{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T08:40:00Z","timestamp":1766220000274,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322201"],"award-info":[{"award-number":["62322201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["JKF-20240598, JKF-2025012343648"],"award-info":[{"award-number":["JKF-20240598, JKF-2025012343648"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,8]]},"DOI":"10.1145\/3754598.3754632","type":"proceedings-article","created":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T08:34:32Z","timestamp":1766219672000},"page":"564-574","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["OVERT: Orchestrating Vector-Scalar Execution for Efficient SpMV on Modern CPUs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8637-4182","authenticated-orcid":false,"given":"Kelun","family":"Lei","sequence":"first","affiliation":[{"name":"Beihang University, Bejing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1101-7927","authenticated-orcid":false,"given":"Hailong","family":"Yang","sequence":"additional","affiliation":[{"name":"Beihang University, Bejing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3261-3483","authenticated-orcid":false,"given":"Kaige","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beihang University, Bejing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0540-0959","authenticated-orcid":false,"given":"Shaokang","family":"Du","sequence":"additional","affiliation":[{"name":"Beihang University, Bejing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4564-2093","authenticated-orcid":false,"given":"Marc","family":"Casas","sequence":"additional","affiliation":[{"name":"Barcelona Supercomputing Center, Barcelona, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7787-6460","authenticated-orcid":false,"given":"Yufan","family":"Xu","sequence":"additional","affiliation":[{"name":"Independent Researcher, Cupertino, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7186-0556","authenticated-orcid":false,"given":"Zhongzhi","family":"Luan","sequence":"additional","affiliation":[{"name":"Beihang University, Bejing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1829-2817","authenticated-orcid":false,"given":"Yi","family":"Liu","sequence":"additional","affiliation":[{"name":"Beihang University, Bejing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5382-1473","authenticated-orcid":false,"given":"Depei","family":"Qian","sequence":"additional","affiliation":[{"name":"Beihang University, Bejing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,20]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"ARM. 2024. ARM Performance Libraries 24.10. https:\/\/developer.arm.com\/documentation\/101004\/2410\/General-information\/Arm-Performance-Libraries."},{"key":"e_1_3_3_1_3_2","unstructured":"Satish Balay Shrirang Abhyankar Mark Adams Jed Brown Peter Brune Kris Buschelman Lisandro Dalcin Alp Dener Victor Eijkhout W Gropp et\u00a0al. 2019. PETSc users manual."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Manya Bansal Olivia Hsu Kunle Olukotun and Fredrik Kjolstad. 2023. Mosaic: An interoperable compiler for tensor algebra. Proceedings of the ACM on Programming Languages 7 PLDI (2023) 394\u2013419.","DOI":"10.1145\/3591236"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2017.93"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Aart Bik Penporn Koanantakool Tatiana Shpeisman Nicolas Vasilache Bixia Zheng and Fredrik Kjolstad. 2022. Compiler support for sparse tensor computations in MLIR. ACM Transactions on Architecture and Code Optimization (TACO) 19 4 (2022) 1\u201325.","DOI":"10.1145\/3544559"},{"key":"e_1_3_3_1_7_2","first-page":"578","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, et\u00a0al. 2018. { TVM} : An automated { End-to-End} optimizing compiler for deep learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). 578\u2013594."},{"key":"e_1_3_3_1_8_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.","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_3_1_9_2","first-page":"1","volume-title":"Proceedings of the 36th ACM International Conference on Supercomputing","author":"Dias Adhitha","year":"2022","unstructured":"Adhitha Dias, Kirshanthan Sundararajah, Charitha Saumya, and Milind Kulkarni. 2022. SparseLNR: accelerating sparse tensor computations using loop nest restructuring. In Proceedings of the 36th ACM International Conference on Supercomputing. 1\u201314."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00071"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2017.38"},{"key":"e_1_3_3_1_12_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_1_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-47789-6_66"},{"key":"e_1_3_3_1_14_2","first-page":"1","volume-title":"50th International Conference on Parallel Processing","author":"Fei Xiang","year":"2021","unstructured":"Xiang Fei and Youhui Zhang. 2021. Regu2D: Accelerating Vectorization of SpMV on Intel Processors through 2D-partitioning and Regular Arrangement. In 50th International Conference on Parallel Processing. 1\u201311."},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1145\/3696443.3708950","volume-title":"Proceedings of the 23rd ACM\/IEEE International Symposium on Code Generation and Optimization","author":"Ghanbari Reza","year":"2025","unstructured":"Reza Ghanbari, Henry Kao, Jo\u00e3o\u00a0PL De\u00a0Carvalho, Ehsan Amiri, and J\u00a0Nelson Amaral. 2025. Scalar Interpolation: A Better Balance between Vector and Scalar Execution for SuperScalar Architectures. In Proceedings of the 23rd ACM\/IEEE International Symposium on Code Generation and Optimization. 77\u201389."},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","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 (2017) 1\u201329.","DOI":"10.1145\/3133901"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Kornilios Kourtis Vasileios Karakasis Georgios Goumas and Nectarios Koziris. 2011. CSX: an extended compression format for spmv on shared memory systems. ACM SIGPLAN Notices 46 8 (2011) 247\u2013256.","DOI":"10.1145\/2038037.1941587"},{"key":"e_1_3_3_1_18_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_1_19_2","unstructured":"Kelun Lei Shaokang Du Xin You Hailong Yang Zhongzhi Luan Yi Liu and Depei Qian. [n. d.]. Exploiting Dynamic Regular Patterns in Irregular Programs for Efficient Vectorization. ACM Transactions on Architecture and Code Optimization ([n. d.])."},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586251"},{"key":"e_1_3_3_1_21_2","first-page":"117","volume-title":"Proceedings of the 34th ACM SIGPLAN conference on Programming language design and implementation","author":"Li Jiajia","year":"2013","unstructured":"Jiajia Li, Guangming Tan, Mingyu Chen, and Ninghui Sun. 2013. SMAT: An input adaptive auto-tuner for sparse matrix-vector multiplication. In Proceedings of the 34th ACM SIGPLAN conference on Programming language design and implementation. 117\u2013126."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3205289.3205313"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751209"},{"key":"e_1_3_3_1_24_2","first-page":"273","volume-title":"Proceedings of the 27th international ACM conference on International conference on supercomputing","author":"Liu Xing","year":"2013","unstructured":"Xing Liu, Mikhail Smelyanskiy, Edmond Chow, and Pradeep Dubey. 2013. Efficient sparse matrix-vector multiplication on x86-based many-core processors. In Proceedings of the 27th international ACM conference on International conference on supercomputing. ACM, Eugene, OR, USA, 273\u2013282."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Yucheng Low Danny Bickson Joseph Gonzalez Carlos Guestrin Aapo Kyrola and Joseph\u00a0M. Hellerstein. 2012. Distributed GraphLab: a framework for machine learning and data mining in the cloud. Proc. VLDB Endow. 5 8 (2012) 716\u2013727.","DOI":"10.14778\/2212351.2212354"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607051"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.57"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00016"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Narayanan Sundaram Nadathur Satish Md\u00a0Mostofa\u00a0Ali Patwary Subramanya\u00a0R Dulloor Michael\u00a0J Anderson Satya\u00a0Gautam Vadlamudi Dipankar Das and Pradeep Dubey. 2015. GraphMat: High performance graph analytics made productive. Proceedings of the VLDB Endowment 8 11 (2015).","DOI":"10.14778\/2809974.2809983"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1109\/CGO57630.2024.10444812","volume-title":"2024 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)","author":"Swann Ryan","year":"2024","unstructured":"Ryan Swann, Muhammad Osama, Karthik Sangaiah, and Jalal Mahmud. 2024. Seer: Predictive Runtime Kernel Selection for Irregular Problems. In 2024 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO). IEEE, 133\u2013142."},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Endong Wang Qing Zhang Bo Shen Guangyong Zhang Xiaowei Lu Qing Wu Yajuan Wang Endong Wang Qing Zhang Bo Shen et\u00a0al. 2014. Intel math kernel library. High-Performance Computing on the Intel\u00ae Xeon Phi\u2122: How to Fully Exploit MIC Architectures (2014) 167\u2013188.","DOI":"10.1007\/978-3-319-06486-4_7"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1109\/IPDPS57955.2024.00011","volume-title":"2024 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","author":"Wang Luhan","year":"2024","unstructured":"Luhan Wang, Haipeng Jia, Lei Xu, Cunyang Wei, Kun Li, Xianmeng Jiang, and Yunquan Zhang. 2024. VNEC: A Vectorized Non-Empty Column Format for SpMV on CPUs. In 2024 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE, 14\u201325."},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/1362622.1362674"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3168818"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"crossref","unstructured":"Carl Yang Ayd\u0131n Bulu\u00e7 and John\u00a0D Owens. 2022. GraphBLAST: A high-performance linear algebra-based graph framework on the GPU. ACM Transactions on Mathematical Software (TOMS) 48 1 (2022) 1\u201351.","DOI":"10.1145\/3466795"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00065"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433815"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3572848.3577506"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3545008.3545042"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3673038.3673108"}],"event":{"name":"ICPP '25: 54th International Conference on Parallel Processing","location":"San Diego CA USA","acronym":"ICPP '25"},"container-title":["Proceedings of the 54th International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3754598.3754632","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T08:38:24Z","timestamp":1766219904000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3754598.3754632"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,8]]},"references-count":39,"alternative-id":["10.1145\/3754598.3754632","10.1145\/3754598"],"URL":"https:\/\/doi.org\/10.1145\/3754598.3754632","relation":{},"subject":[],"published":{"date-parts":[[2025,9,8]]},"assertion":[{"value":"2025-12-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}