{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T15:16:41Z","timestamp":1784906201108,"version":"3.55.0"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032299208","type":"print"},{"value":"9783032299215","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-29921-5_3","type":"book-chapter","created":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T20:16:59Z","timestamp":1782159419000},"page":"32-47","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-GPU Hybrid Particle-in-Cell Monte Carlo Simulations for\u00a0Exascale Computing Systems"],"prefix":"10.1007","author":[{"given":"Jeremy J.","family":"Williams","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jordy","family":"Trilaksono","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan","family":"Costea","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Ju","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Pennati","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonah","family":"Ekelund","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Tskhakaya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leon","family":"Kos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ales","family":"Podolnik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jakub","family":"Hromadka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Allen D.","family":"Malony","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sameer","family":"Shende","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tilman","family":"Dannert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frank","family":"Jenko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erwin","family":"Laure","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefano","family":"Markidis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,23]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Chaudhury, B.: Hybrid Parallelization of Particle in Cell Monte Carlo Collision (PIC-MCC) Algorithm for Simulation of Low Temperature Plasmas. In: Workshop on Software Challenges to Exascale Computing, pp. 32\u201353. Springer (2018)","DOI":"10.1007\/978-981-13-7729-7_3"},{"issue":"4","key":"3_CR2","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.6018","volume":"33","author":"J Choi","year":"2021","unstructured":"Choi, J., et al.: Comparing unified, pinned, and host\/device memory allocations for memory-intensive workloads on tegra SoC. Concurr. Comput. Prac. Exp. 33(4), e6018 (2021)","journal-title":"Concurr. Comput. Prac. Exp."},{"key":"3_CR3","doi-asserted-by":"publisher","unstructured":"Huebl, A., et\u00a0al.: openPMD: a meta data standard for particle and mesh based data (2015). https:\/\/doi.org\/10.5281\/zenodo.591699. https:\/\/www.openPMD.org. https:\/\/github.com\/openPMD","DOI":"10.5281\/zenodo.591699"},{"key":"3_CR4","doi-asserted-by":"publisher","unstructured":"Huebl, A., et\u00a0al.: openPMD-api: C++ & Python API for Scientific I\/O with openPMD (06 (2018). https:\/\/doi.org\/10.14278\/rodare.27. https:\/\/github.com\/openPMD\/openPMD-api","DOI":"10.14278\/rodare.27"},{"key":"3_CR5","unstructured":"IPP-CAS: Bit1 OpenMP Tasks Particle Mover Parallelization. (2025). https:\/\/repo.tok.ipp.cas.cz\/tskhakaya\/bit1\/-\/blob\/feature\/CPU-OpenMP\/BIT1_c8\/mover.c. (Updated: 12-12-2025)"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Krishnaamy, E., et al.: OpenMP Offloading on AMD and NVIDIA GPUs: Programmability and Performance Analysis. In: Proceedings of the 2025 9th International Conference on High Performance Compilation, Computing and Communications, pp. 44\u201356 (2025)","DOI":"10.1145\/3774949.3774956"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Mehta, N., et al.: Evaluating Performance Portability of OpenMP for Snap on Nvidia, Intel, and AMD GPUs using the Roofline Methodology. In: International Workshop on Accelerator Programming Using Directives, pp. 3\u201324. Springer (2020)","DOI":"10.1007\/978-3-030-74224-9_1"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Milojicic, D., Faraboschi, P., Dube, N., Roweth, D.: Future of HPC: diversifying Heterogeneity. In: 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE), pp. 276\u2013281. IEEE (2021)","DOI":"10.23919\/DATE51398.2021.9474063"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Mishra, A., et al.: Benchmarking and Evaluating Unified Memory for OpenMP GPU offloading. In: Proceedings of the Fourth Workshop on the LLVM Compiler Infrastructure in HPC, pp. 1\u201310 (2017)","DOI":"10.1145\/3148173.3148184"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Neth, B., et al.: Beyond Explicit Transfers: Shared and Managed Memory in OpenMP. In: International Workshop on OpenMP, pp. 183\u2013194. Springer (2021)","DOI":"10.1007\/978-3-030-85262-7_13"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Noaje, G., et al.: MultiGPU computing using MPI or OpenMP. In: Proceedings of the 2010 IEEE 6th International Conference on Intelligent Computer Communication and Processing, pp. 347\u2013354. IEEE (2010)","DOI":"10.1109\/ICCP.2010.5606414"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Sewall, J., et al.: A modern memory management system for OpenMP. In: 2016 Third Workshop on Accelerator Programming Using Directives (WACCPD), pp. 25\u201335. IEEE (2016)","DOI":"10.1109\/WACCPD.2016.007"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Tian, S., et al.: Experience Report: Writing a Portable GPU Runtime with OpenMP 5.1. In: International Workshop on OpenMP, pp. 159\u2013169. Springer (2021)","DOI":"10.1007\/978-3-030-85262-7_11"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Tramm, J., et al.: Toward Portable GPU Acceleration of the OpenMC Monte Carlo Particle Transport Code. In: International Conference on Physics of Reactors (PHYSOR 2022). Pittsburgh, USA (2022)","DOI":"10.13182\/PHYSOR22-37847"},{"issue":"1","key":"3_CR15","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1016\/j.jcp.2007.01.002","volume":"225","author":"D Tskhakaya","year":"2007","unstructured":"Tskhakaya, D., et al.: Optimization of PIC codes by improved memory management. J. Comput. Phys. 225(1), 829\u2013839 (2007)","journal-title":"J. Comput. Phys."},{"issue":"8\u20139","key":"3_CR16","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1002\/ctpp.200710072","volume":"47","author":"D Tskhakaya","year":"2007","unstructured":"Tskhakaya, D., et al.: The particle-in-cell method. Contrib. Plasma Phys. 47(8\u20139), 563\u2013594 (2007)","journal-title":"Contrib. Plasma Phys."},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Tskhakaya, D., et al.: PIC\/MC Code BIT1 for Plasma Simulations on HPC. In: 2010 18th Euromicro Conference on Parallel, Distributed and Network-based Processing, pp. 476\u2013481. IEEE (2010)","DOI":"10.1109\/PDP.2010.47"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Vasileska, I., et al.: Modernization of the PIC codes for exascale plasma simulation. In: 2020 43rd International Convention on Information, Communication and Electronic Technology (MIPRO), pp. 209\u2013213. IEEE (2020)","DOI":"10.23919\/MIPRO48935.2020.9245299"},{"issue":"2","key":"3_CR19","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1006\/jcph.1993.1034","volume":"104","author":"J Verboncoeur","year":"1993","unstructured":"Verboncoeur, J., et al.: Simultaneous potential and circuit solution for 1D bounded plasma particle simulation codes. J. Comput. Phys. 104(2), 321\u2013328 (1993)","journal-title":"J. Comput. Phys."},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Williams, J., et al.: Leveraging HPC Profiling and Tracing Tools to Understand the Performance of Particle-in-Cell Monte Carlo Simulations. In: European Conference on Parallel Processing, pp. 123\u2013134. Springer (2023)","DOI":"10.1007\/978-3-031-50684-0_10"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Williams, J., et al.: Enabling High-Throughput Parallel I\/O in Particle-in-Cell Monte Carlo Simulations with OpenPMD and Darshan I\/O Monitoring. In: 2024 IEEE International Conference on Cluster Computing Workshops (CLUSTER Workshops), pp. 86\u201395. IEEE (2024)","DOI":"10.1109\/CLUSTERWorkshops61563.2024.00022"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Williams, J., et al.: Optimizing BIT1, a Particle-in-Cell Monte Carlo Code, with OpenMP\/OpenACC and GPU Acceleration. In: International Conference on Computational Science, pp. 316\u2013330. Springer (2024)","DOI":"10.1007\/978-3-031-63749-0_22"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Williams, J., et al.: Understanding the Impact of OpenPMD on BIT1, a Particle-inCell Monte Carlo Code, Through Instrumentation, Monitoring, and In-Situ Analysis. In: European Conference on Parallel Processing, pp. 214\u2013226. Springer (2024)","DOI":"10.1007\/978-3-031-90200-0_18"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Williams, J., et\u00a0al.: Accelerating Particle-in-Cell Monte Carlo Simulations with MPI, OpenMP\/OpenACC and Asynchronous Multi-GPU Programming. J. Comput. Sci. 102590 (2025)","DOI":"10.1016\/j.jocs.2025.102590"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Williams, J., et\u00a0al.: Integrating High Performance In-Memory Data Streaming and In-Situ Visualization in Hybrid MPI+ OpenMP PIC MC Simulations Towards Exascale. Int. J. High Perform. Comput. Appl. (2026)","DOI":"10.1177\/10943420251409229"},{"issue":"8","key":"3_CR26","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1145\/2517327.2442523","volume":"48","author":"B Wu","year":"2013","unstructured":"Wu, B., et al.: Complexity analysis and algorithm design for reorganizing data to minimize non-coalesced memory accesses on GPU. ACM SIGPLAN Notices 48(8), 57\u201368 (2013)","journal-title":"ACM SIGPLAN Notices"}],"container-title":["Lecture Notes in Computer Science","Computational Science \u2013 ICCS 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-29921-5_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T20:17:09Z","timestamp":1782159429000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-29921-5_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032299208","9783032299215"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-29921-5_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"23 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hamburg","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":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 June 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccs-computsci2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iccs-meeting.org\/iccs2026\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}