Porting uintah to heterogeneous systems

John K. Holmen; Damodar Sahasrabudhe; Martin Berzins

doi:10.1145/3539781.3539794

Porting uintah to heterogeneous systems

John K. Holmen, Damodar Sahasrabudhe, Martin Berzins

System Acceptance and User Environment

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

8 Scopus citations

Abstract

The Uintah Computational Framework is being prepared to make portable use of forthcoming exascale systems, initially the DOE Aurora system through the Aurora Early Science Program. This paper describes the evolution of Uintah to be ready for such architectures. A key part of this preparation has been the adoption of the Kokkos performance portability layer in Uintah. The sheer size of the Uintah codebase has made it imperative to have a representative benchmark. The design of this benchmark and the use of Kokkos within it is discussed. This paper complements recent work with additional details and new scaling studies run 24x further than earlier studies. Results are shown for two benchmarks executing workloads representative of typical Uintah applications. These results demonstrate single-source portability across the DOE Summit and NSF Frontera systems with good strong-scaling characteristics. The challenge of extending this approach to anticipated exascale systems is also considered.

Original language	English
Title of host publication	Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2022
Publisher	Association for Computing Machinery, Inc
ISBN (Electronic)	9781450394109
DOIs	https://doi.org/10.1145/3539781.3539794
State	Published - Jun 27 2022
Event	2022 Platform for Advanced Scientific Computing Conference, PASC 2022 - Basel, Switzerland Duration: Jun 27 2022 → Jun 29 2022

Publication series

Name	Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2022

Conference

Conference	2022 Platform for Advanced Scientific Computing Conference, PASC 2022
Country/Territory	Switzerland
City	Basel
Period	06/27/22 → 06/29/22

Funding

This material is based upon work originally supported by the Department of Energy, National Nuclear Security Administration, under Award Number(s) DE-NA0002375. This research used resources of the Oak Ridge National Laboratory through support of the DOE Aurora project and the NSF Texas Advanced Computing Center. Support for J. K. Holmen and D. Sahasrabudhe comes from the University of Texas at Austin under Award Number(s) UTA19-001215 and a gift from the Intel Parallel Computing Centers Program. We would like to thank all involved with the CCMSC and Uintah, past and present, with special thanks to Brad Peter-son, Jeremy Thornock, Derek Harris, Oscar Díaz-Ibarra, and Todd Harman for Kokkos-related ARCHES efforts.

Keywords

asynchronous many-task runtime system
parallelism and concurrency
performance portability
portability
software engineering

Access to Document

10.1145/3539781.3539794

Cite this

@inproceedings{b08476a76e284e4097d6de16cbcd2069,

title = "Porting uintah to heterogeneous systems",

abstract = "The Uintah Computational Framework is being prepared to make portable use of forthcoming exascale systems, initially the DOE Aurora system through the Aurora Early Science Program. This paper describes the evolution of Uintah to be ready for such architectures. A key part of this preparation has been the adoption of the Kokkos performance portability layer in Uintah. The sheer size of the Uintah codebase has made it imperative to have a representative benchmark. The design of this benchmark and the use of Kokkos within it is discussed. This paper complements recent work with additional details and new scaling studies run 24x further than earlier studies. Results are shown for two benchmarks executing workloads representative of typical Uintah applications. These results demonstrate single-source portability across the DOE Summit and NSF Frontera systems with good strong-scaling characteristics. The challenge of extending this approach to anticipated exascale systems is also considered.",

keywords = "asynchronous many-task runtime system, parallelism and concurrency, performance portability, portability, software engineering",

author = "Holmen, \{John K.\} and Damodar Sahasrabudhe and Martin Berzins",

note = "Publisher Copyright: {\textcopyright} 2022 ACM.; 2022 Platform for Advanced Scientific Computing Conference, PASC 2022 ; Conference date: 27-06-2022 Through 29-06-2022",

year = "2022",

month = jun,

day = "27",

doi = "10.1145/3539781.3539794",

language = "English",

series = "Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2022",

publisher = "Association for Computing Machinery, Inc",

booktitle = "Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2022",

}

Holmen, JK, Sahasrabudhe, D & Berzins, M 2022, Porting uintah to heterogeneous systems. in Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2022., 11, Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2022, Association for Computing Machinery, Inc, 2022 Platform for Advanced Scientific Computing Conference, PASC 2022, Basel, Switzerland, 06/27/22. https://doi.org/10.1145/3539781.3539794

Porting uintah to heterogeneous systems. / Holmen, John K.; Sahasrabudhe, Damodar; Berzins, Martin.
Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2022. Association for Computing Machinery, Inc, 2022. 11 (Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2022).

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

TY - GEN

T1 - Porting uintah to heterogeneous systems

AU - Holmen, John K.

AU - Sahasrabudhe, Damodar

AU - Berzins, Martin

PY - 2022/6/27

Y1 - 2022/6/27

N2 - The Uintah Computational Framework is being prepared to make portable use of forthcoming exascale systems, initially the DOE Aurora system through the Aurora Early Science Program. This paper describes the evolution of Uintah to be ready for such architectures. A key part of this preparation has been the adoption of the Kokkos performance portability layer in Uintah. The sheer size of the Uintah codebase has made it imperative to have a representative benchmark. The design of this benchmark and the use of Kokkos within it is discussed. This paper complements recent work with additional details and new scaling studies run 24x further than earlier studies. Results are shown for two benchmarks executing workloads representative of typical Uintah applications. These results demonstrate single-source portability across the DOE Summit and NSF Frontera systems with good strong-scaling characteristics. The challenge of extending this approach to anticipated exascale systems is also considered.

AB - The Uintah Computational Framework is being prepared to make portable use of forthcoming exascale systems, initially the DOE Aurora system through the Aurora Early Science Program. This paper describes the evolution of Uintah to be ready for such architectures. A key part of this preparation has been the adoption of the Kokkos performance portability layer in Uintah. The sheer size of the Uintah codebase has made it imperative to have a representative benchmark. The design of this benchmark and the use of Kokkos within it is discussed. This paper complements recent work with additional details and new scaling studies run 24x further than earlier studies. Results are shown for two benchmarks executing workloads representative of typical Uintah applications. These results demonstrate single-source portability across the DOE Summit and NSF Frontera systems with good strong-scaling characteristics. The challenge of extending this approach to anticipated exascale systems is also considered.

KW - asynchronous many-task runtime system

KW - parallelism and concurrency

KW - performance portability

KW - portability

KW - software engineering

UR - http://www.scopus.com/inward/record.url?scp=85134809108&partnerID=8YFLogxK

U2 - 10.1145/3539781.3539794

DO - 10.1145/3539781.3539794

M3 - Conference contribution

AN - SCOPUS:85134809108

T3 - Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2022

BT - Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2022

PB - Association for Computing Machinery, Inc

T2 - 2022 Platform for Advanced Scientific Computing Conference, PASC 2022

Y2 - 27 June 2022 through 29 June 2022

ER -

Porting uintah to heterogeneous systems

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this