for Big Scientific Data, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc., 2022. p. 37-43 (Proceedings of DRBSD-8 2022: 8th International Workshop on Data Analysis and Reduction for Big Scientific Data, Held in conjunction with SC 2022: 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 - Evaluating Nonuniform Reduction in HIP and SYCL on GPUs

AU - Jin, Zheming

AU - Vetter, Jeffrey S.

PY - 2022

Y1 - 2022

N2 - Motivated by maturing programming models and portability for heterogeneous computing, we describe the challenges posed by hardware architectures and programming models when migrating an optimized implementation of nonuniform reduction from CUDA to HIP and SYCL. We explain the migration experience, evaluate the performance of the reduction on GPU -based computing platforms, and provide feedback on improving portability for the development of the SYCL programming model.

AB - Motivated by maturing programming models and portability for heterogeneous computing, we describe the challenges posed by hardware architectures and programming models when migrating an optimized implementation of nonuniform reduction from CUDA to HIP and SYCL. We explain the migration experience, evaluate the performance of the reduction on GPU -based computing platforms, and provide feedback on improving portability for the development of the SYCL programming model.

KW - Nonuniform reduction

KW - heterogeneous computing

KW - programming model

UR - http://www.scopus.com/inward/record.url?scp=85147798660&partnerID=8YFLogxK

U2 - 10.1109/DRBSD56682.2022.00010

DO - 10.1109/DRBSD56682.2022.00010

M3 - Conference contribution

AN - SCOPUS:85147798660

T3 - Proceedings of DRBSD-8 2022: 8th International Workshop on Data Analysis and Reduction for Big Scientific Data, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis

SP - 37

EP - 43

BT - Proceedings of DRBSD-8 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 8th IEEE/ACM International Workshop on Data Analysis and Reduction for Big Scientific Data, DRBSD-8 2022

Y2 - 13 November 2022 through 18 November 2022

ER -

Jin Z, Vetter JS. Evaluating Nonuniform Reduction in HIP and SYCL on GPUs. In Proceedings of DRBSD-8 2022: 8th International Workshop on Data Analysis and Reduction for Big Scientific Data, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc. 2022. p. 37-43. (Proceedings of DRBSD-8 2022: 8th International Workshop on Data Analysis and Reduction for Big Scientific Data, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis). doi: 10.1109/DRBSD56682.2022.00010

Evaluating Nonuniform Reduction in HIP and SYCL on GPUs

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this