This article was accepted into the corpus but its outbound wikilinks were never NER-processed — typical at the deepest BFS hop or when the run's entity cap was reached. No expansion funnel to show.
| EuroPAR | |
|---|---|
| Name | EuroPAR |
| Type | Research consortium |
| Founded | 1990s |
| Headquarters | Europe |
| Focus | Parallel computing, high-performance computing |
EuroPAR EuroPAR is a European research consortium and conference series focusing on parallel computing, high-performance computing, and related computational science. It brings together researchers from institutions such as the European Commission, CERN, Max Planck Society, and École Polytechnique as well as industry partners like Intel, IBM, and NVIDIA. EuroPAR serves as a forum linking projects funded by Horizon 2020, FP7, and national agencies including the Science and Technology Facilities Council, Deutsche Forschungsgemeinschaft, and Agence Nationale de la Recherche.
EuroPAR functions as a multidisciplinary hub connecting research groups from University of Cambridge, ETH Zurich, Technical University of Munich, Imperial College London, and École Polytechnique Fédérale de Lausanne. Its activities intersect with initiatives such as the PRACE infrastructure, the European Grid Infrastructure, the European High Performance Computing Joint Undertaking, and collaborations with laboratories like Lawrence Berkeley National Laboratory and Los Alamos National Laboratory. EuroPAR emphasizes topics relevant to projects funded by Horizon Europe, collaborations with industry consortia like OpenMP ARB, and standards bodies including ISO and IEEE.
EuroPAR originated in the 1990s amid rising interest in distributed and parallel systems at venues such as Supercomputing Conference and International Conference on Parallel Processing. Early participants included researchers from University of Edinburgh, Barcelona Supercomputing Center, and CNR laboratories, and EuroPAR evolved alongside milestones like the development of MPI and the maturation of architectures from Cray Research and Fujitsu. Over successive decades EuroPAR adapted to trends from multicore processors championed by Intel and AMD to accelerators advanced by NVIDIA and research driven by the Human Brain Project and European Open Science Cloud.
EuroPAR is governed by a steering committee drawing members from academic institutions such as University of Oxford, Sorbonne University, Politecnico di Milano, and national labs like CEA. The committee coordinates with program chairs from universities including KU Leuven, TU Delft, and Università di Bologna and liaises with funding agencies such as European Research Council and industry partners including Microsoft Research and Google Research. Governance structures reference best practices similar to those used by the Association for Computing Machinery and the Institute of Electrical and Electronics Engineers.
EuroPAR addresses core topics like MPI research, scalable algorithms associated with graph processing, numerical methods used in computational fluid dynamics, and systems research covering operating system kernels and compiler optimization techniques. Participants investigate performance tuning for architectures from ARM Holdings and contend with challenges in fault tolerance studied in projects like Resilient HPC and data locality issues relevant to Hadoop and Spark. EuroPAR activities include workshops on accelerator programming models from OpenACC and CUDA and sessions touching on applied problems in bioinformatics, climate modeling, and computational chemistry.
EuroPAR organizes annual conferences, satellite workshops, and tutorials drawing attendees from SIGPLAN gatherings, SIGARCH symposia, and meetings such as ISC High Performance and SC Conference. Events often feature keynote speakers affiliated with National Institute of Standards and Technology, Argonne National Laboratory, and universities like Princeton University and Stanford University. The program typically includes peer-reviewed paper sessions, poster sessions influenced by formats used at NeurIPS and ICML, and panels with representatives from European Investment Bank and technology vendors such as Hewlett-Packard Enterprise.
Proceedings and special issues associated with EuroPAR are published in venues linked to Springer, ACM Digital Library, and journals including Journal of Parallel and Distributed Computing and Concurrency and Computation. Project outputs often feed into collaborative grants like H2020 projects and deliverables for initiatives such as EuroHPC and the E-Science framework. EuroPAR-affiliated projects have produced software libraries interoperable with PETSc, Trilinos, and middleware used in the Globus Toolkit ecosystem.
EuroPAR fosters collaborations among institutions including University of Manchester, University of Warsaw, Politehnica University of Bucharest, and industry partners such as Siemens and ARM Ltd., influencing standards and training adopted by research centers like Jülich Research Centre and BSC. Its community has contributed to citation networks overlapping with conferences like PODC, SPAA, and PPoPP, and influenced research agendas for funding bodies including European Commission directorates and national research councils. The consortium’s work has impacted applications ranging from astrophysics simulations performed at PRACE systems to machine learning workflows optimized for Graphcore and accelerator platforms.
Category:Computing conferences