{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T10:07:20Z","timestamp":1767262040899,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,8]]},"DOI":"10.1145\/3721145.3725767","type":"proceedings-article","created":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:57:17Z","timestamp":1755867437000},"page":"705-717","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["DIV: An Index & Value compression method for SpMV on large matrices"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2257-8670","authenticated-orcid":false,"given":"Dimitrios","family":"Galanopoulos","sequence":"first","affiliation":[{"name":"Department of Computer Science, National Technical University of Athens, Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5148-6903","authenticated-orcid":false,"given":"Panagiotis","family":"Mpakos","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National Technical University of Athens, Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7821-3610","authenticated-orcid":false,"given":"Petros","family":"Anastasiadis","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National Technical University of Athens, Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4890-8427","authenticated-orcid":false,"given":"Nectarios","family":"Koziris","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National Technical University of Athens, Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7811-4831","authenticated-orcid":false,"given":"Georgios","family":"Goumas","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National Technical University of Athens, Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,8,22]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Martin Burtscher and Paruj Ratanaworabhan. 2009. FPC: A High-Speed Compressor for Double-Precision Floating-Point Data. IEEE Trans. Comput. 58 1 (2009) 18\u201331. https:\/\/doi.org\/10.1109\/TC.2008.131","DOI":"10.1109\/TC.2008.131"},{"key":"e_1_3_3_2_3_2","series-title":"(SC \u201922)","volume-title":"Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis","author":"Cheshmi Kazem","year":"2022","unstructured":"Kazem Cheshmi, Zachary Cetinic, and Maryam\u00a0Mehri Dehnavi. 2022. Vectorizing sparse matrix computations with partially-strided codelets. In Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (Dallas, Texas) (SC \u201922). IEEE Press, Article 32, 15\u00a0pages. https:\/\/api.semanticscholar.org\/CorpusID:245007162"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Timothy\u00a0A Davis and Yifan Hu. 2011. The University of Florida sparse matrix collection. ACM Transactions on Mathematical Software (TOMS) 38 1 (2011) 1\u201325.","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Zhen Du Jiajia Li Yinshan Wang Xueqi Li Guangming Tan and N. Sun. 2022. AlphaSparse: Generating High Performance SpMV Codes Directly from Sparse Matrices. SC22: International Conference for High Performance Computing Networking Storage and Analysis (2022) 1\u201315. https:\/\/api.semanticscholar.org\/CorpusID:254877267","DOI":"10.1109\/SC41404.2022.00071"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2017.38"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356148"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Athena Elafrou Georgios\u00a0I. Goumas and Nectarios Koziris. 2019. BASMAT: bottleneck-aware sparse matrix-vector multiplication auto-tuning on GPGPUs. Proceedings of the 24th Symposium on Principles and Practice of Parallel Programming (2019). https:\/\/api.semanticscholar.org\/CorpusID:59618194","DOI":"10.1145\/3293883.3301490"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Athena Elafrou Vasileios Karakasis Theodoros Gkountouvas Kornilios Kourtis Georgios Goumas and Nectarios Koziris. 2018. SparseX: A library for high-performance sparse matrix-vector multiplication on multicore platforms. ACM Transactions on Mathematical Software (TOMS) 44 3 (2018) 1\u201332.","DOI":"10.1145\/3134442"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/DCC.2000.838221"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Salvatore Filippone Valeria Cardellini Davide Barbieri and Alessandro Fanfarillo. 2017. Sparse matrix-vector multiplication on GPGPUs. ACM Transactions on Mathematical Software (TOMS) 43 4 (2017) 1\u201349.","DOI":"10.1145\/3017994"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"G. Goumas K. Kourtis N. Anastopoulos V. Karakasis and N Koziris. 2009. Performance evaluation of the sparse matrix-vector multiplication on modern architectures. The Journal of Supercomputing 50 (2009) 36\u201377.","DOI":"10.1007\/s11227-008-0251-8"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/PDP.2008.41"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2015.30"},{"key":"e_1_3_3_2_15_2","volume-title":"Euro-Par Workshops","author":"Gr\u00fctzmacher Thomas","year":"2018","unstructured":"Thomas Gr\u00fctzmacher and Hartwig Anzt. 2018. A Modular Precision Format for Decoupling Arithmetic Format and Storage Format. In Euro-Par Workshops. https:\/\/api.semanticscholar.org\/CorpusID:57662952"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Thomas Gr\u00fctzmacher Terry Cojean Goran Flegar Fritz G\u00f6bel and Hartwig Anzt. 2019. A customized precision format based on mantissa segmentation for accelerating sparse linear algebra. Concurrency and Computation: Practice and Experience 32 (2019). https:\/\/api.semanticscholar.org\/CorpusID:198342465","DOI":"10.1002\/cpe.5418"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-29927-8_36"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"IEEE. 2008. IEEE Standard for Floating-Point Arithmetic. IEEE Std 754-2008 (2008) 1\u201370. https:\/\/doi.org\/10.1109\/IEEESTD.2008.4610935","DOI":"10.1109\/IEEESTD.2008.4610935"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Humayun Kabir Joshua\u00a0Dennis Booth and Padma Raghavan. 2014. A multilevel compressed sparse row format for efficient sparse computations on multicore processors. 2014 21st International Conference on High Performance Computing (HiPC) (2014) 1\u201310. https:\/\/api.semanticscholar.org\/CorpusID:11966175","DOI":"10.1109\/HiPC.2014.7116882"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"William Kahan. 1965. Pracniques: further remarks on reducing truncation errors. Commun. ACM 8 1 (1965) 40.","DOI":"10.1145\/363707.363723"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/1366230.1366244"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/1941553.1941587"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Moritz Kreutzer Georg Hager Gerhard Wellein Holger Fehske and Alan\u00a0R Bishop. 2014. A unified sparse matrix data format for efficient general sparse matrix-vector multiplication on modern processors with wide SIMD units. SIAM Journal on Scientific Computing 36 5 (2014) C401\u2013C423.","DOI":"10.1137\/130930352"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Chenyang Li Tian Xia Wenzhe Zhao Nanning Zheng and Pengju Ren. 2021. SpV8: Pursuing Optimal Vectorization and Regular Computation Pattern in SpMV. 2021 58th ACM\/IEEE Design Automation Conference (DAC) (2021) 661\u2013666. https:\/\/api.semanticscholar.org\/CorpusID:243876169","DOI":"10.1109\/DAC18074.2021.9586251"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Yishui Li Peizhen Xie Xinhai Chen J. Liu Bo Yang Shengguo Li Chunye Gong Xinbiao Gan and Han Xu. 2019. VBSF: a new storage format for SIMD sparse matrix\u2013vector multiplication on modern processors. The Journal of Supercomputing 76 (2019) 2063\u20132081. https:\/\/api.semanticscholar.org\/CorpusID:106410121","DOI":"10.1007\/s11227-019-02835-4"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Peter Lindstrom. 2014. Fixed-Rate Compressed Floating-Point Arrays. IEEE Transactions on Visualization and Computer Graphics 20 12 (2014) 2674\u20132683. https:\/\/doi.org\/10.1109\/TVCG.2014.2346458","DOI":"10.1109\/TVCG.2014.2346458"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Peter Lindstrom and Martin Isenburg. 2006. Fast and Efficient Compression of Floating-Point Data. IEEE Transactions on Visualization and Computer Graphics 12 5 (2006) 1245\u20131250. https:\/\/doi.org\/10.1109\/TVCG.2006.143","DOI":"10.1109\/TVCG.2006.143"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"crossref","unstructured":"J. Liu. 2022. Accuracy Controllable SpMV Optimization on GPU. Journal of Physics: Conference Series 2363 (2022). https:\/\/api.semanticscholar.org\/CorpusID:253417997","DOI":"10.1088\/1742-6596\/2363\/1\/012008"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751209"},{"key":"e_1_3_3_2_30_2","unstructured":"John\u00a0D McCalpin et\u00a0al. 1995. Memory bandwidth and machine balance in current high performance computers. IEEE computer society technical committee on computer architecture (TCCA) newsletter 2 19-25 (1995)."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.57"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS54959.2023.00072"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/DCC.2006.35"},{"key":"e_1_3_3_2_34_2","unstructured":"Skyler Ruiter Seth Wolfgang Marc Tunnell Timothy Triche Erin Carrier and Zachary\u00a0J. DeBruine. 2023. Value-Compressed Sparse Column (VCSC): Sparse Matrix Storage for Redundant Data. ArXiv abs\/2309.04355 (2023). https:\/\/api.semanticscholar.org\/CorpusID:261660589"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Prabhjot Sandhu Clark Verbrugge and Laurie\u00a0J. Hendren. 2020. A Fully Structure-Driven Performance Analysis of Sparse Matrix-Vector Multiplication. Proceedings of the ACM\/SPEC International Conference on Performance Engineering (2020). https:\/\/api.semanticscholar.org\/CorpusID:215752935","DOI":"10.1145\/3358960.3379131"},{"key":"e_1_3_3_2_36_2","unstructured":"Seung\u00a0Woo Son Zhengzhang Chen William Hendrix Ankit Agrawal Wei keng Liao and Alok\u00a0N. Choudhary. 2014. Data Compression for the Exascale Computing Era - Survey. Supercomput. Front. Innov. 1 (2014) 76\u201388. https:\/\/api.semanticscholar.org\/CorpusID:3527510"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"crossref","unstructured":"Zhaonian Tan Weixing Ji Jianhua Gao Yueyan Zhao Akrem Benatia Yizhuo Wang and Feng Shi. 2020. MMSparse: 2D partitioning of sparse matrix based on mathematical morphology. Future Gener. Comput. Syst. 108 (2020) 521\u2013532. https:\/\/api.semanticscholar.org\/CorpusID:216022538","DOI":"10.1016\/j.future.2020.02.076"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"crossref","unstructured":"Chenggang\u00a0Clarence Yan Hui Yu Weizhi Xu Yingping Zhang Bochuan Chen Zhu Tian Yuxuan Wang and Jian Yin. 2015. Memory bandwidth optimization of SpMV on GPGPUs. Frontiers of Computer Science 9 (2015) 431\u2013441. https:\/\/api.semanticscholar.org\/CorpusID:3404873","DOI":"10.1007\/s11704-014-4127-1"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-21395-3_5"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"crossref","unstructured":"Naoki Yoshifuji Ryo Sakamoto Keigo Nitadori and Junichiro Makino. 2016. Implementation and Evaluation of Data-Compression Algorithms for Irregular-Grid Iterative Methods on the PEZY-SC Processor. 2016 6th Workshop on Irregular Applications: Architecture and Algorithms (IA3) (2016) 58\u201361. https:\/\/api.semanticscholar.org\/CorpusID:16110604","DOI":"10.1109\/IA3.2016.015"}],"event":{"name":"ICS '25: 2025 International Conference on Supercomputing","location":"Salt Lake City USA","acronym":"ICS '25","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 39th ACM International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721145.3725767","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T13:00:51Z","timestamp":1755867651000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721145.3725767"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,8]]},"references-count":39,"alternative-id":["10.1145\/3721145.3725767","10.1145\/3721145"],"URL":"https:\/\/doi.org\/10.1145\/3721145.3725767","relation":{},"subject":[],"published":{"date-parts":[[2025,6,8]]},"assertion":[{"value":"2025-08-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}