Converting data-parallelism to task-parallelism by rewrites: purely functional programs across multiple GPUs

Svensson, Bo Joel, Vollmer, Michael, Holk, Eric, McDonell, Trevor L., Newton, Ryan R. (2015) Converting data-parallelism to task-parallelism by rewrites: purely functional programs across multiple GPUs. In: FHPC 2015: Proceedings of the 4th ACM SIGPLAN Workshop on Functional High-Performance Computing. . pp. 12-22. (doi:10.1145/2808091.2808093) (KAR id:95507)

PDF Publisher pdf Language: English
Download this file (PDF/762kB)	Preview
Request a format suitable for use with assistive technology e.g. a screenreader
Official URL: https://doi.org/10.1145/2808091.2808093

Abstract

High-level domain-specific languages for array processing on the GPU are increasingly common, but they typically only run on a single GPU. As computational power is distributed across more devices, languages must target multiple devices simultaneously. To this end, we present a compositional translation that fissions data-parallel programs in the Accelerate language, allowing subsequent compiler and runtime stages to map computations onto multiple devices for improved performance---even programs that begin as a single data-parallel kernel.

Item Type:	Conference or workshop item (Paper)
DOI/Identification number:	10.1145/2808091.2808093
Subjects:	Q Science > QA Mathematics (inc Computing science) > QA 76 Software, computer programming,
Institutional Unit:	Schools > School of Computing
Former Institutional Unit:	Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing
Depositing User:	Michael Vollmer
Date Deposited:	07 Dec 2022 21:17 UTC
Last Modified:	22 Jul 2025 09:10 UTC
Resource URI:	https://kar.kent.ac.uk/id/eprint/95507 (The current URI for this page, for reference purposes)

University of Kent Author Information

Vollmer, Michael.

Creator's ORCID:	https://orcid.org/0000-0002-0496-8268
CReDIT Contributor Roles:

Depositors only (login required):

Altmetric

Total Views

Total unique views of this page since July 2020. For more details click on the image.