DOI: 10.1007/s10766-007-0032-7 International Journal of Parallel Programming (© 2007) A Fast and AccurateTechnique for Mapping Parallel Applications on Stream-Oriented MPSoC Platforms with Communication Awareness Martino Ruggiero, 1 Alessio Guerri, 1 Davide Bertozzi, 2,3 Michela Milano 1 and Luca Benini 1 Received: 22 November 2006 / Accepted: 17 January 2007 The problem of allocating and scheduling precedence-constrained tasks on the processors of a distributed real-time system is NP-hard. As such, it has been traditionally tackled by means of heuristics, which provide only approx- imate or near-optimal solutions. This paper proposes a complete allocation and scheduling framework, and deploys an MPSoC virtual platform to val- idate the accuracy of modelling assumptions. The optimizer implements an efficient and exact approach to the mapping problem based on a decomposi- tion strategy. The allocation subproblem is solved through Integer Program- ming (IP) while the scheduling one through Constraint Programming (CP). The two solvers interact by means of an iterative procedure which has been proven to converge to the optimal solution. Experimental results show sig- nificant speed-ups w.r.t. pure IP and CP exact solution strategies as well as high accuracy with respect to cycle-accurate functional simulation. Two case studies further demonstrate the practical viability of our framework for real- life applications. KEY WORDS: MPSoCs; allocation; scheduling; Integer Programming; Constraint Programming. 1 University of Bologna, DEIS, Viale Risorgimento 2, Bologna 40136, Italy. E-mails: {mruggiero; aguerri; mmilano; lbenini}@deis.unibo.it 2 University of Ferrara, via Saragat 1, Ferrara 40132, Italy. E-mail: dbertozzi@ing.unife.it 3 To whom correspondence should be addressed. E-mail: dbertozzi@ing.unife.it © 2007 Springer Science+Business Media, LLC