Skip to main content
Kent Academic Repository

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)

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,
Divisions: 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: 08 Dec 2022 16:49 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

  • Depositors only (login required):

Total unique views for this document in KAR since July 2020. For more details click on the image.