Assembling Portable In-Situ Workflow from Heterogeneous Components using Data Reorganization

Bo Zhang; Pradeep Subedi; Philip E. Davis; Francesco Rizzi; Keita Teranishi; Manish Parashar

doi:10.1109/CCGrid54584.2022.00013

Assembling Portable In-Situ Workflow from Heterogeneous Components using Data Reorganization

Bo Zhang
, Pradeep Subedi
, Philip E. Davis
, Francesco Rizzi
, Keita Teranishi
, Manish Parashar

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

2 Scopus citations

Abstract

Heterogeneous computing is becoming common in the HPC world. The fast-changing hardware landscape is pushing programmers and developers to rely on performance-portable programming models to rewrite old and legacy applications and develop new ones. While this approach is suitable for individual applications, outstanding challenges still remain when multiple applications are combined into complex workflows. One critical difficulty is the exchange of data between communicating applications where performance constraints imposed by heterogeneous hardware advantage different data layouts. We attempt to solve this problem by exploring asynchronous data layout conversions for applications requiring different memory access patterns for shared data. We implement the proposed solution within the DataSpaces data staging service, extending it to support heterogeneous application workflows across a broad spectrum of programming models. In addition, we integrate heterogeneous DataSpaces with the Kokkos programming model and propose the Kokkos Staging Space as an extension of the Kokkos data abstraction. This new abstraction enables us to express data on a virtual shared space for multiple Kokkos applications, thus guaranteeing the portability of each application when assembling them into an efficient heterogeneous workflow. We present performance results for the Kokkos Staging Space using a synthetic workflow emulator and three different scenarios representing access frequency and use patterns in shared data. The results show that the Kokkos Staging Space is a superior solution in terms of time-to-solution and scalability compared to existing file-based Kokkos data abstractions for inter-application data exchange.

Original language	English
Title of host publication	Proceedings - 22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, CCGrid 2022
Editors	Maria Fazio, Dhabaleswar K. Panda, Radu Prodan, Valeria Cardellini, Burak Kantarci, Omer Rana, Massimo Villari
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	41-50
Number of pages	10
ISBN (Electronic)	9781665499569
DOIs	https://doi.org/10.1109/CCGrid54584.2022.00013
State	Published - 2022
Externally published	Yes
Event	22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, CCGrid 2022 - Taormina, Italy Duration: May 16 2022 → May 19 2022

Publication series

Name	Proceedings - 22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, CCGrid 2022

Conference

Conference	22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, CCGrid 2022
Country/Territory	Italy
City	Taormina
Period	05/16/22 → 05/19/22

Funding

We thank Elisabeth Giem, Patricia Gharagozloo, and Joseph Kenny for the consistent support of our research. This material is based upon work supported by the U.S. Department of Energy (DOE), Office of Science, Office of Advanced Scientific Computing Research, under Contract DE-AC02-06CH11357. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Hon-eywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration (NNSA) under con- tract DE-NA0003525. This work was funded by NNSA’s Advanced Simulation and Computing (ASC) Program. This paper describes objective technical results and analysis. Any subjective views or opinions that might be expressed in the paper do not necessarily represent the views of the U.S. Department of Energy or the United States Government. The authors acknowledge Zhao Zhang and the Texas Advanced Computing Center (TACC) at The University of Texas at Austin for providing HPC, visualization, database, or grid resources that have contributed to the research results reported within this paper. URL: http://www.tacc.utexas.edu

Keywords

HPC
Kokkos
Performance Portability

Access to Document

10.1109/CCGrid54584.2022.00013

Cite this

Zhang, B., Subedi, P., Davis, P. E., Rizzi, F., Teranishi, K., & Parashar, M. (2022). Assembling Portable In-Situ Workflow from Heterogeneous Components using Data Reorganization. In M. Fazio, D. K. Panda, R. Prodan, V. Cardellini, B. Kantarci, O. Rana, & M. Villari (Eds.), Proceedings - 22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, CCGrid 2022 (pp. 41-50). (Proceedings - 22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, CCGrid 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CCGrid54584.2022.00013

Zhang, Bo ; Subedi, Pradeep ; Davis, Philip E. et al. / Assembling Portable In-Situ Workflow from Heterogeneous Components using Data Reorganization. Proceedings - 22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, CCGrid 2022. editor / Maria Fazio ; Dhabaleswar K. Panda ; Radu Prodan ; Valeria Cardellini ; Burak Kantarci ; Omer Rana ; Massimo Villari. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 41-50 (Proceedings - 22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, CCGrid 2022).

@inproceedings{39de0cf1d8c24dbbbe79515a2e81616c,

title = "Assembling Portable In-Situ Workflow from Heterogeneous Components using Data Reorganization",

abstract = "Heterogeneous computing is becoming common in the HPC world. The fast-changing hardware landscape is pushing programmers and developers to rely on performance-portable programming models to rewrite old and legacy applications and develop new ones. While this approach is suitable for individual applications, outstanding challenges still remain when multiple applications are combined into complex workflows. One critical difficulty is the exchange of data between communicating applications where performance constraints imposed by heterogeneous hardware advantage different data layouts. We attempt to solve this problem by exploring asynchronous data layout conversions for applications requiring different memory access patterns for shared data. We implement the proposed solution within the DataSpaces data staging service, extending it to support heterogeneous application workflows across a broad spectrum of programming models. In addition, we integrate heterogeneous DataSpaces with the Kokkos programming model and propose the Kokkos Staging Space as an extension of the Kokkos data abstraction. This new abstraction enables us to express data on a virtual shared space for multiple Kokkos applications, thus guaranteeing the portability of each application when assembling them into an efficient heterogeneous workflow. We present performance results for the Kokkos Staging Space using a synthetic workflow emulator and three different scenarios representing access frequency and use patterns in shared data. The results show that the Kokkos Staging Space is a superior solution in terms of time-to-solution and scalability compared to existing file-based Kokkos data abstractions for inter-application data exchange.",

keywords = "HPC, Kokkos, Performance Portability",

author = "Bo Zhang and Pradeep Subedi and Davis, \{Philip E.\} and Francesco Rizzi and Keita Teranishi and Manish Parashar",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, CCGrid 2022 ; Conference date: 16-05-2022 Through 19-05-2022",

year = "2022",

doi = "10.1109/CCGrid54584.2022.00013",

language = "English",

series = "Proceedings - 22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, CCGrid 2022",

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

pages = "41--50",

editor = "Maria Fazio and Panda, \{Dhabaleswar K.\} and Radu Prodan and Valeria Cardellini and Burak Kantarci and Omer Rana and Massimo Villari",

booktitle = "Proceedings - 22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, CCGrid 2022",

}

Zhang, B, Subedi, P, Davis, PE, Rizzi, F, Teranishi, K & Parashar, M 2022, Assembling Portable In-Situ Workflow from Heterogeneous Components using Data Reorganization. in M Fazio, DK Panda, R Prodan, V Cardellini, B Kantarci, O Rana & M Villari (eds), Proceedings - 22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, CCGrid 2022. Proceedings - 22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, CCGrid 2022, Institute of Electrical and Electronics Engineers Inc., pp. 41-50, 22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, CCGrid 2022, Taormina, Italy, 05/16/22. https://doi.org/10.1109/CCGrid54584.2022.00013

Assembling Portable In-Situ Workflow from Heterogeneous Components using Data Reorganization. / Zhang, Bo; Subedi, Pradeep; Davis, Philip E. et al.
Proceedings - 22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, CCGrid 2022. ed. / Maria Fazio; Dhabaleswar K. Panda; Radu Prodan; Valeria Cardellini; Burak Kantarci; Omer Rana; Massimo Villari. Institute of Electrical and Electronics Engineers Inc., 2022. p. 41-50 (Proceedings - 22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, CCGrid 2022).

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

TY - GEN

T1 - Assembling Portable In-Situ Workflow from Heterogeneous Components using Data Reorganization

AU - Zhang, Bo

AU - Subedi, Pradeep

AU - Davis, Philip E.

AU - Rizzi, Francesco

AU - Teranishi, Keita

AU - Parashar, Manish

PY - 2022

Y1 - 2022

N2 - Heterogeneous computing is becoming common in the HPC world. The fast-changing hardware landscape is pushing programmers and developers to rely on performance-portable programming models to rewrite old and legacy applications and develop new ones. While this approach is suitable for individual applications, outstanding challenges still remain when multiple applications are combined into complex workflows. One critical difficulty is the exchange of data between communicating applications where performance constraints imposed by heterogeneous hardware advantage different data layouts. We attempt to solve this problem by exploring asynchronous data layout conversions for applications requiring different memory access patterns for shared data. We implement the proposed solution within the DataSpaces data staging service, extending it to support heterogeneous application workflows across a broad spectrum of programming models. In addition, we integrate heterogeneous DataSpaces with the Kokkos programming model and propose the Kokkos Staging Space as an extension of the Kokkos data abstraction. This new abstraction enables us to express data on a virtual shared space for multiple Kokkos applications, thus guaranteeing the portability of each application when assembling them into an efficient heterogeneous workflow. We present performance results for the Kokkos Staging Space using a synthetic workflow emulator and three different scenarios representing access frequency and use patterns in shared data. The results show that the Kokkos Staging Space is a superior solution in terms of time-to-solution and scalability compared to existing file-based Kokkos data abstractions for inter-application data exchange.

AB - Heterogeneous computing is becoming common in the HPC world. The fast-changing hardware landscape is pushing programmers and developers to rely on performance-portable programming models to rewrite old and legacy applications and develop new ones. While this approach is suitable for individual applications, outstanding challenges still remain when multiple applications are combined into complex workflows. One critical difficulty is the exchange of data between communicating applications where performance constraints imposed by heterogeneous hardware advantage different data layouts. We attempt to solve this problem by exploring asynchronous data layout conversions for applications requiring different memory access patterns for shared data. We implement the proposed solution within the DataSpaces data staging service, extending it to support heterogeneous application workflows across a broad spectrum of programming models. In addition, we integrate heterogeneous DataSpaces with the Kokkos programming model and propose the Kokkos Staging Space as an extension of the Kokkos data abstraction. This new abstraction enables us to express data on a virtual shared space for multiple Kokkos applications, thus guaranteeing the portability of each application when assembling them into an efficient heterogeneous workflow. We present performance results for the Kokkos Staging Space using a synthetic workflow emulator and three different scenarios representing access frequency and use patterns in shared data. The results show that the Kokkos Staging Space is a superior solution in terms of time-to-solution and scalability compared to existing file-based Kokkos data abstractions for inter-application data exchange.

KW - HPC

KW - Kokkos

KW - Performance Portability

UR - https://www.scopus.com/pages/publications/85135747420

U2 - 10.1109/CCGrid54584.2022.00013

DO - 10.1109/CCGrid54584.2022.00013

M3 - Conference contribution

AN - SCOPUS:85135747420

T3 - Proceedings - 22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, CCGrid 2022

SP - 41

EP - 50

BT - Proceedings - 22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, CCGrid 2022

A2 - Fazio, Maria

A2 - Panda, Dhabaleswar K.

A2 - Prodan, Radu

A2 - Cardellini, Valeria

A2 - Kantarci, Burak

A2 - Rana, Omer

A2 - Villari, Massimo

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, CCGrid 2022

Y2 - 16 May 2022 through 19 May 2022

ER -

Zhang B, Subedi P, Davis PE, Rizzi F, Teranishi K, Parashar M. Assembling Portable In-Situ Workflow from Heterogeneous Components using Data Reorganization. In Fazio M, Panda DK, Prodan R, Cardellini V, Kantarci B, Rana O, Villari M, editors, Proceedings - 22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, CCGrid 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 41-50. (Proceedings - 22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, CCGrid 2022). doi: 10.1109/CCGrid54584.2022.00013

Assembling Portable In-Situ Workflow from Heterogeneous Components using Data Reorganization

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this