APEnet+ Publications

Papers on Journals or Conference Proceedings

2013

• R. Ammendola et al., “APEnet+ 34 Gbps data transmission system and custom transmission logic,” in JINST, Journal of Instrumentation, Proceedings of Topical Workshop on Electronics for Particle Physics (TWEPP) 2013, IOP Publishing, 2013. To be published.

• R. Ammendola, M. Bernaschi, A. Biagioni, M. Bisson, M. Fatica, O. Frezza, F. Lo Cicero, A. Lonardo, E. Mastrostefano, P. S. Paolucci, D. Rossetti, F. Simula, L. Tosoratto, and P. Vicini, “GPU Techniques Applied to a Cluster Interconnect,” in Parallel and Distributed Processing Symposium Workshops PhD Forum (IPDPSW), 2013 IEEE 27^th International, pp. 806–815, 2013.

• R. Ammendola et al., “Virtualtohysical Address Translation for an FPGAbased Interconnect with Host and GPU Remote DMA Capabilities.,” in Field-Programmable Technology (FPT), 2013 International Conference on, 2013. To be published.

• R. Ammendola et al., “Design and implementation of a modular, low latency, fault-aware, fpga-based network interface.,” in Track on Interconnect architectures for reconfigurable computing systems, held at Reconfigurable Computing and FPGAs (ReConFig), 2013 International Conference on, 2013. to be published.

• R. Ammendola et al., “Architectural improvements and 28nm FPGA implementation of the APEnet+ 3D Torus network for hybrid HPC systems,” in 20th International Conference on Computing in High Energy and Nuclear Physics (CHEP2013), 2013. To be published.

• R. Ammendola et al., “’Mutual Watch-dog Networking’: Distributed Awareness of Faults and Critical Events in Petascale/Exascale systems,” arXiv:1307.0433, July 2013.

• M. Bernaschi, M. Bisson, and D. Rossetti, “Benchmarking of communication techniques for gpus,” Journal of Parallel and Distributed Computing, vol. 73, no. 2, pp. 250 – 255, 2013. http://www.sciencedirect.com/science/article/pii/S0743731512002213.

2012

• R. Ammendola, A. Biagioni, O. Frezza, F. Lo Cicero, A. Lonardo, P. S. Paolucci, D. Rossetti, A. Salamon, F. Simula, L. Tosoratto, and P. Vicini, “A 34 Gbps data transmission system with FPGAs embedded transceivers and QSFP+ modules,” in Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC), 2012 IEEE, pp. 872–876, 2012.

• R. Ammendola et al., “APEnet+: a 3D Torus network optimized for GPU-based HPC systems,” Journal of Physics: Conference Series, vol. 396, no. 4, p. 042059, 2012.

• M. Bisson, M. Bernaschi, E. Mastrostefano, and D. Rossetti, “Breadth first search on apenet+..” [2 - 1.pdf|http://cass-mt.pnnl.gov/docs/Session 2 - 1.pdf]. IA3 Workshop on Irregular Applications: Architectures and Algorithms, in conjunction with Super Computing 2012.

2011

• R. Ammendola, A. Biagioni, O. Frezza, F. Lo Cicero, A. Lonardo, P. S. Paolucci, D. Rossetti, A. Salamon, G. Salina, F. Simula, et al., “Apenet+: high bandwidth 3d torus direct network for petaflops scale commodity clusters,” Journal of Physics: Conference Series, vol. 331, no. 5, p. 052029, 2011.

• D. Rossetti, R. Ammendola, P. Vicini, A. Biagioni, O. Frezza, F. Lo Cicero, A. Lonardo, P. S. Paolucci, F. Simula, and L. Tosoratto, “Apenet+ project status,” in Proceedings of the XXIX International Symposium on Lattice Field Theory (Lattice 2011). July 10-16, 2011. Squaw Valley, Lake Tahoe, California, id. 45 Online at http://pos.sissa.it/cgi-bin/reader/conf.cgi?confid=139, vol. 1, p. 45, 2011.

• *R. Ammendola et al., “QUonG: A GPU-based HPC system dedicated to LQCD computing,” in Application Accelerators in High-Performance Computing (SAAHPC), 2011 Symposium on, pp. 113–122, 2011.

2010

• R. Ammendola, A. Biagioni, G. Chiodi, O. Frezza, F. Lo Cicero, A. Lonardo, R. Lunadei, P. S. Paolucci, D. Rossetti, A. Salamon, et al., “High-speed data transfer with fpgas and QSFP+ modules,” Journal of Instrumentation, vol. 5, no. 12, p. C12019, 2010.

• R. Ammendola, A. Biagioni, O. Frezza, F. Lo Cicero, A. Lonardo, P. S. Paolucci, R. Petronzio, D. Rossetti, A. Salamon, G. Salina, et al., “Apenet+: a 3d toroidal network enabling petaflops scale lattice qcd simulations on commodity clusters,” arXiv:1012.0253, 2010.

• R. Ammendola, A. Biagioni, O. Frezza, F. Lo Cicero, A. Lonardo, P.S. Paolucci, D. Rossetti, A. Salamon, G. Salina, F. Simula, L. Tosoratto, P. Vicini - Mastering multi-GPU computing on a torus network - GPU Technology Conference 2010 (GTC) - poster

Talks and other publications

• Davide Rossetti, GPU peer-to-peer techniques applied to a cluster interconnect - talk at CASS 2013 workshop in Boston (Communication Architecture for Scalable Systems), 20 May 2013. PDF available here
• Piero Vicini, Analysis of performance improvements for host and gpu interface of the APENet+ 3D Torus network. - talk at ACAT 2013 (15th International Workshop on advanced computing and analysis techniques in physics) in Beijing, 18 May 2013. Presentation available here
• Davide Rossetti, Breadth First Search on APEnet+ - talk at IA^3 Workshop on Irregular Applications at SC12 conference, 10 Nov 2012. Presentation available here
• Roberto Ammendola, APEnet+: a 12x34 Gbps data transmission system with FPGAs embedded transceivers and QSFP+ modules. - Poster at NSS-12 Nuclear Science Symposium. Anaheim, California, October 29 – November 3, 2012. PDF available here
• Davide Rossetti, Multi GPU simulations: status and perspectives - talk given at New Frontiers in Lattice Gauge Theory workshop in Florence, 26 Sep 2012.
• Davide Rossetti, Leveraging NVIDIA GPUDirect on APEnet+ 3D Torus Cluster Interconnect - talk given at GTC 2012 conference. Video and pdf available here
• Davide Rossetti, Remote Direct Memory Access Between NVIDIA GPUs with the APEnet 3D Torus Interconnect - talk given at NVidia booth at Supercomputing 2011 conference. Video available here. PPTX of presentation is here
• Piero Vicini, QUonG: a GPU-based parallel processor system for scientific computing - talk given at SM&FT 2011 conference, Bari september 2011. Presentation available here
• Piero Vicini - talk given at SAAHPC Symposium on Application Accelerators in High-Performance Computing 2011, July 19-20, 2011. University of Tennessee Conference Center, Knoxville, Tennessee.
• Davide Rossetti, Status of the APEnet+ project - talk given at Lattice 2011 Conference, July 10-16 2011, Squaw Valley CA. Presentation avaialble here
• Davide Rossetti, Many-core platforms and HEP experiments computing - talk given at SuperB Computing R&D workshop, 4-7 July 2011, Ferrara, Italy.
• Davide Rossetti, Many-core platforms and HEP experiments computing - talk given at XVII SuperB Workshop and Kick Off meeting, May 28 - June 2 2011, Isola d'Elba, Italy
• Davide Rossetti, Mastering Multi-GPU Computing on a Torus Network - poster at GTC 2010 conference, Sept 2010, San Jose CA.
• Roberto Ammendola APENet+: a 3D Toroidal Network Enabling PetaFlops Scale Lattice QCD Simulations on Commodity Clusters - talk given at Lattice 2010, Villasimius 18 June 2010 [1].
• Roberto Ammendola, Review on the GPU-related activities in INFN - talk given at INFN CCR & GRID workshop, 17-21 May 2010, Acireale, Italy