Current thinking about state-of-the-art infrastructure for computational science isdominatedbytwoconcepts: computingclustersandcomputationalgrids.Cl- ter architectures consistently hold the majority of slots on the list of Top 500 supercomputersites, andcomputationalGrids, inbothexperimentalandprod- tiondeployments, havebecome commonin academic, governmentandindustrial research communities around the world. The message passing is the dominant programmingparadigmforhigh-performancescienti?ccomputingonthesearc- tectures. MPI and PVM have emerged as standard programming environments in the message-passing paradigm. The EuroPVM/MPI conference series is the premierresearcheventforhigh-performanceparallelprogramminginthemessa- passingparadigm.Applications usingparallelmessage-passingprogramming, - oneered in this researchcommunity, are having signi?cant impact in the areas of computational science, such as bioinformatics, atmospheric sciences, chemistry, physics, astronomy, medicine, banking and ?nance, energy, etc. EuroPVM/MPIisa?agshipconferenceforthiscommunity, establishedasthe premier international forum for researchers, users and vendors to present their latest advances in MPI and PVM. EuroPVM/MPI is the forum where fun- mental aspects of message passing, implementations, standards, benchmarking, performance and new techniques are presented and discussed by researchers, developers and users from academia and industry. EuroPVM/MPI 2008 was organized by the UCD School of Computer S- ence and Informatics in Dublin, September 7-10, 2008. This was the 15th issue of the conference, which takes place each year at a di?erent European location. Previous meetings were held in Paris (2007), Bonn (2006), Sorrento (2005), - dapest(2004), Venice(2003), Linz(2002), Santorini(2001), Balatonfured(2000), Barcelona(1999), Liverpool(1998), Krakow(1997), Munich(1996), Lyon(1995), and Rome (1994). The main topics of the meeting were formal veri?cation of message passing programs, collective operations, parallel applications using the message passing paradigm, one-sided and point-to-point communication, MPI standard ext- sions or evolution, tools for performance evaluation and optimization, MPI-I/O, mutli-core and multithreaded architectures, and heterogen

This book features chapters which explore algorithms, programming languages, systems, tools and theoretical models aimed at high performance computing on heterogeneous networks of computers.