{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T20:06:42Z","timestamp":1773778002953,"version":"3.50.1"},"reference-count":70,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,3,17]],"date-time":"2021-03-17T00:00:00Z","timestamp":1615939200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,3,17]],"date-time":"2021-03-17T00:00:00Z","timestamp":1615939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000271","name":"Science and Technology Facilities Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000271","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Comput Softw Big Sci"],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>This paper presents the first study of Graphcore\u2019s Intelligence Processing Unit (IPU) in the context of particle physics applications. The IPU is a new type of processor optimised for machine learning. Comparisons are made for neural-network-based event simulation, multiple-scattering correction, and flavour tagging, implemented on IPUs, GPUs and CPUs, using a variety of neural network architectures and hyperparameters. Additionally, a K\u00e1lm\u00e1n filter for track reconstruction is implemented on IPUs and GPUs. The results indicate that IPUs hold considerable promise in addressing the rapidly increasing compute needs in particle physics.<\/jats:p>","DOI":"10.1007\/s41781-021-00057-z","type":"journal-article","created":{"date-parts":[[2021,3,17]],"date-time":"2021-03-17T15:02:46Z","timestamp":1615993366000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Studying the Potential of Graphcore\u00ae IPUs for Applications in Particle Physics"],"prefix":"10.1007","volume":"5","author":[{"given":"Samuel","family":"Maddrell-Mander","sequence":"first","affiliation":[]},{"given":"Lakshan Ram Madhan","family":"Mohan","sequence":"additional","affiliation":[]},{"given":"Alexander","family":"Marshall","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3001-6690","authenticated-orcid":false,"given":"Daniel","family":"O\u2019Hanlon","sequence":"additional","affiliation":[]},{"given":"Konstantinos","family":"Petridis","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2599-7209","authenticated-orcid":false,"given":"Jonas","family":"Rademacker","sequence":"additional","affiliation":[]},{"given":"Victoria","family":"Rege","sequence":"additional","affiliation":[]},{"given":"Alexander","family":"Titterton","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,3,17]]},"reference":[{"key":"57_CR1","unstructured":"Aaij R et al (2018) Physics case for an LHCb Upgrade II\u2014opportunities in flavour physics, and beyond, in the HL-LHC era"},{"key":"57_CR2","unstructured":"Abi B et al (2020) Deep Underground Neutrino Experiment (DUNE), far detector technical design report, volume III DUNE far detector technical coordination"},{"key":"57_CR3","doi-asserted-by":"publisher","unstructured":"Leggett C, Shapoval I (2018) Simulating HEP workflows on heterogeneous architectures. In: 14th International Conference on e-Science, p 343. https:\/\/doi.org\/10.1109\/eScience.2018.00087","DOI":"10.1109\/eScience.2018.00087"},{"key":"57_CR4","unstructured":"Yeo B, Lee M, Kuno Y (2019) GPU-accelerated event reconstruction for the COMET phase-I experiment"},{"issue":"1","key":"57_CR5","doi-asserted-by":"publisher","first-page":"012101","DOI":"10.1088\/1742-6596\/1525\/1\/012101","volume":"1525","author":"R Cenci","year":"2020","unstructured":"Cenci R, Di Luca A, Lazzari F, Morello MJ, Punzi G (2020) Real-time reconstruction of long-lived particles at LHCb using FPGAs. J Phys 1525(1):012101. https:\/\/doi.org\/10.1088\/1742-6596\/1525\/1\/012101","journal-title":"J Phys"},{"issue":"1","key":"57_CR6","doi-asserted-by":"publisher","first-page":"012044","DOI":"10.1088\/1742-6596\/1525\/1\/012044","volume":"1525","author":"F Lazzari","year":"2020","unstructured":"Lazzari F, Bassi G, Cenci R, Morello MJ, Punzi G (2020) Real-time cluster finding for LHCb silicon pixel VELO detector using FPGA. J Phys 1525(1):012044. https:\/\/doi.org\/10.1088\/1742-6596\/1525\/1\/012044","journal-title":"J Phys"},{"issue":"1","key":"57_CR7","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1007\/s41781-020-00039-7","volume":"4","author":"R Aaij","year":"2020","unstructured":"Aaij R et al (2020) Allen: a high level trigger on GPUs for LHCb. Comput Softw Big Sci 4(1):7. https:\/\/doi.org\/10.1007\/s41781-020-00039-7","journal-title":"Comput Softw Big Sci"},{"key":"57_CR8","doi-asserted-by":"publisher","first-page":"052003","DOI":"10.1088\/1742-6596\/513\/5\/052003","volume":"513","author":"R Andreassen","year":"2014","unstructured":"Andreassen R, Meadows B, de Silva M, Sokoloff M, Tomko K (2014) GooFit: a library for massively parallelising maximum-likelihood fits. J Phys 513:052003. https:\/\/doi.org\/10.1088\/1742-6596\/513\/5\/052003","journal-title":"J Phys"},{"key":"57_CR9","doi-asserted-by":"publisher","unstructured":"Morris A, Poluektov A, Mauri A, Merli A, Mathad A, Martinelli M (2018) Using TensorFlow for amplitude fits. In: PyHEP workshop. Sofia, Bulgaria. https:\/\/doi.org\/10.5281\/zenodo.1415413","DOI":"10.5281\/zenodo.1415413"},{"key":"57_CR10","doi-asserted-by":"publisher","unstructured":"Eschle J, Puig Navarro A, Silva Coutinho R, Serra N (2019) zfit: scalable pythonic fitting. https:\/\/doi.org\/10.1016\/j.softx.2020.100508","DOI":"10.1016\/j.softx.2020.100508"},{"key":"57_CR11","doi-asserted-by":"publisher","unstructured":"Mohan LRM, Marshall A, O\u2019Hanlon D, Maddrell-Mander S (2020) dpohanlon\/IPU4HEP. https:\/\/doi.org\/10.5281\/zenodo.3993387","DOI":"10.5281\/zenodo.3993387"},{"key":"57_CR12","unstructured":"Jia Z, Tillman B, Maggioni M, Scarpazza DP (2019) Dissecting the graphcore ipu architecture via microbenchmarking"},{"key":"57_CR13","unstructured":"Graphcore: Graphcore.ai (2020 (accessed 24 July, 2020)). https:\/\/www.graphcore.ai\/"},{"key":"57_CR14","unstructured":"Intel: Intel Xeon Platinum 8168 specifications (2020 (accessed 18 Aug, 2020)). https:\/\/ark.intel.com\/content\/www\/us\/en\/ark\/products\/120504\/intel-xeon-platinum-8168-processor-33m-cache-2-70-ghz.html"},{"key":"57_CR15","unstructured":"Intel: Intel Xeon Processor E5-2680 v4 specifications (2020 (accessed 18 Aug, 2020)). https:\/\/ark.intel.com\/content\/www\/us\/en\/ark\/products\/91754\/intel-xeon-processor-e5-2680-v4-35m-cache-2-40-ghz.html"},{"key":"57_CR16","unstructured":"Nvidia: NVIDIA TESLA P100 specifications (2020 (accessed 18 Aug, 2020)). https:\/\/www.nvidia.com\/en-gb\/data-center\/tesla-p100\/"},{"key":"57_CR17","unstructured":"Graphcore: private communication"},{"key":"57_CR18","unstructured":"Graphcore (2020) Performance Benchmarks of the Graphcore IPU. https:\/\/www.graphcore.ai\/benchmarks"},{"key":"57_CR19","unstructured":"Mathew G, Graphcore (2020) Accelerating Text to Speech Models with the IPU. https:\/\/www.graphcore.ai\/posts\/accelerating-text-to-speech-models-with-the-ipu"},{"key":"57_CR20","unstructured":"Masters D, Graphcore (2020) Delving deep into modern computer vision models. https:\/\/www.graphcore.ai\/posts\/introducing-second-generation-ipu-systems-for-ai-at-scale"},{"issue":"1","key":"57_CR21","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.1063\/1.4771869","volume":"1504","author":"J Therhaag","year":"2012","unstructured":"Therhaag J (2012) TMVA: Toolkit for multivariate data analysis. AIP Conf Proc 1504(1):1013\u20131016. https:\/\/doi.org\/10.1063\/1.4771869","journal-title":"AIP Conf Proc"},{"key":"57_CR22","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1145\/1365490.1365500","volume":"6","author":"J Nickolls","year":"2008","unstructured":"Nickolls J, Buck I, Garland M, Skadron K (2008) Scalable parallel programming with cuda. Queue 6:2. https:\/\/doi.org\/10.1145\/1365490.1365500","journal-title":"Queue"},{"key":"57_CR23","unstructured":"Abadi M et al (2015) TensorFlow: Large-scale machine learning on heterogeneous systems. http:\/\/tensorflow.org\/. Software available from tensorflow.org"},{"key":"57_CR24","unstructured":"Paszke A, Gross S, Chintala S, Chanan G, Yang E, DeVito Z, Lin Z, Desmaison A, Antiga L, Lerer A (2017) Automatic differentiation in pytorch"},{"issue":"07","key":"57_CR25","doi-asserted-by":"publisher","first-page":"1530022","DOI":"10.1142\/S0217751X15300227","volume":"30","author":"R Aaij","year":"2015","unstructured":"Aaij R et al (2015) LHCb detector performance. Int J Mod Phys A 30(07):1530022. https:\/\/doi.org\/10.1142\/S0217751X15300227","journal-title":"Int J Mod Phys A"},{"issue":"05","key":"57_CR26","doi-asserted-by":"publisher","first-page":"P05010","DOI":"10.1088\/1748-0221\/11\/05\/P05010","volume":"11","author":"R Aaij","year":"2016","unstructured":"Aaij R et al (2016) A new algorithm for identifying the flavour of $${B_{s}^{0}}$$ mesons at LHCb. JINST 11(05):P05010. https:\/\/doi.org\/10.1088\/1748-0221\/11\/05\/P05010","journal-title":"JINST"},{"key":"57_CR27","doi-asserted-by":"publisher","first-page":"P04022","DOI":"10.1088\/1748-0221\/8\/04\/P04022","volume":"8","author":"R Aaij","year":"2013","unstructured":"Aaij R et al (2013) The LHCb trigger and its performance in 2011. JINST 8:P04022. https:\/\/doi.org\/10.1088\/1748-0221\/8\/04\/P04022","journal-title":"JINST"},{"key":"57_CR28","doi-asserted-by":"publisher","first-page":"P02013","DOI":"10.1088\/1748-0221\/8\/02\/P02013","volume":"8","author":"V Gligorov","year":"2013","unstructured":"Gligorov V, Williams M (2013) Efficient, reliable and fast high-level triggering using a bonsai boosted decision tree. JINST 8:P02013. https:\/\/doi.org\/10.1088\/1748-0221\/8\/02\/P02013","journal-title":"JINST"},{"key":"57_CR29","doi-asserted-by":"publisher","first-page":"06038","DOI":"10.1051\/epjconf\/201921406038","volume":"214","author":"K Rinnert","year":"2019","unstructured":"Rinnert K, Cristoforetti M (2019) Deep learning approach to track reconstruction in the upgraded VELO. EPJ Web Conf 214:06038. https:\/\/doi.org\/10.1051\/epjconf\/201921406038","journal-title":"EPJ Web Conf"},{"key":"57_CR30","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Advances in neural information processing systems, pp 2672\u20132680"},{"key":"57_CR31","unstructured":"Karras T, Aila T, Laine S, Lehtinen J (2017) Progressive growing of gans for improved quality, stability, and variation. arXiv:1710.10196"},{"key":"57_CR32","doi-asserted-by":"crossref","unstructured":"Yu J, Lin Z, Yang J, Shen X, Lu X, Huang TS (2018) Generative image inpainting with contextual attention. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5505\u20135514","DOI":"10.1109\/CVPR.2018.00577"},{"key":"57_CR33","unstructured":"Zhang H, Goodfellow I, Metaxas D, Odena A (2019) Self-attention generative adversarial networks. In: International Conference on Machine Learning, pp 7354\u20137363"},{"key":"57_CR34","doi-asserted-by":"crossref","unstructured":"Zhang H, Xu T, Li H, Zhang S, Wang X, Huang X, Metaxas DN (2017) Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks. In: Proceedings of the IEEE international conference on computer vision, pp 5907\u20135915","DOI":"10.1109\/ICCV.2017.629"},{"key":"57_CR35","doi-asserted-by":"crossref","unstructured":"Isola P, Zhu JY, Zhou T, Efros AA (2016) Image-to-image translation with conditional adversarial networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 5967\u20135976","DOI":"10.1109\/CVPR.2017.632"},{"key":"57_CR36","doi-asserted-by":"crossref","unstructured":"Ledig C, Theis L, Husz\u00e1r F, Caballero JA, Aitken A, Tejani A, Totz J, Wang Z, Shi W (2017) Photo-realistic single image super-resolution using a generative adversarial network. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 105\u2013114","DOI":"10.1109\/CVPR.2017.19"},{"issue":"1","key":"57_CR37","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1007\/s41781-017-0004-6","volume":"1","author":"L de Oliveira","year":"2017","unstructured":"de Oliveira L, Paganini M, Nachman B (2017) Learning particle physics by example: location-aware generative adversarial networks for physics synthesis. Comput Softw Big Sci 1(1):4","journal-title":"Comput Softw Big Sci"},{"issue":"11","key":"57_CR38","doi-asserted-by":"publisher","first-page":"P11028","DOI":"10.1088\/1748-0221\/14\/11\/P11028","volume":"14","author":"C Ahdida","year":"2019","unstructured":"Ahdida C, Albanese R, Alexandrov A, Anokhina A, Aoki S, Arduini G, Atkin E, Azorskiy N, Back J, Bagulya A et al (2019) Fast simulation of muons produced at the ship experiment using generative adversarial networks. J Instrum 14(11):P11028","journal-title":"J Instrum"},{"issue":"8","key":"57_CR39","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1007\/JHEP08(2019)110","volume":"2019","author":"R Di Sipio","year":"2019","unstructured":"Di Sipio R, Giannelli MF, Haghighat SK, Palazzo S (2019) Dijetgan: a generative-adversarial network approach for the simulation of qcd dijet events at the lhc. J High Energy Phys 2019(8):110","journal-title":"J High Energy Phys"},{"key":"57_CR40","doi-asserted-by":"crossref","unstructured":"Butter A, Plehn T, Winterhalder R (2019) How to GAN event subtraction","DOI":"10.21468\/SciPostPhys.7.6.075"},{"issue":"1","key":"57_CR41","doi-asserted-by":"publisher","first-page":"012081","DOI":"10.1088\/1742-6596\/1525\/1\/012081","volume":"1525","author":"J Arjona Mart\u00ednez","year":"2020","unstructured":"Arjona Mart\u00ednez J, Nguyen TQ, Pierini M, Spiropulu M, Vlimant JR (2020) Particle Generative Adversarial Networks for full-event simulation at the LHC and their application to pileup description. J Phys 1525(1):012081. https:\/\/doi.org\/10.1088\/1742-6596\/1525\/1\/012081","journal-title":"J Phys"},{"issue":"11","key":"57_CR42","doi-asserted-by":"publisher","first-page":"979","DOI":"10.1140\/epjc\/s10052-019-7501-1","volume":"79","author":"S Carrazza","year":"2019","unstructured":"Carrazza S, Dreyer FA (2019) Lund jet images from generative and cycle-consistent adversarial networks. Eur Phys J C 79(11):979. https:\/\/doi.org\/10.1140\/epjc\/s10052-019-7501-1","journal-title":"Eur Phys J C"},{"issue":"6","key":"57_CR43","doi-asserted-by":"publisher","first-page":"075","DOI":"10.21468\/SciPostPhys.7.6.075","volume":"7","author":"A Butter","year":"2019","unstructured":"Butter A, Plehn T, Winterhalder R (2019) How to GAN LHC events. SciPost Phys. 7(6):075. https:\/\/doi.org\/10.21468\/SciPostPhys.7.6.075","journal-title":"SciPost Phys."},{"issue":"1","key":"57_CR44","doi-asserted-by":"publisher","first-page":"014021","DOI":"10.1103\/PhysRevD.97.014021","volume":"97","author":"M Paganini","year":"2018","unstructured":"Paganini M, de Oliveira L, Nachman B (2018) Calogan: Simulating 3d high energy particle showers in multilayer electromagnetic calorimeters with generative adversarial networks. Phys Rev D 97(1):014021","journal-title":"Phys Rev D"},{"issue":"4","key":"57_CR45","doi-asserted-by":"publisher","first-page":"042003","DOI":"10.1103\/PhysRevLett.120.042003","volume":"120","author":"M Paganini","year":"2018","unstructured":"Paganini M, de Oliveira L, Nachman B (2018) Accelerating science with generative adversarial networks: an application to 3d particle showers in multilayer calorimeters. Phys Rev Lett 120(4):042003","journal-title":"Phys Rev Lett"},{"key":"57_CR46","doi-asserted-by":"crossref","unstructured":"Maevskiy A, Derkach D, Kazeev N, Ustyuzhanin A, Artemev M, Anderlini L (2019) Fast data-driven simulation of Cherenkov detectors using Generative Adversarial Networks. In: 19th International Workshop on Advanced Computing and Analysis Techniques in Physics Research: Empowering the revolution: Bringing Machine Learning to High Performance Computing","DOI":"10.1088\/1742-6596\/1525\/1\/012097"},{"issue":"1","key":"57_CR47","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1007\/s41781-018-0019-7","volume":"3","author":"M Erdmann","year":"2019","unstructured":"Erdmann M, Glombitza J, Quast T (2019) Precise simulation of electromagnetic calorimeter showers using a Wasserstein Generative Adversarial Network. Comput Softw Big Sci 3(1):4. https:\/\/doi.org\/10.1007\/s41781-018-0019-7","journal-title":"Comput Softw Big Sci"},{"key":"57_CR48","doi-asserted-by":"crossref","unstructured":"Buhmann E, Diefenbacher S, Eren E, Gaede F, Kasieczka G, Korol A, Kr\u00fcger K (2020) Getting High: high fidelity simulation of high granularity calorimeters with high speed","DOI":"10.1007\/s41781-021-00056-0"},{"issue":"4","key":"57_CR49","doi-asserted-by":"publisher","first-page":"070","DOI":"10.21468\/SciPostPhys.8.4.070","volume":"8","author":"M Bellagente","year":"2020","unstructured":"Bellagente M, Butter A, Kasieczka G, Plehn T, Winterhalder R (2020) How to GAN away detector effects. SciPost Phys 8(4):070. https:\/\/doi.org\/10.21468\/SciPostPhys.8.4.070","journal-title":"SciPost Phys"},{"issue":"1","key":"57_CR50","doi-asserted-by":"publisher","first-page":"012077","DOI":"10.1088\/1742-6596\/1525\/1\/012077","volume":"1525","author":"A Ghosh","year":"2020","unstructured":"Ghosh A (2020) Deep generative models for fast shower simulation in ATLAS. J Phys 1525(1):012077. https:\/\/doi.org\/10.1088\/1742-6596\/1525\/1\/012077","journal-title":"J Phys"},{"issue":"1","key":"57_CR51","doi-asserted-by":"publisher","first-page":"012064","DOI":"10.1088\/1742-6596\/1525\/1\/012064","volume":"1525","author":"F Carminati","year":"2020","unstructured":"Carminati F, Khattak G, Loncar V, Nguyen TQ, Pierini M, Da Rocha RB, Samaras-Tsakiris K, Vallecorsa S, Vlimant JR (2020) Generative Adversarial Networks for fast simulation. J Phys Conf Ser 1525(1):012064. https:\/\/doi.org\/10.1088\/1742-6596\/1525\/1\/012064","journal-title":"J Phys Conf Ser"},{"issue":"7","key":"57_CR52","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1140\/epjc\/s10052-020-8251-9","volume":"80","author":"D Belayneh","year":"2020","unstructured":"Belayneh D et al (2020) Calorimetry with deep learning: particle simulation and reconstruction for collider physics. Eur Phys J C 80(7):688. https:\/\/doi.org\/10.1140\/epjc\/s10052-020-8251-9","journal-title":"Eur Phys J C"},{"key":"57_CR53","doi-asserted-by":"publisher","first-page":"062024","DOI":"10.1088\/1742-6596\/513\/6\/062024","volume":"513","author":"E Karavakis","year":"2014","unstructured":"Karavakis E et al (2014) Common accounting system for monitoring the atlas distributed computing resources. J Phys Conf Ser 513:062024","journal-title":"J Phys Conf Ser"},{"key":"57_CR54","doi-asserted-by":"crossref","unstructured":"Apollinari G, B\u00e9jar Alonso I, Br\u00fcning O, Fessia P, Lamont M, Rossi L, Tavian L (2017) High-luminosity large hadron collider (hl-lhc): technical design report v. 0.1. cern yellow reports: Monographs. cern, geneva","DOI":"10.2172\/1767028"},{"key":"57_CR55","unstructured":"Anelli M, Aoki S, Arduini G, Back J, Bagulya A, Baldini W, Baranov A, Barker G, Barsuk S, Battistin M et al (2015) A facility to search for hidden particles (ship) at the cern sps. arXiv preprint arXiv:1504.04956"},{"key":"57_CR56","doi-asserted-by":"publisher","DOI":"10.22323\/1.282.0177","author":"P Canal","year":"2016","unstructured":"Canal P et al (2016) GeantV: from CPU to accelerators. PoS ICHEP2016. https:\/\/doi.org\/10.22323\/1.282.0177","journal-title":"PoS ICHEP2016"},{"key":"57_CR57","doi-asserted-by":"crossref","unstructured":"Amadio G et al (2020) GeantV: Results from the prototype of concurrent vector particle transport simulation in HEP","DOI":"10.1007\/s41781-020-00048-6"},{"issue":"1","key":"57_CR58","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1007\/s41781-018-0018-8","volume":"3","author":"J Albrecht","year":"2019","unstructured":"Albrecht J, Alves AA, Amadio G, Andronico G, Anh-Ky N, Aphecetche L, Apostolakis J, Asai M, Atzori L, Babik M et al (2019) A roadmap for hep software and computing r&d for the 2020s. Comput Softw Big Sci 3(1):7","journal-title":"Comput Softw Big Sci"},{"issue":"1","key":"57_CR59","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1007\/s41781-018-0015-y","volume":"2","author":"P Musella","year":"2018","unstructured":"Musella P, Pandolfi F (2018) Fast and accurate simulation of particle detectors using generative adversarial networks. Comput Softw Big Sci 2(1):8","journal-title":"Comput Softw Big Sci"},{"key":"57_CR60","doi-asserted-by":"publisher","unstructured":"Tanabashi M et\u00a0al. (2018) Review of particle physics. Phys Rev D98:030001. https:\/\/doi.org\/10.1103\/PhysRevD.98.030001","DOI":"10.1103\/PhysRevD.98.030001"},{"key":"57_CR61","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. arXiv:1505.04597","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"57_CR62","unstructured":"Identification of Jets Containing $$b$$-Hadrons with Recurrent Neural Networks at the ATLAS Experiment. Tech. Rep. ATL-PHYS-PUB-2017-003, CERN, Geneva (2017). https:\/\/cds.cern.ch\/record\/2255226"},{"issue":"8","key":"57_CR63","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"57_CR64","unstructured":"Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L et al (2019) Pytorch: an imperative style, high-performance deep learning library. In: Advances in neural information processing systems, pp 8026\u20138037"},{"key":"57_CR65","unstructured":"Bai J, Lu F, Zhang K et al (2019) Onnx: Open neural network exchange. https:\/\/github.com\/onnx\/onnx"},{"key":"57_CR66","unstructured":"Chetlur S, Woolley C, Vandermersch P, Cohen J, Tran J, Catanzaro B, Shelhamer E (2014) cudnn: Efficient primitives for deep learning. arXiv preprint arXiv:1410.0759"},{"key":"57_CR67","doi-asserted-by":"publisher","unstructured":"Campora Perez DH (2017) LHCb Kalman \u00ef\u0148\u0104lter cross architecture studies. J Phys 898(LHCb-PROC-2017-041. CERN-LHCb-PROC-2017-041. 3):032052. 8. https:\/\/doi.org\/10.1088\/1742-6596\/898\/3\/032052. https:\/\/cds.cern.ch\/record\/2292435","DOI":"10.1088\/1742-6596\/898\/3\/032052"},{"key":"57_CR68","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1016\/0168-9002(87)90887-4","volume":"262","author":"R Fruhwirth","year":"1987","unstructured":"Fruhwirth R (1987) Application of Kalman filtering to track and vertex fitting. Nucl Instrum Meth A 262:444\u2013450. https:\/\/doi.org\/10.1016\/0168-9002(87)90887-4","journal-title":"Nucl Instrum Meth A"},{"key":"57_CR69","unstructured":"Hernando JA The Kalman filter technique applied to track fitting in GLAST http:\/\/citeseerx.ist.psu.edu\/viewdoc\/summary?doi=10.1.1.48.1880"},{"key":"57_CR70","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1016\/0168-9002(93)91285-U","volume":"329","author":"E Wolin","year":"1993","unstructured":"Wolin E, Ho L (1993) Covariance matrices for track fitting with the Kalman filter. Nucl Instrum Meth A 329:493\u2013500. https:\/\/doi.org\/10.1016\/0168-9002(93)91285-U","journal-title":"Nucl Instrum Meth A"}],"container-title":["Computing and Software for Big Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41781-021-00057-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41781-021-00057-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41781-021-00057-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,26]],"date-time":"2021-12-26T11:03:54Z","timestamp":1640516634000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41781-021-00057-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,17]]},"references-count":70,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["57"],"URL":"https:\/\/doi.org\/10.1007\/s41781-021-00057-z","relation":{},"ISSN":["2510-2036","2510-2044"],"issn-type":[{"value":"2510-2036","type":"print"},{"value":"2510-2044","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,17]]},"assertion":[{"value":"24 August 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 March 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Some authors of this publication are members of Graphcore, the manufacturer of the IPU evaluated in this paper. Graphcore supported the University of Bristol team by providing free access to its hardware and technical\/software support. One member of the University of Bristol team became Graphcore employee in the course of this project.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"N\/A.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Availability of data and material"}},{"value":"The code used for this research can be accessed at the doi given in [].","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}}],"article-number":"8"}}