Efficient execution of Kahn process networks on multi-processor systems using protothreads and windowed FIFOs
- 1 October 2009
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2009 IEEE/ACM/IFIP 7th Workshop on Embedded Systems for Real-Time Multimedia
Abstract
As single-processor systems are ceasing to scale effectively, multi-processor systems are becoming more and more popular. While there are many challenges of designing multi-processor systems in hardware, writing efficient parallel applications that utilize the computing capability of multiple processors may reveal to be even more challenging. In this paper, we introduce a framework that allows to efficiently execute applications expressed as Kahn process networks on multi-processor systems using protothreads and windowed FIFOs. We show that application developers can use this framework to achieve considerable speed-ups on the Cell Broadband Engine without needing to write architecture-specific code.Keywords
This publication has 20 references indexed in Scilit:
- A lightweight streaming layer for multicore executionACM SIGARCH Computer Architecture News, 2008
- Receiver-initiated message passing over RDMA Networks2008 IEEE International Symposium on Parallel and Distributed Processing, 2008
- Mapping Applications to Tiled Multiprocessor Embedded SystemsSeventh International Conference on Application of Concurrency To System Design (ACSD 2007), 2007
- Sequoia: Programming the Memory HierarchyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- ProtothreadsPublished by Association for Computing Machinery (ACM) ,2006
- UML-based multiprocessor SoC design frameworkACM Transactions on Embedded Computing Systems, 2006
- Requirements on the Execution of Kahn Process NetworksLecture Notes in Computer Science, 2003
- StreamIt: A Language for Streaming ApplicationsLecture Notes in Computer Science, 2002
- YAPI: application modeling for signal processing systemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2000
- Dataflow process networksProceedings of the IEEE, 1995