Composition of Algorithmic Building Blocks in Template Task Graphs

Thomas Herault; Joseph Schuchart; Edward F. Valeev; George Bosilca

doi:10.1109/PAW-ATM56565.2022.00008

Composition of Algorithmic Building Blocks in Template Task Graphs

Thomas Herault
, Joseph Schuchart
, Edward F. Valeev
, George Bosilca

Institute for Advanced Computational Science

University of Tennessee
Virginia Polytechnic Institute and State University

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

2 Scopus citations

Abstract

In this paper, we explore the composition capabilities of the Template Task Graph (TTG) programming model. We show how fine-grain composition of tasks is possible in TTG between DAGs belonging to different libraries, even in a distributed setup. We illustrate the benefits of this fine-grain composition on a linear algebra operation, the matrix inversion via the Cholesky method, which consists of three operations that need to be applied in sequence.Evaluation on a cluster of many core shows that the transparent fine-grain composition implements the complex operation without introducing unnecessary synchronizations, increasing the overlap of communication and computation, and thus improving significantly the performance of the entire composed operation.

Original language	English
Title of host publication	Proceedings of PAW-ATM 2022
Subtitle of host publication	Parallel Applications Workshop, Alternatives to MPI+X, 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	26-38
Number of pages	13
ISBN (Electronic)	9781665454100
DOIs	https://doi.org/10.1109/PAW-ATM56565.2022.00008
State	Published - 2022
Event	5th Annual IEEE/ACM Parallel Applications Workshop, Alternatives to MPI+X, PAW-ATM 2022 - Dallas, United States Duration: Nov 13 2022 → Nov 18 2022

Publication series

Name	Proceedings of PAW-ATM 2022: Parallel Applications Workshop, Alternatives to MPI+X, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis

Conference

Conference	5th Annual IEEE/ACM Parallel Applications Workshop, Alternatives to MPI+X, PAW-ATM 2022
Country/Territory	United States
City	Dallas
Period	11/13/22 → 11/18/22

Keywords

Layered software design
Library composition
Task-Based Runtime System
Template Task Graph

Access to Document

10.1109/PAW-ATM56565.2022.00008

Cite this

Herault, T., Schuchart, J., Valeev, E. F., & Bosilca, G. (2022). Composition of Algorithmic Building Blocks in Template Task Graphs. In Proceedings of PAW-ATM 2022: Parallel Applications Workshop, Alternatives to MPI+X, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis (pp. 26-38). (Proceedings of PAW-ATM 2022: Parallel Applications Workshop, Alternatives to MPI+X, 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/PAW-ATM56565.2022.00008

Herault, Thomas ; Schuchart, Joseph ; Valeev, Edward F. et al. / Composition of Algorithmic Building Blocks in Template Task Graphs. Proceedings of PAW-ATM 2022: Parallel Applications Workshop, Alternatives to MPI+X, 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. 26-38 (Proceedings of PAW-ATM 2022: Parallel Applications Workshop, Alternatives to MPI+X, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis).

@inproceedings{51e0af08739446e797f9823dd7dd5a8a,

title = "Composition of Algorithmic Building Blocks in Template Task Graphs",

abstract = "In this paper, we explore the composition capabilities of the Template Task Graph (TTG) programming model. We show how fine-grain composition of tasks is possible in TTG between DAGs belonging to different libraries, even in a distributed setup. We illustrate the benefits of this fine-grain composition on a linear algebra operation, the matrix inversion via the Cholesky method, which consists of three operations that need to be applied in sequence.Evaluation on a cluster of many core shows that the transparent fine-grain composition implements the complex operation without introducing unnecessary synchronizations, increasing the overlap of communication and computation, and thus improving significantly the performance of the entire composed operation.",

keywords = "Layered software design, Library composition, Task-Based Runtime System, Template Task Graph",

author = "Thomas Herault and Joseph Schuchart and Valeev, \{Edward F.\} and George Bosilca",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 5th Annual IEEE/ACM Parallel Applications Workshop, Alternatives to MPI+X, PAW-ATM 2022 ; Conference date: 13-11-2022 Through 18-11-2022",

year = "2022",

doi = "10.1109/PAW-ATM56565.2022.00008",

language = "English",

series = "Proceedings of PAW-ATM 2022: Parallel Applications Workshop, Alternatives to MPI+X, 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 = "26--38",

booktitle = "Proceedings of PAW-ATM 2022",

}

Herault, T, Schuchart, J, Valeev, EF & Bosilca, G 2022, Composition of Algorithmic Building Blocks in Template Task Graphs. in Proceedings of PAW-ATM 2022: Parallel Applications Workshop, Alternatives to MPI+X, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis. Proceedings of PAW-ATM 2022: Parallel Applications Workshop, Alternatives to MPI+X, 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. 26-38, 5th Annual IEEE/ACM Parallel Applications Workshop, Alternatives to MPI+X, PAW-ATM 2022, Dallas, United States, 11/13/22. https://doi.org/10.1109/PAW-ATM56565.2022.00008

Composition of Algorithmic Building Blocks in Template Task Graphs. / Herault, Thomas; Schuchart, Joseph; Valeev, Edward F. et al.
Proceedings of PAW-ATM 2022: Parallel Applications Workshop, Alternatives to MPI+X, 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. 26-38 (Proceedings of PAW-ATM 2022: Parallel Applications Workshop, Alternatives to MPI+X, 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 - Composition of Algorithmic Building Blocks in Template Task Graphs

AU - Herault, Thomas

AU - Schuchart, Joseph

AU - Valeev, Edward F.

AU - Bosilca, George

PY - 2022

Y1 - 2022

N2 - In this paper, we explore the composition capabilities of the Template Task Graph (TTG) programming model. We show how fine-grain composition of tasks is possible in TTG between DAGs belonging to different libraries, even in a distributed setup. We illustrate the benefits of this fine-grain composition on a linear algebra operation, the matrix inversion via the Cholesky method, which consists of three operations that need to be applied in sequence.Evaluation on a cluster of many core shows that the transparent fine-grain composition implements the complex operation without introducing unnecessary synchronizations, increasing the overlap of communication and computation, and thus improving significantly the performance of the entire composed operation.

AB - In this paper, we explore the composition capabilities of the Template Task Graph (TTG) programming model. We show how fine-grain composition of tasks is possible in TTG between DAGs belonging to different libraries, even in a distributed setup. We illustrate the benefits of this fine-grain composition on a linear algebra operation, the matrix inversion via the Cholesky method, which consists of three operations that need to be applied in sequence.Evaluation on a cluster of many core shows that the transparent fine-grain composition implements the complex operation without introducing unnecessary synchronizations, increasing the overlap of communication and computation, and thus improving significantly the performance of the entire composed operation.

KW - Layered software design

KW - Library composition

KW - Task-Based Runtime System

KW - Template Task Graph

UR - https://www.scopus.com/pages/publications/85148041049

U2 - 10.1109/PAW-ATM56565.2022.00008

DO - 10.1109/PAW-ATM56565.2022.00008

M3 - Conference contribution

AN - SCOPUS:85148041049

T3 - Proceedings of PAW-ATM 2022: Parallel Applications Workshop, Alternatives to MPI+X, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis

SP - 26

EP - 38

BT - Proceedings of PAW-ATM 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 5th Annual IEEE/ACM Parallel Applications Workshop, Alternatives to MPI+X, PAW-ATM 2022

Y2 - 13 November 2022 through 18 November 2022

ER -

Herault T, Schuchart J, Valeev EF, Bosilca G. Composition of Algorithmic Building Blocks in Template Task Graphs. In Proceedings of PAW-ATM 2022: Parallel Applications Workshop, Alternatives to MPI+X, 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. 26-38. (Proceedings of PAW-ATM 2022: Parallel Applications Workshop, Alternatives to MPI+X, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis). doi: 10.1109/PAW-ATM56565.2022.00008

Composition of Algorithmic Building Blocks in Template Task Graphs

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this