{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:48:51Z","timestamp":1742914131299,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030024642"},{"type":"electronic","value":"9783030024659"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-02465-9_26","type":"book-chapter","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T20:06:48Z","timestamp":1548360408000},"page":"387-401","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Early Experience on Running OpenStaPLE on DAVIDE"],"prefix":"10.1007","author":[{"given":"Claudio","family":"Bonati","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enrico","family":"Calore","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Massimo","family":"D\u2019Elia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michele","family":"Mesiti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesco","family":"Negro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sebastiano Fabio","family":"Schifano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giorgio","family":"Silvi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raffaele","family":"Tripiccione","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,1,25]]},"reference":[{"key":"26_CR1","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1016\/S0920-5632(01)01664-4","volume":"106-107","author":"Claude Bernard","year":"2002","unstructured":"Bernard, C., et al.: Panel discussion on the cost of dynamical quarksimulations. Nucl. Phys. B-Proc. Suppl.106-107(Suppl. C), 199\u2013205 (2002). \n                      https:\/\/doi.org\/10.1016\/S0920-5632(01)01664-4","journal-title":"Nuclear Physics B - Proceedings Supplements"},{"key":"26_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1007\/11602569_41","volume-title":"High Performance Computing \u2013 HiPC 2005","author":"G Bilardi","year":"2005","unstructured":"Bilardi, G., Pietracaprina, A., Pucci, G., Schifano, F., Tripiccione, R.: The potential of on-chip multiprocessing for QCD machines. In: Bader, D.A., Parashar, M., Sridhar, V., Prasanna, V.K. (eds.) HiPC 2005. LNCS, vol. 3769, pp. 386\u2013397. Springer, Heidelberg (2005). \n                      https:\/\/doi.org\/10.1007\/11602569_41"},{"key":"26_CR3","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1016\/0010-4655(87)90172-X","volume":"45","author":"M Albanese","year":"1987","unstructured":"Albanese, M., et al.: The ape computer: an array processor optimized for lattice gauge theory simulations. Comput. Phys. Commun. 45, 345\u2013353 (1987). \n                      https:\/\/doi.org\/10.1016\/0010-4655(87)90172-X","journal-title":"Comput. Phys. Commun."},{"issue":"2.3","key":"26_CR4","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1147\/rd.492.0351","volume":"49","author":"P Boyle","year":"2005","unstructured":"Boyle, P., et al.: Overview of the QCDSP and QCDOC computers. IBM J. Res. Dev. 49(2.3), 351\u2013365 (2005). \n                      https:\/\/doi.org\/10.1147\/rd.492.0351","journal-title":"IBM J. Res. Dev."},{"issue":"1","key":"26_CR5","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/MCSE.2006.4","volume":"8","author":"F Belletti","year":"2006","unstructured":"Belletti, F., et al.: Computing for LQCD: Ape NEXT. Comput. Sci. Eng. 8(1), 50\u201361 (2006). \n                      https:\/\/doi.org\/10.1109\/MCSE.2006.4","journal-title":"Comput. Sci. Eng."},{"key":"26_CR6","doi-asserted-by":"publisher","unstructured":"Adiga, N.R., et al.: An overview of the BlueGene\/L Supercomputer. In: ACM\/IEEE 2002 Conference on Supercomputing, pp. 60\u201360, November 2002. \n                      https:\/\/doi.org\/10.1109\/SC.2002.10017","DOI":"10.1109\/SC.2002.10017"},{"issue":"6","key":"26_CR7","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1109\/MCSE.2008.153","volume":"10","author":"G Goldrian","year":"2008","unstructured":"Goldrian, G., et al.: QPACE: quantum chromodynamics parallel computing on the cell broadband engine. Comput. Sci. Eng. 10(6), 46\u201354 (2008). \n                      https:\/\/doi.org\/10.1109\/MCSE.2008.153","journal-title":"Comput. Sci. Eng."},{"issue":"2","key":"26_CR8","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1109\/MM.2011.108","volume":"32","author":"R Haring","year":"2012","unstructured":"Haring, R., et al.: The IBM Blue Gene\/Q Compute Chip. IEEE Micro 32(2), 48\u201360 (2012). \n                      https:\/\/doi.org\/10.1109\/MM.2011.108","journal-title":"IEEE Micro"},{"key":"26_CR9","unstructured":"OpenACC.org: OpenACC directives for accelerators. \n                      http:\/\/www.openacc-standard.org"},{"key":"26_CR10","unstructured":"OpenMP: The OpenMP API specification for parallel programming. \n                      http:\/\/www.openmp.org\/"},{"key":"26_CR11","doi-asserted-by":"publisher","unstructured":"Blair, S., Albing, C., Grund, A., Jocksch, A.: Accelerating an MPI lattice boltzmann code using OpenACC. In: Proceedings of the Second Workshop on Accelerator Programming Using Directives, WACCPD 2015, pp. 3:1\u20133:9. ACM, New York (2015). \n                      https:\/\/doi.org\/10.1145\/2832105.2832111","DOI":"10.1145\/2832105.2832111"},{"key":"26_CR12","doi-asserted-by":"publisher","unstructured":"Kraus, J., Schlottke, M., Adinetz, A., Pleiter, D.: Accelerating a C++ CFD code with OpenACC. In: 2014 First Workshop on Accelerator Programming using Directives (WACCPD), pp. 47\u201354 (2014). \n                      https:\/\/doi.org\/10.1109\/WACCPD.2014.11","DOI":"10.1109\/WACCPD.2014.11"},{"issue":"12","key":"26_CR13","doi-asserted-by":"publisher","first-page":"3485","DOI":"10.1002\/cpe.3862","volume":"28","author":"E Calore","year":"2016","unstructured":"Calore, E., Gabbana, A., Kraus, J., Schifano, S.F., Tripiccione, R.: Performance and portability of accelerated lattice Boltzmann applications with OpenACC. Concurr. Comput. Pract. Exp. 28(12), 3485\u20133502 (2016). \n                      https:\/\/doi.org\/10.1002\/cpe.3862","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Gupta, S., Majumdar, P.: Accelerating lattice QCD simulations with 2 flavours of staggered fermions on multiple GPUs using OpenACC - a first attempt \n                      arXiv:1710.09178\n                      \n                    , [hep-lat] (2017)","DOI":"10.1016\/j.cpc.2018.03.008"},{"issue":"05","key":"26_CR15","doi-asserted-by":"publisher","first-page":"1750063","DOI":"10.1142\/S0129183117500632","volume":"28","author":"Claudio Bonati","year":"2017","unstructured":"Bonati, C., et al.: Design and optimization of a portable LQCD Monte Carlo code using OpenACC. Int. J. Mod. Phys. C 28(5) (2017). \n                      https:\/\/doi.org\/10.1142\/S0129183117500632","journal-title":"International Journal of Modern Physics C"},{"issue":"01","key":"26_CR16","doi-asserted-by":"publisher","first-page":"1850010","DOI":"10.1142\/S0129183118500109","volume":"29","author":"Claudio Bonati","year":"2018","unstructured":"Bonati, C., et al.: Portable multi-node LQCD Monte Carlo simulations using OpenACC. Int. J. Mod. Phys. C 29(1) (2018). \n                      https:\/\/doi.org\/10.1142\/S0129183118500109","journal-title":"International Journal of Modern Physics C"},{"key":"26_CR17","doi-asserted-by":"publisher","unstructured":"Ahmad, W.A., et al.: Design of an energy aware petaflops class high performance cluster based on power architecture. In: 2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 964\u2013973, May 2017. \n                      https:\/\/doi.org\/10.1109\/IPDPSW.2017.22","DOI":"10.1109\/IPDPSW.2017.22"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Bonati, C., et al.: Roberge-Weiss endpoint and chiral symmetry restoration in \n                      \n                        \n                      \n                      $$N_f = 2+1$$\n                    . QCD \n                      arXiv:1807.02106\n                      \n                    , [hep-lat] (2018)","DOI":"10.1103\/PhysRevD.99.014502"},{"issue":"4","key":"26_CR19","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1016\/j.cpc.2011.12.011","volume":"183","author":"C Bonati","year":"2012","unstructured":"Bonati, C., Cossu, G., D\u2019Elia, M., Incardona, P.: Qcd simulations with staggered fermions on gpus. Comput. Phys. Commun. 183(4), 853\u2013863 (2012). \n                      https:\/\/doi.org\/10.1016\/j.cpc.2011.12.011","journal-title":"Comput. Phys. Commun."},{"key":"26_CR20","doi-asserted-by":"publisher","unstructured":"Bonati, C., et al.: Development of scientific software for HPC architectures using OpenACC: the case of LQCD. In: The 2015 International Workshop on Software Engineering for High Performance Computing in Science (SE4HPCS), pp. 9\u201315. ICSE Companion Proceedings (2015). \n                      https:\/\/doi.org\/10.1109\/SE4HPCS.2015.9","DOI":"10.1109\/SE4HPCS.2015.9"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Clark, M., Kennedy, A., Sroczynski, Z.: Exact 2+ 1 flavour RHMC simulations. arXiv hep-lat\/0409133 (2004)","DOI":"10.1016\/j.nuclphysbps.2004.11.192"},{"issue":"5","key":"26_CR22","doi-asserted-by":"publisher","first-page":"051601","DOI":"10.1103\/PhysRevLett.98.051601","volume":"98","author":"M Clark","year":"2007","unstructured":"Clark, M., Kennedy, A.: Accelerating dynamical-fermion computations using the rational hybrid monte carlo algorithm with multiple pseudofermion fields. Phys. Rev. Lett. 98(5), 051601 (2007)","journal-title":"Phys. Rev. Lett."},{"issue":"1","key":"26_CR23","doi-asserted-by":"publisher","first-page":"011502","DOI":"10.1103\/PhysRevD.75.011502","volume":"75","author":"M Clark","year":"2007","unstructured":"Clark, M., Kennedy, A.: Accelerating staggered-fermion dynamics with the rational hybrid Monte Carlo algorithm. Phys. Rev. D 75(1), 011502 (2007)","journal-title":"Phys. Rev. D"},{"issue":"2","key":"26_CR24","first-page":"216","volume":"195","author":"S Duane","year":"1987","unstructured":"Duane, S., Kennedy, A.D., Pendleton, B.J., Roweth, D.: Hybrid Monte Carlo. Phys. Rev. D 195(2), 216\u2013222 (1987)","journal-title":"Phys. Rev. D"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Kennedy, A.: Algorithms for dynamical fermions. arXiv hep-lat\/0607038 (2006)","DOI":"10.1142\/9789812790927_0002"},{"key":"26_CR26","unstructured":"Jegerlehner, B.: Krylov space solvers for shifted linear systems. arXiv hep-lat\/9612014 (1996)"},{"issue":"1","key":"26_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1002\/nla.499","volume":"14","author":"V Simoncini","year":"2007","unstructured":"Simoncini, V., Szyld, D.B.: Recent computational developments in krylov subspace methods for linear systems. Numer. Linear Algebr. Appl. 14(1), 1\u201359 (2007)","journal-title":"Numer. Linear Algebr. Appl."},{"issue":"1","key":"26_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0550-3213(83)90595-3","volume":"212","author":"P Weisz","year":"1983","unstructured":"Weisz, P.: Continuum limit improved lattice action for pure yang-mills theory (i). Nucl. Phys. B 212(1), 1\u201317 (1983)","journal-title":"Nucl. Phys. B"},{"issue":"3\u20134","key":"26_CR29","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1016\/0370-2693(83)91043-2","volume":"130","author":"G Curci","year":"1983","unstructured":"Curci, G., Menotti, P., Paffuti, G.: Symanzik\u2019s improved lagrangian for lattice gauge theory. Phys. Lett. B 130(3\u20134), 205\u2013208 (1983)","journal-title":"Phys. Lett. B"},{"key":"26_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1007\/978-3-319-17248-4_2","volume-title":"High Performance Computing Systems. Performance Modeling, Benchmarking, and Simulation","author":"AV Adinetz","year":"2015","unstructured":"Adinetz, A.V., et al.: Performance evaluation of scientific applications on POWER8. In: Jarvis, S.A., Wright, S.A., Hammond, S.D. (eds.) PMBS 2014. LNCS, vol. 8966, pp. 24\u201345. Springer, Cham (2015). \n                      https:\/\/doi.org\/10.1007\/978-3-319-17248-4_2"},{"key":"26_CR31","unstructured":"Eshelman, E.: Comparing NVLink vs PCI-e with NVIDIA Tesla P100 GPUs onOpenPOWER servers, January 2017. \n                      https:\/\/www.microway.com\/hpc-tech-tips\/comparing-nvlink-vs-pci-e-nvidia-tesla-p100-gpus-openpower-servers\/"},{"key":"26_CR32","unstructured":"Caldeira, A.B., Haug, V., Vetter, S.: IBM Power System S822LC for High Performance Computing Introduction and Technical Overview. IBM, October 2016"},{"key":"26_CR33","doi-asserted-by":"publisher","unstructured":"Eliuk, S., Upright, C., Skjellum, A.: dMath: Linear algebra for scaleoutGP-GPUs. In: 2016 IEEE 18th International Conference on High PerformanceComputing and Communications; IEEE 14th International Conference on SmartCity; IEEE 2nd International Conference on Data Science and Systems(HPCC\/SmartCity\/DSS), pp. 647\u2013654, December 2016. \n                      https:\/\/doi.org\/10.1109\/HPCC-SmartCity-DSS.2016.0096","DOI":"10.1109\/HPCC-SmartCity-DSS.2016.0096"},{"key":"26_CR34","doi-asserted-by":"publisher","unstructured":"Beneventi, F., Bartolini, A., Cavazzoni, C., Benini, L.: Continuous learning of HPC infrastructure models using big data analytics and in-memory processing tools. In: Proceedings of the Conference on Design, Automation & Test in Europe, DATE 2017, pp. 1038\u20131043 (2017). \n                      https:\/\/doi.org\/10.23919\/DATE.2017.7927143","DOI":"10.23919\/DATE.2017.7927143"},{"key":"26_CR35","doi-asserted-by":"publisher","unstructured":"Calore, E., Marchi, D., Schifano, S.F., Tripiccione, R.: Optimizing communications in multi-GPU Lattice Boltzmann simulations. In: 2015 International Conference on High Performance Computing Simulation (HPCS), pp. 55\u201362, July 2015. \n                      https:\/\/doi.org\/10.1109\/HPCSim.2015.7237021","DOI":"10.1109\/HPCSim.2015.7237021"},{"key":"26_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.parco.2016.08.005","volume":"58","author":"E Calore","year":"2016","unstructured":"Calore, E., Gabbana, A., Kraus, J., Pellegrini, E., Schifano, S.F., Tripiccione, R.: Massively parallel lattice-Boltzmann codes on large GPU clusters. Parallel Comput. 58, 1\u201324 (2016). \n                      https:\/\/doi.org\/10.1016\/j.parco.2016.08.005","journal-title":"Parallel Comput."}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-02465-9_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T05:02:32Z","timestamp":1558328552000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-02465-9_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030024642","9783030024659"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-02465-9_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"25 January 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISC High Performance","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on High Performance Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Frankfurt","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 June 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 June 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"33","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"supercomputing2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.isc-hpc.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}