FFTX-IRIS: Towards Performance Portability and Heterogeneity for SPIRAL Generated Code

Sanil Rao; Mohammad Alaul Haque Monil; Het Mankad; Jeffrey Vetter; Franz Franchetti

doi:10.1145/3624062.3624242

FFTX-IRIS: Towards Performance Portability and Heterogeneity for SPIRAL Generated Code

Sanil Rao, Mohammad Alaul Haque Monil, Het Mankad, Jeffrey Vetter, Franz Franchetti

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

1 Scopus citations

Abstract

FFTX-IRIS is a dynamic system to efficiently utilize novel heterogeneous platforms. This system links two next-generation frameworks, FFTX and IRIS, to navigate the complexity of different hardware architectures. FFTX provides a runtime code generation framework for high-performance Fast Fourier Transform kernels. IRIS runtime provides portability and multi-device heterogeneity, allowing computation on any available compute resource. Together, FFTX-IRIS enables code generation, seamless portability, and performance without user involvement. We show the design of the FFTX-IRIS system along with an evaluation of various small FFT benchmarks. We also demonstrate multi-device heterogeneity of FFTX-IRIS with a larger stencil application.

Original language	English
Title of host publication	Proceedings of 2023 SC Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023
Publisher	Association for Computing Machinery
Pages	1635-1641
Number of pages	7
ISBN (Electronic)	9798400707858
DOIs	https://doi.org/10.1145/3624062.3624242
State	Published - Nov 12 2023
Event	2023 International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023 - Denver, United States Duration: Nov 12 2023 → Nov 17 2023

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	2023 International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023
Country/Territory	United States
City	Denver
Period	11/12/23 → 11/17/23

Funding

This work is funded, in part, by Bluestone, a X-Stack project in the DOE Advanced Scientific Computing Office with program manager Hal Finkel. This research used resources of the Experimental Computing Laboratory (ExCL) 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

FFT
Heterogeneity
IRIS
Performance portability
SPIRAL

Access to Document

10.1145/3624062.3624242

Cite this

Rao, S., Monil, M. A. H., Mankad, H., Vetter, J., & Franchetti, F. (2023). FFTX-IRIS: Towards Performance Portability and Heterogeneity for SPIRAL Generated Code. In Proceedings of 2023 SC Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023 (pp. 1635-1641). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3624062.3624242

Rao, Sanil ; Monil, Mohammad Alaul Haque ; Mankad, Het et al. / FFTX-IRIS : Towards Performance Portability and Heterogeneity for SPIRAL Generated Code. Proceedings of 2023 SC Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023. Association for Computing Machinery, 2023. pp. 1635-1641 (ACM International Conference Proceeding Series).

@inproceedings{7e5d329e1cef4044863f08d1e560cf87,

title = "FFTX-IRIS: Towards Performance Portability and Heterogeneity for SPIRAL Generated Code",

abstract = "FFTX-IRIS is a dynamic system to efficiently utilize novel heterogeneous platforms. This system links two next-generation frameworks, FFTX and IRIS, to navigate the complexity of different hardware architectures. FFTX provides a runtime code generation framework for high-performance Fast Fourier Transform kernels. IRIS runtime provides portability and multi-device heterogeneity, allowing computation on any available compute resource. Together, FFTX-IRIS enables code generation, seamless portability, and performance without user involvement. We show the design of the FFTX-IRIS system along with an evaluation of various small FFT benchmarks. We also demonstrate multi-device heterogeneity of FFTX-IRIS with a larger stencil application.",

keywords = "FFT, Heterogeneity, IRIS, Performance portability, SPIRAL",

author = "Sanil Rao and Monil, {Mohammad Alaul Haque} and Het Mankad and Jeffrey Vetter and Franz Franchetti",

note = "Publisher Copyright: {\textcopyright} 2023 Owner/Author.; 2023 International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023 ; Conference date: 12-11-2023 Through 17-11-2023",

year = "2023",

month = nov,

day = "12",

doi = "10.1145/3624062.3624242",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "1635--1641",

booktitle = "Proceedings of 2023 SC Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023",

}

Rao, S, Monil, MAH , Mankad, H , Vetter, J & Franchetti, F 2023, FFTX-IRIS: Towards Performance Portability and Heterogeneity for SPIRAL Generated Code. in Proceedings of 2023 SC Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 1635-1641, 2023 International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023, Denver, United States, 11/12/23. https://doi.org/10.1145/3624062.3624242

FFTX-IRIS: Towards Performance Portability and Heterogeneity for SPIRAL Generated Code. / Rao, Sanil; Monil, Mohammad Alaul Haque ; Mankad, Het et al.
Proceedings of 2023 SC Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023. Association for Computing Machinery, 2023. p. 1635-1641 (ACM International Conference Proceeding Series).

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

TY - GEN

T1 - FFTX-IRIS

T2 - 2023 International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023

AU - Rao, Sanil

AU - Monil, Mohammad Alaul Haque

AU - Mankad, Het

AU - Vetter, Jeffrey

AU - Franchetti, Franz

PY - 2023/11/12

Y1 - 2023/11/12

N2 - FFTX-IRIS is a dynamic system to efficiently utilize novel heterogeneous platforms. This system links two next-generation frameworks, FFTX and IRIS, to navigate the complexity of different hardware architectures. FFTX provides a runtime code generation framework for high-performance Fast Fourier Transform kernels. IRIS runtime provides portability and multi-device heterogeneity, allowing computation on any available compute resource. Together, FFTX-IRIS enables code generation, seamless portability, and performance without user involvement. We show the design of the FFTX-IRIS system along with an evaluation of various small FFT benchmarks. We also demonstrate multi-device heterogeneity of FFTX-IRIS with a larger stencil application.

AB - FFTX-IRIS is a dynamic system to efficiently utilize novel heterogeneous platforms. This system links two next-generation frameworks, FFTX and IRIS, to navigate the complexity of different hardware architectures. FFTX provides a runtime code generation framework for high-performance Fast Fourier Transform kernels. IRIS runtime provides portability and multi-device heterogeneity, allowing computation on any available compute resource. Together, FFTX-IRIS enables code generation, seamless portability, and performance without user involvement. We show the design of the FFTX-IRIS system along with an evaluation of various small FFT benchmarks. We also demonstrate multi-device heterogeneity of FFTX-IRIS with a larger stencil application.

KW - FFT

KW - Heterogeneity

KW - IRIS

KW - Performance portability

KW - SPIRAL

UR - http://www.scopus.com/inward/record.url?scp=85178116003&partnerID=8YFLogxK

U2 - 10.1145/3624062.3624242

DO - 10.1145/3624062.3624242

M3 - Conference contribution

AN - SCOPUS:85178116003

T3 - ACM International Conference Proceeding Series

SP - 1635

EP - 1641

BT - Proceedings of 2023 SC Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023

PB - Association for Computing Machinery

Y2 - 12 November 2023 through 17 November 2023

ER -

Rao S, Monil MAH , Mankad H , Vetter J, Franchetti F. FFTX-IRIS: Towards Performance Portability and Heterogeneity for SPIRAL Generated Code. In Proceedings of 2023 SC Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023. Association for Computing Machinery. 2023. p. 1635-1641. (ACM International Conference Proceeding Series). doi: 10.1145/3624062.3624242

FFTX-IRIS: Towards Performance Portability and Heterogeneity for SPIRAL Generated Code

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this