Tampere University of Technology

TUTCRIS Research Portal

Programming graphics processing units in the RVC-CAL dataflow language

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Details

Original languageEnglish
Title of host publicationElectronic Proceedings of the 2015 IEEE International Workshop on Signal Processing Systems, SiPS 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Volume2015-December
ISBN (Electronic)9781467396042
DOIs
Publication statusPublished - 2 Dec 2015
Publication typeA4 Article in a conference publication
EventIEEE International Workshop on Signal Processing Systems, SiPS 2015 - Hangzhou, China
Duration: 14 Oct 201516 Oct 2015

Conference

ConferenceIEEE International Workshop on Signal Processing Systems, SiPS 2015
CountryChina
CityHangzhou
Period14/10/1516/10/15

Abstract

The interest towards programming of streaming applications using dataflow models of computation has been increasing steadily in the recent years. Among the numerous dataflow formalisms, the ISO-standardized RVC-CAL dataflow language has offered a solid basis for programming tool development and research. To this date RVC-CAL programming tools have enabled transforming dataflow programs into concurrent executables for multicore processors, as well as for generating synthesizable hardware descriptions. In this paper it is shown how the RVC-CAL dataflow language can be used for programming graphics processing units (GPUs) with high efficiency. Considering the processing architectures of recent mobile and desktop computing devices, this advance is of high importance, as most consumer devices contain a graphics processing unit nowadays. To evaluate the proposed solution, the paper presents a video processing application case study. At best, the solution is shown to provide a speedup of 42× over single-threaded CPU execution.

Keywords

  • Dataflow computing, design automation, parallel processing