This special issue of Concurrency and Computation: Practice and Experience contains revised and extended versions of selected papers presented at the Euro-Par 2010 conference.
Euro-Par—the European Conference on Parallel Computing—is an annual series of international conferences dedicated to the promotion and the advancement of all aspects of parallel and distributed computing. Euro-Par covers a wide spectrum of topics from algorithms and theory to software technology and hardware-related issues, with application areas ranging from scientific to mobile and cloud computing. The main audience of Euro-Par are the researchers in academic institutions, government laboratories, and industrial organizations.
Euro-Par 2010, the 16th conference in the Euro-Par series, was organized by the Institute for High Performance Computing and Networking of the Italian National Research Council and was held at the Hotel Continental Terme on the Italian island of Ischia, in the Naples Bay.
Fourteen broad topics were defined and advertised, covering a large variety of aspects of parallel and distributed computing. The call for papers attracted a total of 256 submissions. The submitted papers were reviewed at least three and, in many cases, four times. A total of 90 papers were finally accepted for publication. This makes a global acceptance rate of 35%. The authors of the accepted papers come from 24 countries, with the four main contributing countries—USA, France, Spain, and Germany—accounting for about 55% of the authors. The distribution of authors followed the pattern typical for a Euro-Par conference: of the 10 authors, this year, six have been academic researchers, three PhD students, and one from industry.
The topical distribution of the papers in the proceedings of Euro-Par 2010 reflects the current trends in the field of parallel and distributed computing: 18 of 90 papers are devoted to the relatively new topic Multicore and Manycore Programming. This figure was 11 in 2009 and was even lower in 2008 when the subject was part of the topic High-Performance Architectures and Compilers. On the other hand, the well-established Euro-Par topics such as Support Tools and Environments or Scheduling and Load-Balancing, for instance, have remained quite stable throughout the years. These figures demonstrate that the topic structure of Euro-Par has the flexibility to adapt to current trends in a wide spectrum of research areas.
With its topic structure, Euro-Par has been filling two complementary rôles: as a regular meeting place for established communities and as a place to develop new communities. In recent years, the latter rôle has been strengthened by the introduction of satellite workshops, at which researchers can meet initially and form a new community that later settles and flourishes in other fora. In 2010, the number of satellite workshops was higher than ever before, 11, and we strive to have it grow further, maintaining the Euro-Par claim of being the wide-spectrum conference on parallelism in Europe.
Returning to the spread of papers in 2010, based on the results of the reviews and a majority opinion of the topic program committees, several papers were recommended for a special journal issue. The authors were contacted at the conference and invited to submit revised and extended versions of their papers. These new versions were reviewed independently by three reviewers; two had also reviewed the conference version, the third had not. Eventually, eight papers were accepted for publication.
Topic 7 on Peer-to-Peer Computing is represented by the paper Meeting subscriber-defined QoS constraints in publish/subscribe systems, authored by Muhammad Adnan Tariq, Boris Koldehofe, Gerald George Koch, Imran Khan, and Kurt Rothermel from the University of Stuttgart, Germany . Current distributed publish/subscribe systems consider all participants to have similar QoS requirements and contribute equally to the system's resources. The authors propose a peer-to-peer-based approach to satisfy the individual delay requirements of subscribers in the presence of bandwidth constraints. This way, subscribers can adjust the granularity of their subscriptions dynamically according to their bandwidth constraints and delay requirements. Simulations evaluate the approach.
Topic 8 on Distributed Systems and Algorithms is represented by two papers, both from IRISA, Rennes, France.
The liveness of concurrent objects despite asynchrony and failures is a fundamental problem. The strongest progress condition is known as wait-freedom, in asynchronous read/write systems with n processes also termed more precisely as n-wait-freedom. In the paper A liveness condition for concurrent objects: x-wait-freedom , Damien Imbs and Michel Raynal relax the requirement of wait-freedom to a subset of x processes (x ≤ n), which are considered particularly important. This progress condition reflects many practical scenarios more accurately. The authors present a consensus algorithm that satisfies this progress condition and prove it correct.
The paper Active optimistic and distributed message logging for message passing applications by Thomas Ropars and Christine Morin  proposes a scalable message logging technique, called distributed event logging. The technique rests on a gossip-based dissemination protocol that makes application processes aware of new stable events and can be combined with the authors’ optimistic message logging protocol, called O2P, to provide an efficient and scalable solution for fault tolerance in message passing applications. The authors also compare the performance of their approach, based on both a pessimistic message logging protocol and O2P, with a centralized event logger.
Topic 10 on Parallel Numerical Algorithms is represented by the paper Computing subdominant unstable modes of turbulent plasma with a parallel Jacobi-Davidson eigensolver, authored by Eloy Romero and Jose E. Roman from Valencia Technical University, Spain . The authors report on the development and the use of a parallel Jacobi-Davidson eigenvalue solver integrated into the Scalable Library for Eigenvalue Problem Computations in one application related to the simulation of plasma turbulence. The main focus of the numerical experiments is on the parallel computation of rightmost eigenvalues of a large-scale complex non-Hermitian matrix that is not available explicitly.
Topic 13 on Multicore and Manycore Programming is represented by two papers.
Hans Zima, Mark James, and Paul Springer from the National Aeronautics and Space Administration (NASA) Jet Propulsion Laboratory in the USA present Fault-tolerant on-board computing for robotic space missions . The authors’ goal is to provide software fault tolerance for deep-space robotic NASA missions. The focus is on introspection-based fault tolerance, where the program execution is monitored to identify, locate, and analyze errors. Fault tolerance assertions can be provided by the user via domain-specific knowledge or via the results of a static or dynamic program analysis.
Biological sequence comparison is one of the most important tasks in bioinformatics. In the paper Scalable multicore architectures for long DNA sequence comparison , Friman Sánchez from the Technical University of Catalonia and Felipe Cabarcas, Alex Ramirez, and Mateo Valero from the Barcelona Supercomputing Center, Spain, propose two implementations of the Smith–Waterman algorithm in the IBM Cell/BE architecture: one centralized and one distributed. The centralized approach uses the shared memory for communication and the distributed approach uses local buffers and a delayed synchronization protocol. Simulation experiments produced very good results for the distributed approach.
Topic 12 on Theory and Algorithms for Parallel Computation is represented by the paper Multi-organization scheduling approximation algorithms authored by Johanne Cohen of the University of Versailles, Daniel Cordeiro and Denis Trystram of Grenoble University, and Frédéric Wagner of the Institut Universitaire de France . The authors consider the competition of heterogeneous organizations that make their resources mutually available and that compete to satisfy their own resource requirements. Optimization of the local objective functions of makespan and average completion time are both NP-hard. A notion of selfishness serves to approximate the solution. A selfish organization does not allow schedules in which jobs of others are finished before all own jobs are started. The authors prove several complexity results.
Topic 13 on High-Performance Networks is represented by the paper Cost-effective queue schemes for reducing head-of-line blocking in fat-trees authored by Jesus Escudero-Sahuquillo, Pedro Javier Garcia and Francisco José Quiles from the University of Castilla-La Mancha, and Jose Flich and Jose Duato from Valencia Technical University, Spain . When several packets from different input ports seek concurrently access to the same output port, only one can be successful at a time. If this contention persists, also other packets, which seek access to free output ports, will be delayed. This is called the head-of-line (HoL) problem. As a network topology, k-ary n-trees, which form a subset of the fat-trees family, are considered. The fat-tree is one of the most common topologies among the interconnection networks of the systems currently used for high-performance parallel computing. Besides other advantages, fat-trees allow the use of simple but very efficient routing schemes. The authors eliminate HoL blocking by adding a number of extra queues to switches, combined with a suitable routing policy.
Concluding this preface, we would like to thank Professors Geoffrey Fox and Luc Moreau, editors of this journal, for their support of this special issue. We would also like to thank our peers who assisted us in reviewing the papers and helped strengthen the final versions. Last, but not least, we also appreciate the support of Springer-Verlag, who agreed to the publication of the extended versions of the articles that appeared originally in the series Lecture Notes in Computer Science.