{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T12:49:52Z","timestamp":1782996592742,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,6]]},"DOI":"10.1145\/3797905.3807833","type":"proceedings-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T11:50:37Z","timestamp":1782993037000},"page":"422-435","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SHIRO: Near-Optimal Communication Strategies for Distributed Sparse Matrix Multiplication"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4156-9879","authenticated-orcid":false,"given":"Chen","family":"Zhuang","sequence":"first","affiliation":[{"name":"Institute of Science Tokyo, Tokyo, Japan and RIKEN Center for Computational Science, Kobe, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2452-1551","authenticated-orcid":false,"given":"Lingqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"RIKEN Center for Computational Science, Kobe, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1488-1622","authenticated-orcid":false,"given":"Benjamin","family":"Brock","sequence":"additional","affiliation":[{"name":"Intel Corporation, San Francisco, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4002-0837","authenticated-orcid":false,"given":"Du","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Science Tokyo, Tokyo, Japan and RIKEN Center for Computational Science, Kobe, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1244-3151","authenticated-orcid":false,"given":"Peng","family":"Chen","sequence":"additional","affiliation":[{"name":"RIKEN Center for Computational Science, Kobe, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7297-6211","authenticated-orcid":false,"given":"Toshio","family":"Endo","sequence":"additional","affiliation":[{"name":"Institute of Science Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1910-8532","authenticated-orcid":false,"given":"Satoshi","family":"Matsuoka","sequence":"additional","affiliation":[{"name":"RIKEN Center for Computational Science, Kobe, Japan and Institute of Science Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7165-2095","authenticated-orcid":false,"given":"Mohamed","family":"Wahib","sequence":"additional","affiliation":[{"name":"RIKEN Center for Computational Science, Kobe, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,5]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"[n. d.]. NVIDIA Nsight Systems. https:\/\/developer.nvidia.com\/nsight-systems. Accessed: 2026-01-22."},{"key":"e_1_3_3_2_3_2","unstructured":"Nabil Abubaker and Torsten Hoefler. 2024. SpComm3D: A Framework for Enabling Sparse Communication in 3D Sparse Kernels. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.19638 (2024)."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Seher Acer Oguz Selvitopi and Cevdet Aykanat. 2016. Improving performance of sparse matrix dense matrix multiplication on large-scale parallel systems. Parallel Comput. 59 (2016) 71\u201396.","DOI":"10.1016\/j.parco.2016.10.001"},{"key":"e_1_3_3_2_5_2","unstructured":"William\u00a0E. Allcock Benjamin\u00a0S. Allen James Anchell Victor Anisimov Thomas Applencourt Abhishek Bagusetty Ramesh Balakrishnan Riccardo Balin Solomon Bekele Colleen Bertoni Cyrus Blackworth Renzo Bustamante Kevin Canada John Carrier Christopher Chan-nui Lance\u00a0C. Cheney Taylor Childers Paul Coffman Susan Coghlan Tanima Dey Michael D\u2019Mello Ashok Emani Murali Emani Kyle\u00a0G. Felker Sam Foreman Olivier Franza Longfei Gao Marta Garc\u00eda Mar\u00eda Garzar\u00e1n Balazs Gerofi Yasaman Ghadar Subrata Goswami Neha Gupta Kevin Harms V\u00e4in\u00f6 Hatanp\u00e4\u00e4 Brian Holland Carissa Holohan Brian Homerding Khalid Hossain Xue Hu Louise Huot Huda Ibeid Joseph\u00a0A. Insley Sai Jayanthi Hong Jiang Wei Jiang Xiao-Yong Jin Jeongnim Kim Christopher Knight Panagiotis Kourdis Kalyan Kumaran JaeHyuk Kwack Janghaeng Lee Ti Leggett Ben Lenard Chris Lewis Nevin Liber Johann Lombardi Raymond\u00a0M. Loy Ye Luo Bethany Lusch Nilakantan Mahadevan Beth Markey Victor\u00a0A. Mateevitsi Gordon McPheeters Ryan Milner Jerome Mitchell Vitali\u00a0A. Morozov Servesh Muralidharan Tom Musta Mrigendra Nagar Vikram Narayana Marieme Ngom Anthony-Trung Nguyen Nathan Nichols Aditya Nishtala James\u00a0C. Osborn Michael\u00a0E. Papka Scott Parker Saumil\u00a0S. Patel Julia Piotrowska Adrian\u00a0C. Pope Sucheta Raghunanda Esteban Rangel Paul\u00a0M. Rich Katherine\u00a0M. Riley Silvio Rizzi Kris Rowe Varuni Sastry Adam Scovel Filippo Simini Haritha\u00a0Siddabathuni Som Patrick Steinbrecher Rick Stevens Xinmin Tian Peter Upton Thomas Uram Archit\u00a0K. Vasan \u00c1lvaro V\u00e1zquez-Mayagoitia Kaushik Velusamy Brice Videau Venkatram Vishwanath Brian Whitney Timothy\u00a0J. Williams Michael Woodacre Sam Zeltner Chuanjun Zhang Gengbin Zheng and Huihuo Zheng. 2025. Aurora: Architecting Argonne\u2019s First Exascale Supercomputer for Accelerated Scientific Discovery. arxiv:https:\/\/arXiv.org\/abs\/2509.08207\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2509.08207"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00014"},{"key":"e_1_3_3_2_7_2","unstructured":"Amanda Bienz. 2018. Reducing Communication in Sparse Solvers. Ph.\u00a0D. Dissertation. University of Illinois at Urbana-Champaign."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Amanda Bienz William\u00a0D Gropp and Luke\u00a0N Olson. 2020. Reducing communication in algebraic multigrid with multi-step node aware communication. The International Journal of High Performance Computing Applications 34 5 (2020) 547\u2013561.","DOI":"10.1177\/1094342020925535"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640427"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3650200.3656623"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Timothy\u00a0A Davis and Yifan Hu. 2011. The University of Florida sparse matrix collection. ACM Trans. Math. Software 38 1 (2011) 1\u201325.","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_3_2_12_2","unstructured":"Efim\u00a0A Dinic. 1970. Algorithm for solution of a problem of maximum flow in networks with power estimation. Soviet Mathematics Doklady 11 (1970) 1277\u20131280."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651378"},{"key":"e_1_3_3_2_14_2","unstructured":"Matthias Fey and Jan\u00a0Eric Lenssen. 2019. Fast Graph Representation Learning with PyTorch Geometric. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1903.02428 (2019). ICLR Workshop on Representation Learning on Graphs and Manifolds."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Lester\u00a0Randolph Ford\u00a0Jr and Delbert\u00a0Ray Fulkerson. 1956. Maximal flow through a network. Canadian Journal of Mathematics 8 (1956) 399\u2013404.","DOI":"10.4153\/CJM-1956-045-5"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433723"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627535.3638496"},{"key":"e_1_3_3_2_18_2","series-title":"Proceedings of Machine Learning Research","first-page":"1263","volume-title":"Proceedings of the 34th International Conference on Machine Learning","volume":"70","author":"Gilmer Justin","year":"2017","unstructured":"Justin Gilmer, Samuel\u00a0S. Schoenholz, Patrick\u00a0F. Riley, Oriol Vinyals, and George\u00a0E. Dahl. 2017. Neural Message Passing for Quantum Chemistry. In Proceedings of the 34th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a070), Doina Precup and Yee\u00a0Whye Teh (Eds.). PMLR, 1263\u20131272."},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Roger\u00a0G Grimes John\u00a0G Lewis and Horst\u00a0D Simon. 1994. A shifted block Lanczos algorithm for solving sparse symmetric generalized eigenproblems. SIAM J. Matrix Anal. Appl. 15 1 (1994) 228\u2013272.","DOI":"10.1137\/S0895479888151111"},{"key":"e_1_3_3_2_20_2","first-page":"420","volume-title":"Modern mathematical models, methods and algorithms for real world systems","author":"Gutknecht Martin\u00a0H","year":"2007","unstructured":"Martin\u00a0H Gutknecht. 2007. Block Krylov space methods for linear systems with multiple right-hand sides: an introduction. In Modern mathematical models, methods and algorithms for real world systems. Anshan, 420\u2013447."},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00041"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00053"},{"key":"e_1_3_3_2_24_2","unstructured":"Weihua Hu Matthias Fey Hongyu Ren Maho Nakata Yuxiao Dong and Jure Leskovec. 2021. Ogb-lsc: A large-scale challenge for machine learning on graphs. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2103.09430 (2021)."},{"key":"e_1_3_3_2_25_2","unstructured":"Weihua Hu Matthias Fey Marinka Zitnik Yuxiao Dong Hongyu Ren Bowen Liu Michele Catasta and Jure Leskovec. 2020. Open Graph Benchmark: Datasets for Machine Learning on Graphs. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2005.00687 (2020)."},{"key":"e_1_3_3_2_26_2","unstructured":"Institute of Science Tokyo. 2024. TSUBAME4.0 User\u2019s Guide. https:\/\/www.t4.cii.isct.ac.jp\/docs\/handbook.en\/."},{"key":"e_1_3_3_2_27_2","unstructured":"Intel Corporation. 2024. Intel oneAPI Collective Communications Library (oneCCL). https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/oneccl.html. Accessed: 2026-05-04."},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599843"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2016.117"},{"key":"e_1_3_3_2_30_2","unstructured":"Jure Leskovec and Andrej Krevl. 2014. SNAP Datasets: Stanford Large Network Dataset Collection. http:\/\/snap.stanford.edu\/data."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Jure Leskovec and Rok Sosi\u010d. 2016. SNAP: A General-Purpose Network Analysis and Graph-Mining Library. ACM Transactions on Intelligent Systems and Technology 8 1 (2016) 1\u201320.","DOI":"10.1145\/2898361"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"crossref","unstructured":"Shelby Lockhart Amanda Bienz William Gropp and Luke Olson. 2023. Performance analysis and optimal node-aware communication for enlarged conjugate gradient methods. ACM Transactions on Parallel Computing 10 1 (2023) 1\u201325.","DOI":"10.1145\/3580003"},{"key":"e_1_3_3_2_33_2","unstructured":"Mellanox Technologies. 2019. Introducing 200G HDR InfiniBand Solutions. https:\/\/network.nvidia.com\/files\/doc-2020\/wp-introducing-200g-hdr-infiniband-solutions.pdf. Accessed: 2024."},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3673038.3673152"},{"key":"e_1_3_3_2_35_2","unstructured":"NVIDIA Corporation. 2024. cuSPARSE Library. https:\/\/developer.nvidia.com\/cusparse."},{"key":"e_1_3_3_2_36_2","unstructured":"NVIDIA Corporation. 2024. NCCL: NVIDIA Collective Communication Library. https:\/\/developer.nvidia.com\/nccl."},{"key":"e_1_3_3_2_37_2","unstructured":"NVIDIA Corporation. 2024. NVIDIA H100 Tensor Core GPU. https:\/\/www.nvidia.com\/en-us\/data-center\/h100\/. Accessed: 2024."},{"key":"e_1_3_3_2_38_2","unstructured":"NVIDIA Corporation. 2024. NVSHMEM. https:\/\/developer.nvidia.com\/nvshmem."},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Dianne\u00a0P O\u2019Leary. 1980. The block conjugate gradient algorithm and related methods. Linear algebra and its applications 29 (1980) 293\u2013322.","DOI":"10.1016\/0024-3795(80)90247-5"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627535.3638470"},{"key":"e_1_3_3_2_41_2","unstructured":"Adam Paszke Sam Gross Francisco Massa et\u00a0al. 2019. PyTorch: An imperative style high-performance deep learning library. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_3_2_42_2","unstructured":"PyTorch Team. 2024. PyTorch Distributed. https:\/\/docs.pytorch.org\/docs\/stable\/distributed.html."},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00052"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"crossref","unstructured":"Miloud Sadkane. 1993. A block Arnoldi-Chebyshev method for computing the leading eigenpairs of large sparse unsymmetric matrices. Numerische mathematik 64 1 (1993) 181\u2013193.","DOI":"10.1007\/BF01388686"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Olaf Schenk and Klaus G\u00e4rtner. 2004. Solving Unsymmetric Sparse Systems of Linear Equations with PARDISO. Future Generation Computer Systems 20 3 (2004) 475\u2013487.","DOI":"10.1016\/j.future.2003.07.011"},{"key":"e_1_3_3_2_46_2","volume-title":"Combinatorial Optimization: Polyhedra and Efficiency","author":"Schrijver Alexander","year":"2003","unstructured":"Alexander Schrijver. 2003. Combinatorial Optimization: Polyhedra and Efficiency. Springer, Berlin, Heidelberg."},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447818.3461472"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-48224-5_15"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433794"},{"key":"e_1_3_3_2_50_2","unstructured":"Borui Wan Juntao Zhao and Chuan Wu. 2023. Adaptive message quantization and parallelization for distributed full-graph gnn training. Proceedings of Machine Learning and Systems 5 (2023) 203\u2013218."},{"key":"e_1_3_3_2_51_2","unstructured":"Cheng Wan Youjie Li Ang Li Nam\u00a0Sung Kim and Yingyan Lin. 2022. Bns-gcn: Efficient full-graph training of graph convolutional networks with partition-parallelism and random boundary node sampling. Proceedings of Machine Learning and Systems 4 (2022) 673\u2013693."},{"key":"e_1_3_3_2_52_2","unstructured":"Minjie Wang Da Zheng Zihao Ye Quan Gan Mufei Li Xiang Song Jinjing Zhou Chao Ma Lingfan Yu Yu Gai Tianjun Xiao Tong He George Karypis Jinyang Li and Zheng Zhang. 2019. Deep Graph Library: A Graph-Centric Highly-Performant Package for Graph Neural Networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1909.01315 (2019)."},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"crossref","unstructured":"Quan Wang Zhendong Mao Bin Wang and Li Guo. 2017. Knowledge Graph Embedding: A Survey of Approaches and Applications. IEEE Transactions on Knowledge and Data Engineering 29 12 (2017) 2724\u20132743.","DOI":"10.1109\/TKDE.2017.2754499"},{"key":"e_1_3_3_2_54_2","first-page":"149","volume-title":"2023 USENIX Annual Technical Conference (USENIX ATC 23)","author":"Wang Yuke","year":"2023","unstructured":"Yuke Wang, Boyuan Feng, Zheng Wang, Guyue Huang, and Yufei Ding. 2023. { TC-GNN} : Bridging sparse { GNN} computation and dense tensor cores on { GPUs}. In 2023 USENIX Annual Technical Conference (USENIX ATC 23). 149\u2013164."},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582047"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3721145.3730425"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3721145.3730422"}],"event":{"name":"ICS '26: 2026 International Conference on Supercomputing","location":"Belfast United Kingdom","acronym":"ICS '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 40th ACM International Conference on Supercomputing"],"original-title":[],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T12:35:55Z","timestamp":1782995755000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3797905.3807833"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":56,"alternative-id":["10.1145\/3797905.3807833","10.1145\/3797905"],"URL":"https:\/\/doi.org\/10.1145\/3797905.3807833","relation":{},"subject":[],"published":{"date-parts":[[2026,7,5]]},"assertion":[{"value":"2026-07-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}