{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T20:56:24Z","timestamp":1775854584318,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,21]]},"DOI":"10.1145\/3695053.3731052","type":"proceedings-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T16:46:17Z","timestamp":1750437977000},"page":"1956-1968","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["MD-pipe: A Strong Scaling Enhanced Pipeline Architecture for Ab Initio Accuracy Molecular Dynamics"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7383-9018","authenticated-orcid":false,"given":"Ning","family":"Kang","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4864-7677","authenticated-orcid":false,"given":"Guojun","family":"Yuan","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1578-6003","authenticated-orcid":false,"given":"Zihan","family":"Yan","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7302-2073","authenticated-orcid":false,"given":"Beining","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5548-0829","authenticated-orcid":false,"given":"Boyang","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8388-9564","authenticated-orcid":false,"given":"Zeyu","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5704-597X","authenticated-orcid":false,"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[{"name":"Southwest University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7516-2406","authenticated-orcid":false,"given":"Guanglei","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9662-4980","authenticated-orcid":false,"given":"Jiayi","family":"Rao","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4274-7671","authenticated-orcid":false,"given":"Zhan","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8539-8326","authenticated-orcid":false,"given":"Weile","family":"Jia","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4179-2660","authenticated-orcid":false,"given":"Ninghui","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6361-5948","authenticated-orcid":false,"given":"Guangming","family":"Tan","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"key":"e_1_3_3_1_2_2","volume-title":"AMD Versal\u2122 Premium Series VPK180 Evaluation Kit","author":"Micro\u00a0Devices Inc. Advanced","year":"2024","unstructured":"Inc. Advanced Micro\u00a0Devices. 2024. AMD Versal\u2122 Premium Series VPK180 Evaluation Kit. Retrieved November 21, 2024 from https:\/\/www.amd.com\/en\/products\/adaptive-socs-and-fpgas\/evaluation-boards\/vpk180.html#product-overview"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","unstructured":"Simon Batzner Albert Musaelian Lixin Sun Mario Geiger Jonathan\u00a0P. Mailoa Mordechai Kornbluth Nicola Molinari Tess\u00a0E. Smidt and Boris Kozinsky. 2022. E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials. Nature Communications 13 1 (04 May 2022) 2453. 10.1038\/s41467-022-29939-5","DOI":"10.1038\/s41467-022-29939-5"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Jorg Behler. 2021. Four generations of high-dimensional neural network potentials. Chemical Reviews 121 16 (2021) 10037\u201310072.","DOI":"10.1021\/acs.chemrev.0c00868"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"J\u00f6rg Behler and Michele Parrinello. 2007. Generalized neural-network representation of high-dimensional potential-energy surfaces. Physical review letters 98 14 (2007) 146401.","DOI":"10.1103\/PhysRevLett.98.146401"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"David\u00a0A Case Hasan\u00a0Metin Aktulga Kellon Belfon David\u00a0S Cerutti G\u00a0Andr\u00e9s Cisneros Vin\u00edcius Wilian\u00a0D Cruzeiro Negin Forouzesh Timothy\u00a0J Giese Andreas\u00a0W G\u00f6tz Holger Gohlke et\u00a0al. 2023. AmberTools. Journal of chemical information and modeling 63 20 (2023) 6183\u20136191.","DOI":"10.1021\/acs.jcim.3c01153"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS60453.2023.00257"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Zheyong Fan Yanzhou Wang Penghua Ying Keke Song Junjie Wang Yong Wang Zezhu Zeng Ke Xu Eric Lindgren J\u00a0Magnus Rahm et\u00a0al. 2022. GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations. The Journal of Chemical Physics 157 11 (2022).","DOI":"10.1063\/5.0106617"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Toshiyuki Fukushige Makoto Taiji Junichiro Makino Toshikazu Ebisuzaki and Daiichiro Sugimoto. 1996. A highly parallelized special-purpose computer for many-body simulations with an arbitrary central force: MD-GRAPE. Astrophysical Journal v. 468 p. 51 468 (1996) 51.","DOI":"10.1086\/177668"},{"key":"e_1_3_3_1_10_2","unstructured":"Mirza Galib and David\u00a0T Limmer. 2020. Elucidating the mechanism of reactive uptake of N \\( _{-}\\!2 \\) O \\( _{-}\\!5 \\) in aqueous aerosol. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2005.10134 (2020)."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508425"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Wei Hu Lin Lin and Chao Yang. 2015. DGDFT: A massively parallel method for large scale density functional theory calculations. The Journal of chemical physics 143 12 (2015).","DOI":"10.1063\/1.4931732"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830777"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433707"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Kyuhyun Lee Dongsun Yoo Wonseok Jeong and Seungwu Han. 2019. SIMPLE-NN: An efficient package for training and executing neural-network interatomic potentials. Computer Physics Communications 242 (2019) 95\u2013103.","DOI":"10.1016\/j.cpc.2019.04.014"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00036"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00071"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2019.8875654"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Sean Lie. 2023. Cerebras architecture deep dive: First look inside the hardware\/software co-design for deep learning. IEEE Micro 43 3 (2023) 18\u201330.","DOI":"10.1109\/MM.2023.3256384"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","unstructured":"Yury Lysogorskiy Cas van\u00a0der Oord Anton Bochkarev Sarath Menon Matteo Rinaldi Thomas Hammerschmidt Matous Mrovec Aidan Thompson G\u00e1bor Cs\u00e1nyi Christoph Ortner and Ralf Drautz. 2021. Performant implementation of the atomic cluster expansion (PACE) and application to copper and silicon. npj Computational Materials 7 1 (28 Jun 2021) 97. 10.1038\/s41524-021-00559-9","DOI":"10.1038\/s41524-021-00559-9"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476190"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Albert Musaelian Simon Batzner Anders Johansson Lixin Sun Cameron\u00a0J Owen Mordechai Kornbluth and Boris Kozinsky. 2023. Learning local equivariant representations for large-scale atomistic dynamics. Nature Communications 14 1 (2023) 579.","DOI":"10.1038\/s41467-023-36329-y"},{"key":"e_1_3_3_1_25_2","first-page":"49\u2013es","volume-title":"Proceedings of the 2006 ACM\/IEEE conference on Supercomputing","author":"Narumi Tetsu","year":"2006","unstructured":"Tetsu Narumi, Yousuke Ohno, Noriaki Okimoto, Takahiro Koishi, Atsushi Suenaga, Noriyuki Futatsugi, Ryoko Yanai, Ryutaro Himeno, Shigenori Fujikawa, Makoto Taiji, et\u00a0al. 2006. A 55 TFLOPS simulation of amyloid-forming peptides from yeast prion Sup35 with the special-purpose computer system MDGRAPE-3. In Proceedings of the 2006 ACM\/IEEE conference on Supercomputing. 49\u2013es."},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Thomas Norrie Nishant Patil Doe\u00a0Hyun Yoon George Kurian Sheng Li James Laudon Cliff Young Norman Jouppi and David Patterson. 2021. The design process for Google\u2019s training chips: TPUv2 and TPUv3. IEEE Micro 41 2 (2021) 56\u201363.","DOI":"10.1109\/MM.2021.3058217"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Itta Ohmura Gentaro Morimoto Yousuke Ohno Aki Hasegawa and Makoto Taiji. 2014. MDGRAPE-4: a special-purpose computer system for molecular dynamics simulations. Philosophical Transactions of the Royal Society A: Mathematical Physical and Engineering Sciences 372 2021 (2014) 20130387.","DOI":"10.1098\/rsta.2013.0387"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Jose Rodriguez-Borbon Amin Kalantar Sharma Yamijala M\u00a0Bel\u00e9n Oviedo Wallid Najar and Bryan Wong. 2020. Field Programmable Gate Arrays for Enhancing the Speed and Energy Efficiency of Quantum Dynamics Simulations. (2020).","DOI":"10.26434\/chemrxiv.11977899.v1"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Kylee Santos Stan Moore Tomas Oppelstrup Amirali Sharifian Ilya Sharapov Aidan Thompson Delyan\u00a0Z Kalchev Danny Perez Robert Schreiber Scott Pakin et\u00a0al. 2024. Breaking the Molecular Dynamics Timescale Barrier Using a Wafer-Scale System. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.07898 (2024).","DOI":"10.1109\/SC41406.2024.00014"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Stefan Seritan Christoph Bannwarth Bryan\u00a0S Fales Edward\u00a0G Hohenstein Christine\u00a0M Isborn Sara\u00a0IL Kokkila-Schumacher Xin Li Fang Liu Nathan Luehr James\u00a0W Snyder\u00a0Jr et\u00a0al. 2021. TeraChem: A graphical processing unit-accelerated electronic structure package for large-scale ab initio molecular dynamics. Wiley Interdisciplinary Reviews: Computational Molecular Science 11 2 (2021) e1494.","DOI":"10.1002\/wcms.1494"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3487397"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"David\u00a0E Shaw Martin\u00a0M Deneroff Ron\u00a0O Dror Jeffrey\u00a0S Kuskin Richard\u00a0H Larson John\u00a0K Salmon Cliff Young Brannon Batson Kevin\u00a0J Bowers Jack\u00a0C Chao et\u00a0al. 2008. Anton a special-purpose machine for molecular dynamics simulation. Commun. ACM 51 7 (2008) 91\u201397.","DOI":"10.1145\/1364782.1364802"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.9"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"crossref","unstructured":"Ryutaro Susukita Toshikazu Ebisuzaki Bruce\u00a0G Elmegreen Hideaki Furusawa Kenya Kato Atsushi Kawai Yoshinao Kobayashi Takahiro Koishi Geoffrey\u00a0D McNiven Tetsu Narumi et\u00a0al. 2003. Hardware accelerator for molecular dynamics: MDGRAPE-2. Computer Physics Communications 155 2 (2003) 115\u2013131.","DOI":"10.1016\/S0010-4655(03)00349-7"},{"key":"e_1_3_3_1_35_2","volume-title":"DesignWare Library-Datapath and Building Block IP","author":"Synopsys Inc.","year":"2024","unstructured":"Inc. Synopsys. 2024. DesignWare Library-Datapath and Building Block IP. Retrieved Nov. 21, 2024 from https:\/\/www.synopsys.com\/dw\/buildingblock.php"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS55958.2022.9895534"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"crossref","unstructured":"Han Wang Linfeng Zhang Jiequn Han and E Weinan. 2018. DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics. Computer Physics Communications 228 (2018) 178\u2013184.","DOI":"10.1016\/j.cpc.2018.03.016"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607100"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"crossref","unstructured":"Jinzhe Zeng Duo Zhang Denghui Lu Pinghui Mo Zeyu Li Yixiao Chen Mari\u00e1n Rynik Li\u2019ang Huang Ziyao Li Shaochen Shi et\u00a0al. 2023. DeePMD-kit v2: A software package for deep potential models. The Journal of Chemical Physics 159 5 (2023).","DOI":"10.1063\/5.0155600"}],"event":{"name":"ISCA '25: Proceedings of the 52nd Annual International Symposium on Computer Architecture","location":"Tokyo Japan","acronym":"SIGARCH '25","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 52nd Annual International Symposium on Computer Architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3695053.3731052","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T11:06:03Z","timestamp":1750503963000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3695053.3731052"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,20]]},"references-count":38,"alternative-id":["10.1145\/3695053.3731052","10.1145\/3695053"],"URL":"https:\/\/doi.org\/10.1145\/3695053.3731052","relation":{},"subject":[],"published":{"date-parts":[[2025,6,20]]},"assertion":[{"value":"2025-06-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}