{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T08:00:14Z","timestamp":1776931214865,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","funder":[{"name":"Wallenberg AI, Autonomous Systems and Sotware Program (WASP) funded by the Knut and Alice Wallenberg Foundation","award":[""],"award-info":[{"award-number":[""]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3731599.3767477","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T16:13:44Z","timestamp":1762532024000},"page":"1017-1027","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ASaP: Automatic Software Prefetching for Sparse Tensor Computations in MLIR"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6603-1171","authenticated-orcid":false,"given":"Konstantinos","family":"Sotiropoulos","sequence":"first","affiliation":[{"name":"Chalmers University of Technology, Gothenburg, Sweden and University of Gothenburg, Gothenburg, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4549-6260","authenticated-orcid":false,"given":"Jonas","family":"Skeppstedt","sequence":"additional","affiliation":[{"name":"Lund University, Lund, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7441-8245","authenticated-orcid":false,"given":"Per","family":"Stenstr\u00f6m","sequence":"additional","affiliation":[{"name":"Chalmers University of Technology, Gothenburg, Sweden and University of Gothenburg, Goteborg, Sweden"}],"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.]. Benchmarking tips \u2014 LLVM 21.0.0git documentation. https:\/\/llvm.org\/docs\/Benchmarking.html"},{"key":"e_1_3_3_2_3_2","unstructured":"2023. Whitepaper: Hardware Prefetch Controls for Intel Atom Cores. https:\/\/www.intel.com\/content\/www\/us\/en\/content-details\/795247\/hardware-prefetch-controls-for-intel-atom-cores.html"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","unstructured":"Mart\u00edn Abadi Paul Barham Jianmin Chen Zhifeng Chen Andy Davis Jeffrey Dean Matthieu Devin Sanjay Ghemawat Geoffrey Irving Michael Isard Manjunath Kudlur Josh Levenberg Rajat Monga Sherry Moore Derek\u00a0G. Murray Benoit Steiner Paul Tucker Vijay Vasudevan Pete Warden Martin Wicke Yuan Yu and Xiaoqiang Zheng. 2016. TensorFlow: A system for large-scale machine learning. 10.48550\/ARXIV.1605.08695Version Number: 2.","DOI":"10.48550\/ARXIV.1605.08695"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3519939.3523442"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.5555\/3049832.3049865"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","unstructured":"Sam Ainsworth and Timothy\u00a0M. Jones. 2018. Software Prefetching for Indirect Memory Accesses: A Microarchitectural Perspective. ACM Transactions on Computer Systems 36 3 (Aug. 2018) 1\u201334. 10.1145\/3319393","DOI":"10.1145\/3319393"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378498"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00051"},{"key":"e_1_3_3_2_10_2","volume-title":"Compiler support for sparse matrix computations","author":"Bik Aart Johannes\u00a0Casimir","year":"1997","unstructured":"Aart Johannes\u00a0Casimir Bik. 1997. Compiler support for sparse matrix computations."},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/165939.166023"},{"key":"e_1_3_3_2_12_2","volume-title":"JAX: composable transformations of Python+NumPy programs","author":"Bradbury James","year":"2018","unstructured":"James Bradbury, Roy Frostig, Peter Hawkins, Matthew\u00a0James Johnson, Chris Leary, Dougal Maclaurin, George Necula, Adam Paszke, Jake VanderPlas, Skye Wanderman-Milne, and Qiao Zhang. 2018. JAX: composable transformations of Python+NumPy programs. http:\/\/github.com\/jax-ml\/jax"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/106972.106979"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","unstructured":"Stephen Chou Fredrik Kjolstad and Saman Amarasinghe. 2018. Format abstraction for sparse tensor algebra compilers. Proceedings of the ACM on Programming Languages 2 OOPSLA (Oct. 2018) 1\u201330. 10.1145\/3276493","DOI":"10.1145\/3276493"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","unstructured":"Timothy\u00a0A. Davis. 2019. Algorithm 1000: SuiteSparse:GraphBLAS: Graph Algorithms in the Language of Sparse Linear Algebra. ACM Trans. Math. Software 45 4 (Dec. 2019) 1\u201325. 10.1145\/3322125","DOI":"10.1145\/3322125"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","unstructured":"Timothy\u00a0A. Davis and Yifan Hu. 2011. The university of Florida sparse matrix collection. ACM Trans. Math. Software 38 1 (Nov. 2011) 1\u201325. 10.1145\/2049662.2049663","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","unstructured":"Jack Dongarra Michael\u00a0A. Heroux and Piotr Luszczek. 2016. A new metric for ranking high-performance computing systems. National Science Review 3 1 (March 2016) 30\u201335. 10.1093\/nsr\/nwv084","DOI":"10.1093\/nsr\/nwv084"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","unstructured":"Lieven Eeckhout. 2024. R.I.P. Geomean Speedup Use Equal-Work (Or Equal-Time) Harmonic Mean Speedup Instead. IEEE Computer Architecture Letters 23 1 (Jan. 2024) 78\u201382. 10.1109\/LCA.2024.3361925","DOI":"10.1109\/LCA.2024.3361925"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","unstructured":"Aleksandar Ilic Frederico Pratas and Leonel Sousa. 2014. Cache-aware Roofline model: Upgrading the loft. IEEE Computer Architecture Letters 13 1 (Jan. 2014) 21\u201324. 10.1109\/L-CA.2013.6","DOI":"10.1109\/L-CA.2013.6"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519583"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","unstructured":"Fredrik Kjolstad Shoaib Kamil Stephen Chou David Lugato and Saman Amarasinghe. 2017. The tensor algebra compiler. Proceedings of the ACM on Programming Languages 1 OOPSLA (Oct. 2017) 1\u201329. 10.1145\/3133901","DOI":"10.1145\/3133901"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2019.8661185"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.5555\/AAI28928307"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0002751"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370308"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC50251.2020.00027"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","unstructured":"Peiming Liu Alexander\u00a0J Root Anlun Xu Yinying Li Fredrik Kjolstad and Aart\u00a0J.C. Bik. 2024. Compiler Support for Sparse Tensor Convolutions. Proceedings of the ACM on Programming Languages 8 OOPSLA2 (Oct. 2024) 275\u2013303. 10.1145\/3689721","DOI":"10.1145\/3689721"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3696443.3708922"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3497776.3517783"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","unstructured":"Todd\u00a0C. Mowry Monica\u00a0S. Lam and Anoop Gupta. 1992. Design and evaluation of a compiler algorithm for prefetching. ACM SIGPLAN Notices 27 9 (Sept. 1992) 62\u201373. 10.1145\/143371.143488","DOI":"10.1145\/143371.143488"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-95953-17"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","unstructured":"Maxim Naumov Dheevatsa Mudigere Hao-Jun\u00a0Michael Shi Jianyu Huang Narayanan Sundaraman Jongsoo Park Xiaodong Wang Udit Gupta Carole-Jean Wu Alisson\u00a0G. Azzolini Dmytro Dzhulgakov Andrey Mallevich Ilia Cherniavskii Yinghai Lu Raghuraman Krishnamoorthi Ansha Yu Volodymyr Kondratenko Stephanie Pereira Xianjie Chen Wenlin Chen Vijay Rao Bill Jia Liang Xiong and Misha Smelyanskiy. 2019. Deep Learning Recommendation Model for Personalization and Recommendation Systems. 10.48550\/ARXIV.1906.00091Version Number: 1.","DOI":"10.48550\/ARXIV.1906.00091"},{"key":"e_1_3_3_2_33_2","series-title":"(LCPC \u201998)","first-page":"213","volume-title":"Proceedings of the 11th International Workshop on Languages and Compilers for Parallel Computing","author":"Pugh William","year":"1998","unstructured":"William Pugh and Tatiana Shpeisman. 1998. SIPR: A New Framework for Generating Efficient Code for Sparse Matrix Computations. In Proceedings of the 11th International Workshop on Languages and Compilers for Parallel Computing(LCPC \u201998). Springer-Verlag, 213\u2013229."},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","unstructured":"Efraim Rotem Adi Yoaz Lihu Rappoport Stephen\u00a0J. Robinson Julius\u00a0Yuli Mandelblat Arik Gihon Eliezer Weissmann Rajshree Chabukswar Vadim Basin Russell Fenger Monica Gupta and Ahmad Yasin. 2022. Intel Alder Lake CPU Architectures. IEEE Micro 42 3 (May 2022) 13\u201319. 10.1109\/MM.2022.3164338","DOI":"10.1109\/MM.2022.3164338"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/2833179.2833183"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","unstructured":"Michelle\u00a0Mills Strout Mary Hall and Catherine Olschanowsky. 2018. The Sparse Polyhedral Framework: Composing Compiler-Generated Inspector-Executor Code. Proc. IEEE 106 11 (Nov. 2018) 1921\u20131934. 10.1109\/JPROC.2018.2857721","DOI":"10.1109\/JPROC.2018.2857721"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","unstructured":"Michelle\u00a0Mills Strout Alan LaMielle Larry Carter Jeanne Ferrante Barbara Kreaseck and Catherine Olschanowsky. 2016. An approach for code generation in the Sparse Polyhedral Framework. Parallel Comput. 53 C (April 2016) 32\u201357. 10.1016\/j.parco.2016.02.004","DOI":"10.1016\/j.parco.2016.02.004"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00061"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/LLVMHPC54804.2021.00009"},{"key":"e_1_3_3_2_40_2","unstructured":"Nicolas Vasilache Oleksandr Zinenko Aart J.\u00a0C. Bik Mahesh Ravishankar Thomas Raoux Alexander Belyaev Matthias Springer Tobias Gysi Diego Caballero Stephan Herhut Stella Laurenzo and Albert Cohen. 2022. Composable and Modular Code Generation in MLIR: A Structured and Retargetable Approach to Tensor Compiler Construction. arXiv:https:\/\/arXiv.org\/abs\/2202.03293 [cs]."},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","unstructured":"Anand Venkat Mary Hall and Michelle Strout. 2015. Loop and data transformations for sparse matrix code. ACM SIGPLAN Notices 50 6 (Aug. 2015) 521\u2013532. 10.1145\/2813885.2738003","DOI":"10.1145\/2813885.2738003"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","unstructured":"Samuel Williams Andrew Waterman and David Patterson. 2009. Roofline: an insightful visual performance model for multicore architectures. Commun. ACM 52 4 (April 2009) 65\u201376. 10.1145\/1498765.1498785","DOI":"10.1145\/1498765.1498785"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582047"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","unstructured":"Genghan Zhang Olivia Hsu and Fredrik Kjolstad. 2024. Compilation of Modular and General Sparse Workspaces. Proceedings of the ACM on Programming Languages 8 PLDI (June 2024) 1213\u20131238. 10.1145\/3656426","DOI":"10.1145\/3656426"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640396"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","unstructured":"Tuowen Zhao Tobi Popoola Mary Hall Catherine Olschanowsky and Michelle Strout. 2023. Polyhedral Specification and Code Generation of Sparse Tensor Contraction with Co-iteration. ACM Transactions on Architecture and Code Optimization 20 1 (March 2023) 1\u201326. 10.1145\/3566054","DOI":"10.1145\/3566054"}],"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\/3731599.3767477","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T19:27:55Z","timestamp":1767986875000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731599.3767477"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":45,"alternative-id":["10.1145\/3731599.3767477","10.1145\/3731599"],"URL":"https:\/\/doi.org\/10.1145\/3731599.3767477","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"}}]}}