Portable and Efficient Dense Linear Algebra in the Beginning of the Exascale Era

Mark Gates; Asim Yarkhan; Dalal Sukkari; Kadir Akbudak; Sebastien Cayrols; Daniel Bielich; Ahmad Abdelfattah; Mohammed Al Farhan; Jack Dongarra

doi:10.1109/P3HPC56579.2022.00009

Portable and Efficient Dense Linear Algebra in the Beginning of the Exascale Era

Mark Gates, Asim Yarkhan, Dalal Sukkari, Kadir Akbudak, Sebastien Cayrols, Daniel Bielich, Ahmad Abdelfattah, Mohammed Al Farhan, Jack Dongarra

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

4 Scopus citations

Abstract

The SLATE project is implementing a distributed dense linear algebra library for highly-scalable distributed-memory accelerator-based computer systems. The goal is to provide a library that can be easily ported to different hardware (CPUs, GPUs, accelerators) and will provide high performance for machines into the future. Current ports include CPUs, CUDA, ROCm, and oneAPI. We achieve both performance and portability by leveraging several layers and abstractions, including OpenMP tasks to track data dependencies, MPI for distributed communication, and the BLAS++ and LAPACK++ libraries developed as a portable layer across vendor-optimized CPU and GPU BLAS and LAPACK functionality. We rely on the C++ standard library and templating to reduce code duplication for better maintainability. The few kernels not present in BLAS are implemented in CUDA, HIP, and OpenMP target offload, and are easily ported to new platforms.

Original language	English
Title of host publication	Proceedings of P3HPC 2022
Subtitle of host publication	2022 International Workshop on Performance, Portability and Productivity in HPC, 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	36-46
Number of pages	11
ISBN (Electronic)	9781665460217
DOIs	https://doi.org/10.1109/P3HPC56579.2022.00009
State	Published - 2022
Externally published	Yes
Event	5th IEEE/ACM International Workshop on Performance, Portability and Productivity in HPC, P3HPC 2022 - Dallas, United States Duration: Nov 13 2022 → Nov 18 2022

Publication series

Name	Proceedings of P3HPC 2022: 2022 International Workshop on Performance, Portability and Productivity in HPC, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis

Conference

Conference	5th IEEE/ACM International Workshop on Performance, Portability and Productivity in HPC, P3HPC 2022
Country/Territory	United States
City	Dallas
Period	11/13/22 → 11/18/22

Funding

This research was supported by the Exascale Computing Project (17-SC-20-SC), a joint project of the U.S. Department of Energy’s Office of Science and National Nuclear Security Administration, responsible for delivering a capable exascale ecosystem, including software, applications, and hardware technology, to support the nation’s exascale computing imperative. This research used resources of the Oak Ridge Leadership Computing Facility at the Oak Ridge National Laboratory, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725.

Keywords

GPU computing
distributed computing
numerical linear algebra

Access to Document

10.1109/P3HPC56579.2022.00009

Cite this

Gates, M., Yarkhan, A., Sukkari, D., Akbudak, K., Cayrols, S., Bielich, D., Abdelfattah, A., Farhan, M. A., & Dongarra, J. (2022). Portable and Efficient Dense Linear Algebra in the Beginning of the Exascale Era. In Proceedings of P3HPC 2022: 2022 International Workshop on Performance, Portability and Productivity in HPC, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis (pp. 36-46). (Proceedings of P3HPC 2022: 2022 International Workshop on Performance, Portability and Productivity in HPC, 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/P3HPC56579.2022.00009

Gates, Mark ; Yarkhan, Asim ; Sukkari, Dalal et al. / Portable and Efficient Dense Linear Algebra in the Beginning of the Exascale Era. Proceedings of P3HPC 2022: 2022 International Workshop on Performance, Portability and Productivity in HPC, 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. 36-46 (Proceedings of P3HPC 2022: 2022 International Workshop on Performance, Portability and Productivity in HPC, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis).

@inproceedings{8f86db6cf1c84cfab5412b91a90a871c,

title = "Portable and Efficient Dense Linear Algebra in the Beginning of the Exascale Era",

abstract = "The SLATE project is implementing a distributed dense linear algebra library for highly-scalable distributed-memory accelerator-based computer systems. The goal is to provide a library that can be easily ported to different hardware (CPUs, GPUs, accelerators) and will provide high performance for machines into the future. Current ports include CPUs, CUDA, ROCm, and oneAPI. We achieve both performance and portability by leveraging several layers and abstractions, including OpenMP tasks to track data dependencies, MPI for distributed communication, and the BLAS++ and LAPACK++ libraries developed as a portable layer across vendor-optimized CPU and GPU BLAS and LAPACK functionality. We rely on the C++ standard library and templating to reduce code duplication for better maintainability. The few kernels not present in BLAS are implemented in CUDA, HIP, and OpenMP target offload, and are easily ported to new platforms.",

keywords = "GPU computing, distributed computing, numerical linear algebra",

author = "Mark Gates and Asim Yarkhan and Dalal Sukkari and Kadir Akbudak and Sebastien Cayrols and Daniel Bielich and Ahmad Abdelfattah and Farhan, {Mohammed Al} and Jack Dongarra",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 5th IEEE/ACM International Workshop on Performance, Portability and Productivity in HPC, P3HPC 2022 ; Conference date: 13-11-2022 Through 18-11-2022",

year = "2022",

doi = "10.1109/P3HPC56579.2022.00009",

language = "English",

series = "Proceedings of P3HPC 2022: 2022 International Workshop on Performance, Portability and Productivity in HPC, 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 = "36--46",

booktitle = "Proceedings of P3HPC 2022",

}

Gates, M, Yarkhan, A, Sukkari, D, Akbudak, K, Cayrols, S, Bielich, D, Abdelfattah, A, Farhan, MA & Dongarra, J 2022, Portable and Efficient Dense Linear Algebra in the Beginning of the Exascale Era. in Proceedings of P3HPC 2022: 2022 International Workshop on Performance, Portability and Productivity in HPC, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis. Proceedings of P3HPC 2022: 2022 International Workshop on Performance, Portability and Productivity in HPC, 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. 36-46, 5th IEEE/ACM International Workshop on Performance, Portability and Productivity in HPC, P3HPC 2022, Dallas, United States, 11/13/22. https://doi.org/10.1109/P3HPC56579.2022.00009

Portable and Efficient Dense Linear Algebra in the Beginning of the Exascale Era. / Gates, Mark; Yarkhan, Asim; Sukkari, Dalal et al.
Proceedings of P3HPC 2022: 2022 International Workshop on Performance, Portability and Productivity in HPC, 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. 36-46 (Proceedings of P3HPC 2022: 2022 International Workshop on Performance, Portability and Productivity in HPC, 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 - Portable and Efficient Dense Linear Algebra in the Beginning of the Exascale Era

AU - Gates, Mark

AU - Yarkhan, Asim

AU - Sukkari, Dalal

AU - Akbudak, Kadir

AU - Cayrols, Sebastien

AU - Bielich, Daniel

AU - Abdelfattah, Ahmad

AU - Farhan, Mohammed Al

AU - Dongarra, Jack

PY - 2022

Y1 - 2022

N2 - The SLATE project is implementing a distributed dense linear algebra library for highly-scalable distributed-memory accelerator-based computer systems. The goal is to provide a library that can be easily ported to different hardware (CPUs, GPUs, accelerators) and will provide high performance for machines into the future. Current ports include CPUs, CUDA, ROCm, and oneAPI. We achieve both performance and portability by leveraging several layers and abstractions, including OpenMP tasks to track data dependencies, MPI for distributed communication, and the BLAS++ and LAPACK++ libraries developed as a portable layer across vendor-optimized CPU and GPU BLAS and LAPACK functionality. We rely on the C++ standard library and templating to reduce code duplication for better maintainability. The few kernels not present in BLAS are implemented in CUDA, HIP, and OpenMP target offload, and are easily ported to new platforms.

AB - The SLATE project is implementing a distributed dense linear algebra library for highly-scalable distributed-memory accelerator-based computer systems. The goal is to provide a library that can be easily ported to different hardware (CPUs, GPUs, accelerators) and will provide high performance for machines into the future. Current ports include CPUs, CUDA, ROCm, and oneAPI. We achieve both performance and portability by leveraging several layers and abstractions, including OpenMP tasks to track data dependencies, MPI for distributed communication, and the BLAS++ and LAPACK++ libraries developed as a portable layer across vendor-optimized CPU and GPU BLAS and LAPACK functionality. We rely on the C++ standard library and templating to reduce code duplication for better maintainability. The few kernels not present in BLAS are implemented in CUDA, HIP, and OpenMP target offload, and are easily ported to new platforms.

KW - GPU computing

KW - distributed computing

KW - numerical linear algebra

UR - http://www.scopus.com/inward/record.url?scp=85147909366&partnerID=8YFLogxK

U2 - 10.1109/P3HPC56579.2022.00009

DO - 10.1109/P3HPC56579.2022.00009

M3 - Conference contribution

AN - SCOPUS:85147909366

T3 - Proceedings of P3HPC 2022: 2022 International Workshop on Performance, Portability and Productivity in HPC, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis

SP - 36

EP - 46

BT - Proceedings of P3HPC 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 5th IEEE/ACM International Workshop on Performance, Portability and Productivity in HPC, P3HPC 2022

Y2 - 13 November 2022 through 18 November 2022

ER -

Gates M, Yarkhan A, Sukkari D, Akbudak K, Cayrols S, Bielich D et al. Portable and Efficient Dense Linear Algebra in the Beginning of the Exascale Era. In Proceedings of P3HPC 2022: 2022 International Workshop on Performance, Portability and Productivity in HPC, 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. 36-46. (Proceedings of P3HPC 2022: 2022 International Workshop on Performance, Portability and Productivity in HPC, Held in conjunction with SC 2022: The International Conference for High Performance Computing, Networking, Storage and Analysis). doi: 10.1109/P3HPC56579.2022.00009

Portable and Efficient Dense Linear Algebra in the Beginning of the Exascale Era

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this