Abstract
Streaming applications are generally modelled by dataflow graphs, among which Synchronous Dataflow Graphs (SDFGs) are one of the most popular models. Self-timed Execution (STE) based methods are proved to be very powerful for analyzing and scheduling SDFGs. In this paper, an extension of STE is presented based on which, an exact algorithm is proposed to find the minimal memory usage for buffering to guarantee execution under maximal throughput (rate-optimal execution) of an SDFG on a multicore system. Experimental results show that the proposed exact algorithm obtains less buffer usage than a widely used state-of-art heuristic in a number of cases and equal buffer usage in the rest. In addition, a heuristic is proposed as an efficient approximate method, which gives equal or less buffer usage than a state-of-art heuristic.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
