{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T08:00:32Z","timestamp":1776931232019,"version":"3.51.2"},"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":[[2025,11,16]]},"DOI":"10.1145\/3731599.3767436","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T16:18:44Z","timestamp":1762532324000},"page":"766-774","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Generating Permutations at Scale"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3658-1233","authenticated-orcid":false,"given":"Oded","family":"Green","sequence":"first","affiliation":[{"name":"NVIDIA Corporation, Santa Clara, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7540-995X","authenticated-orcid":false,"given":"Joe","family":"Eaton","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation, Santa Clara, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6755-3895","authenticated-orcid":false,"given":"Alok","family":"Tripathy","sequence":"additional","affiliation":[{"name":"UC Berkeley, Berkeley, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2117-7636","authenticated-orcid":false,"given":"Corey","family":"Nolet","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation, Santa Clara, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8787-8785","authenticated-orcid":false,"given":"Justin","family":"Luitjens","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation, Santa Clara, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"[n. d.]. https:\/\/en.wikipedia.org\/wiki\/Hyperparameter_optimization"},{"key":"e_1_3_3_2_3_2","unstructured":"Austin Appleby. 2008. Murmurhash 2.0."},{"key":"e_1_3_3_2_4_2","unstructured":"Axel Bacher Olivier Bodini Alexandros Hollender and J\u00e9r\u00e9mie Lumbroso. 2015. MergeShuffle: a very fast parallel random permutation algorithm. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1508.03167 (2015)."},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","unstructured":"Cagri Balkesen Gustavo Alonso Jens Teubner and M.\u00a0Tamar \u00d6zsu. 2013. Multi-core main-memory joins: sort vs. hash revisited. Proc. VLDB Endow. 7 1 (2013) 85\u201396. 10.14778\/2732219.2732227","DOI":"10.14778\/2732219.2732227"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Arash Beiranvand and Paul Cuffe. 2019. A topological sorting approach to identify coherent cut-sets within power grids. IEEE Transactions on Power Systems 35 1 (2019) 721\u2013730.","DOI":"10.1109\/TPWRS.2019.2936099"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Guido Bertoni Joan Daemen Seth Hoffert Micha\u00ebl Peeters Gilles Van\u00a0Assche and Ronny Van\u00a0Keer. 2016. Farfalle: parallel permutation-based cryptography. Cryptology ePrint Archive (2016).","DOI":"10.46586\/tosc.v2017.i4.1-38"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/1989323.1989328"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Wayne\u00a0F Boyer and Gurdeep\u00a0S Hura. 2005. Non-evolutionary algorithm for scheduling dependent tasks in distributed heterogeneous computing environments. J. Parallel and Distrib. Comput. 65 9 (2005) 1035\u20131046.","DOI":"10.1016\/j.jpdc.2005.04.017"},{"key":"e_1_3_3_2_10_2","volume-title":"Machine Learning Algorithms From Scratch with Python","author":"Brownlee J.","year":"2016","unstructured":"J. Brownlee. 2016. Machine Learning Algorithms From Scratch with Python. Machine Learning Mastery. 20,21 pages. https:\/\/books.google.com\/books?id=5giqDwAAQBAJ"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/2020373.2020375"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Douglas Curran-Everett. 2012. Explorations in statistics: permutation methods. Advances in physiology education 36 3 (2012) 181\u2013187.","DOI":"10.1152\/advan.00072.2012"},{"key":"e_1_3_3_2_13_2","unstructured":"Deep Graph\u00a0Library documentation team. 2022. https:\/\/docs.dgl.ai\/tutorials\/large\/L0_neighbor_sampling_overview.html"},{"key":"e_1_3_3_2_14_2","volume-title":"Statistical tables for biological, agricultural and medical research","author":"Fisher Ronald\u00a0Aylmer","year":"1953","unstructured":"Ronald\u00a0Aylmer Fisher and Frank Yates. 1953. Statistical tables for biological, agricultural and medical research. Hafner Publishing Company. 26\u201327 pages."},{"key":"e_1_3_3_2_15_2","volume-title":"IEEE Proc. High Performance Extreme Computing (HPEC)","author":"Oded Fox, James and Tripathy, Alok and Green,","year":"2019","unstructured":"Fox, James and Tripathy, Alok and Green, Oded. 2019. Improving Scheduling for Irregular Applications with Logarithmic Radix Binning. In IEEE Proc. High Performance Extreme Computing (HPEC)."},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Oded Green. 2021. HashGraph\u2014Scalable Hash Tables Using a Sparse Graph Data Structure. ACM Transactions on Parallel Computing (TOPC) 8 2 (2021) 1\u201317.","DOI":"10.1145\/3460872"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC55821.2022.9926387"},{"key":"e_1_3_3_2_18_2","first-page":"1024","volume-title":"Advances in Neural Information Processing Systems 30","author":"Hamilton Will","year":"2017","unstructured":"Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive Representation Learning on Large Graphs. In Advances in Neural Information Processing Systems 30, I.\u00a0Guyon, U.\u00a0V. Luxburg, S.\u00a0Bengio, H.\u00a0Wallach, R.\u00a0Fergus, S.\u00a0Vishwanathan, and R.\u00a0Garnett (Eds.). Curran Associates, Inc., 1024\u20131034. http:\/\/papers.nips.cc\/paper\/6703-inductive-representation-learning-on-large-graphs.pdf"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Yang-Hui He. 2023. Machine-learning mathematical structures. International Journal of Data Science in the Mathematical Sciences 1 01 (2023) 23\u201347.","DOI":"10.1142\/S2810939222500010"},{"key":"e_1_3_3_2_20_2","unstructured":"Jared Hoberock and Nathan Bell. 2010. Thrust: A Parallel Template Library. http:\/\/www.meganewtons.com\/ Version 1.3.0."},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Charles\u00a0A Holt and Sean\u00a0P Sullivan. 2023. Permutation tests for experimental data. Experimental economics 26 4 (2023) 775\u2013812.","DOI":"10.1007\/s10683-023-09799-6"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW50202.2020.00104"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Changkyu Kim Tim Kaldewey Victor\u00a0W Lee Eric Sedlar Anthony\u00a0D Nguyen Nadathur Satish Jatin Chhugani Andrea Di\u00a0Blas and Pradeep Dubey. 2009. Sort vs. Hash revisited: fast join implementation on modern multi-core CPUs. Proceedings of the VLDB Endowment 2 2 (2009) 1378\u20131389.","DOI":"10.14778\/1687553.1687564"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Ruby\u00a0B Lee Zhijie Shi and Xiiao Yang. 2001. Efficient permutation instructions for fast software cryptography. IEEE Micro 21 6 (2001) 56\u201369.","DOI":"10.1109\/40.977759"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/IA349570.2019.00007"},{"key":"e_1_3_3_2_26_2","unstructured":"Duane Merrill and NVIDIA-Labs. 2015. Cuda Unbound (cub) Library. NVIDIA-Labs (2015)."},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Rory Mitchell Daniel Stokes Eibe Frank and Geoffrey Holmes. 2022. Bandwidth-optimal random shuffling for GPUs. ACM Transactions on Parallel Computing 9 1 (2022) 1\u201320.","DOI":"10.1145\/3505287"},{"key":"e_1_3_3_2_28_2","unstructured":"Richard\u00a0C Murphy Kyle\u00a0B Wheeler Brian\u00a0W Barrett and James\u00a0A Ang. 2010. Introducing the Graph 500. Cray User?s Group (CUG) (2010)."},{"key":"e_1_3_3_2_29_2","unstructured":"ROYUD Nishino and Shohei Hido\u00a0Crissman Loomis. 2017. Cupy: A numpy-compatible library for nvidia gpu calculations. 31st conference on neural information processing systems 151 7 (2017)."},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Ashwin Pananjady Martin\u00a0J Wainwright and Thomas\u00a0A Courtade. 2017. Linear regression with shuffled data: Statistical and computational limits of permutation recovery. IEEE Transactions on Information Theory 64 5 (2017) 3286\u20133300.","DOI":"10.1109\/TIT.2017.2776217"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.104"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2019.00045"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/1378533.1378560"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"crossref","unstructured":"Robert Sedgewick. 1977. Permutation generation methods. ACM Computing Surveys (CSUR) 9 2 (1977) 137\u2013164.","DOI":"10.1145\/356689.356692"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Devavrat Shah. 2021. Computing choice: Learning distributions over permutations. Information-Theoretic Methods in Data Science (2021) 229.","DOI":"10.1017\/9781108616799.009"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1109\/ASAP.2000.862385","volume-title":"Proceedings IEEE International Conference on Application-Specific Systems, Architectures, and Processors","author":"Shi Zhijie","year":"2000","unstructured":"Zhijie Shi and Ruby\u00a0B Lee. 2000. Bit permutation instructions for accelerating software cryptography. In Proceedings IEEE International Conference on Application-Specific Systems, Architectures, and Processors. IEEE, 138\u2013148."},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607103"},{"key":"e_1_3_3_2_38_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Zeng Hanqing","year":"2020","unstructured":"Hanqing Zeng, Hongkuan Zhou, Ajitesh Srivastava, Rajgopal Kannan, and Viktor Prasanna. 2020. GraphSAINT: Graph Sampling based inductive learning method. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_2_39_2","volume-title":"Proceedings of Neural Information Processing Systems (NeurIPS)","author":"Zou Difan","year":"2019","unstructured":"Difan Zou, Ziniu Hu, Yewen Wang, Song Jiang, Yizhou Sun, and Quanquan Gu. 2019. Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks. In Proceedings of Neural Information Processing Systems (NeurIPS)."}],"event":{"name":"SC Workshops '25: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St Louis MO USA","acronym":"SC Workshops '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767436","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T19:31:13Z","timestamp":1767987073000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731599.3767436"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":38,"alternative-id":["10.1145\/3731599.3767436","10.1145\/3731599"],"URL":"https:\/\/doi.org\/10.1145\/3731599.3767436","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}