Transformation of Sequential Program to KPN - An Overview

paper describes a general transformation theory in transforming a sequential C application to Kahn Process Network. It briefly describes in detail the two major transformation steps namely task partitioning and channel generation. We also discuss the previous approaches which automate the transformation from sequential model to parallel model and compare these with our approach.

[1]  Stephen A. Edwards,et al.  Pointer analysis for source-to-source transformations , 2005, Fifth IEEE International Workshop on Source Code Analysis and Manipulation (SCAM'05).

[2]  S.K. Nandy,et al.  A runtime mechanism for detection of artificial deadlocks in process networks , 2004, The 2004 47th Midwest Symposium on Circuits and Systems, 2004. MWSCAS '04..

[3]  Philippe Marquet,et al.  Design of a Real-Time Scheduler for Kahn Process Networks on Multiprocessor Systems , 2004, PDPTA.

[4]  Daniel J. Quinlan,et al.  Extending Automatic Parallelization to Optimize High-Level Abstractions for Multicore , 2009, IWOMP.

[5]  Niraj K. Jha,et al.  COSYN: Hardware-software co-synthesis of heterogeneous distributed embedded systems , 1999, IEEE Trans. Very Large Scale Integr. Syst..

[6]  Lothar Thiele,et al.  Efficient execution of Kahn process networks on multi-processor systems using protothreads and windowed FIFOs , 2009, 2009 IEEE/ACM/IFIP 7th Workshop on Embedded Systems for Real-Time Multimedia.

[7]  Kristof Denolf,et al.  SPRINT: A Tool to Generate Concurrent Transaction-Level Models from Sequential Code , 2007, EURASIP J. Adv. Signal Process..

[8]  Twan Basten,et al.  Requirements on the Execution of Kahn Process Networks , 2003, ESOP.