{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T14:30:54Z","timestamp":1787495454949,"version":"build-2736575974"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819248049","type":"print"},{"value":"9789819248056","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-981-92-4805-6_26","type":"book-chapter","created":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T13:47:08Z","timestamp":1787492828000},"page":"390-403","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ARROW: Adaptive Row Reorganization for\u00a0Warp-Balanced SpMV"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1092-5363","authenticated-orcid":false,"given":"Yuxiang","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3828-0015","authenticated-orcid":false,"given":"Jianhua","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3250-0435","authenticated-orcid":false,"given":"Weixing","family":"Ji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,24]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Ahmad, K., Sundar, H., Hall, M.: Data-driven mixed precision sparse matrix-vector multiplication for GPUs. ACM Trans. Archit. Code Optim. 16(4) (2019)","DOI":"10.1145\/3371275"},{"key":"26_CR2","unstructured":"Bell, N., Garland, M.: Efficient sparse matrix-vector multiplication on CUDA, NVIDIA Corporation (2008). NVR-2008-004 NVIDIA Technical Report"},{"key":"26_CR3","doi-asserted-by":"crossref","unstructured":"Benatia, A., Ji, W., Wang, Y., Shi, F.: BestSF: a sparse meta-format for optimizing SpMV on GPU. ACM Trans. Archit. Code Optim. 15(3) (2018)","DOI":"10.1145\/3226228"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Bian, H., Huang, J., Dong, R., Liu, L., Wang, X.: CSR2: a new format for SIMD-accelerated SPMV. In: Proceedings of the 2020 IEEE\/ACM International Symposium on Cluster, Cloud and Internet Computing, pp. 350\u2013359 (2020)","DOI":"10.1109\/CCGrid49817.2020.00-58"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., Yu, J.X.: Bitmap-based sparse matrix-vector multiplication with tensor cores. In: Proceedings of the 53rd International Conference on Parallel Processing, pp. 1135\u20131144 (2024)","DOI":"10.1145\/3673038.3673055"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Daga, M., Greathouse, J.L.: Structural agnostic SPMV: adapting CSR-adaptive for irregular matrices. In: Proceedings of the 2015 IEEE 22nd International Conference on High Performance Computing, pp. 64\u201374 (2015)","DOI":"10.1109\/HiPC.2015.55"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Davis, T.A., Hu, Y.: The university of Florida sparse matrix collection. ACM Trans. Math. Softw. 38(1) (2011)","DOI":"10.1145\/2049662.2049663"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Du, Z., Li, J., Wang, Y., Li, X., Tan, G., Sun, N.: AlphaSparse: generating high performance SPMV codes directly from sparse matrices. In: SC22: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201315 (2022)","DOI":"10.1109\/SC41404.2022.00071"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Du, Z., Liu, Y., Sun, N., Cui, H., Feng, X., Li, J.: SRSparse: generating codes for high-performance sparse matrix-vector semiring computations. ACM Trans. Archit. Code Optim. 22 (2025)","DOI":"10.1145\/3722114"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Filippone, S., Cardellini, V., Barbieri, D., Fanfarillo, A.: Sparse matrix-vector multiplication on GPGPUs. ACM Trans. Math. Softw. 43(4) (2017)","DOI":"10.1145\/3017994"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Gao, J., Ji, W., Liu, J., Shao, S., Wang, Y., Shi, F.: AMF-CSR: adaptive multi-row folding of CSR for SPMV on GPU. In: Proceedings of the 2021 IEEE 27th International Conference on Parallel and Distributed Systems, pp. 418\u2013425 (2021)","DOI":"10.1109\/ICPADS53394.2021.00058"},{"key":"26_CR12","unstructured":"Gao, J., Liu, B., Ji, W., Huang, H.: A systematic literature survey of sparse matrix-vector multiplication (2024). arXiv:2404.06047 arXiv preprint"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Greathouse, J.L., Daga, M.: Efficient sparse matrix-vector multiplication on GPUs using the CSR storage format. In: SC\u201914: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 769\u2013780. IEEE (2014)","DOI":"10.1109\/SC.2014.68"},{"key":"26_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2022.101609","volume":"61","author":"K Isupov","year":"2022","unstructured":"Isupov, K.: Multiple-precision sparse matrix-vector multiplication on GPUs. J. Comput. Sci. 61, 101609 (2022)","journal-title":"J. Comput. Sci."},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Kjolstad, F., Kamil, S., Chou, S., Lugato, D., Amarasinghe, S.: The tensor algebra compiler. Proc. ACM Program. Lang.1 (2017)","DOI":"10.1145\/3133901"},{"issue":"5","key":"26_CR16","doi-asserted-by":"publisher","first-page":"C401","DOI":"10.1137\/130930352","volume":"36","author":"M Kreutzer","year":"2014","unstructured":"Kreutzer, M., Hager, G., Wellein, G., Fehske, H., Bishop, A.R.: A unified sparse matrix data format for efficient general sparse matrix-vector multiplication on modern processors with wide simd units. SIAM J. Sci. Comput. 36(5), C401\u2013C423 (2014)","journal-title":"SIAM J. Sci. Comput."},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Li, J., Tan, G., Chen, M., Sun, N.: 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, pp. 117\u2013126 (2013)","DOI":"10.1145\/2491956.2462181"},{"issue":"6","key":"26_CR18","first-page":"549","volume":"6","author":"J Liu","year":"2024","unstructured":"Liu, J., Wang, Y., Gao, J., Ji, W.: PSPMV: precision-based sparse matrix partition and SPMV optimization. CCF Trans. High Perf. Comput. 6(6), 549\u2013565 (2024)","journal-title":"CCF Trans. High Perf. Comput."},{"key":"26_CR19","doi-asserted-by":"crossref","unstructured":"Liu, J., Zhao, Z., Ding, Z., Brock, B., Rong, H., Zhang, Z.: UniSparse: an intermediate language for general sparse format customization. Proc. ACM Program. Lang 8 (2024)","DOI":"10.1145\/3649816"},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Liu, W., Vinter, B.: CSR5: an efficient storage format for cross-platform sparse matrix-vector multiplication. In: Proceedings of the 29th ACM International Conference on Supercomputing, pp. 339\u2013350 (2015)","DOI":"10.1145\/2751205.2751209"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Lu, Y., Liu, W.: DASP: specific dense matrix multiply-accumulate units accelerated general sparse matrix-vector multiplication. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (2023)","DOI":"10.1145\/3581784.3607051"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Ma, T., Gou, Z., Xu, N., Sun, S.: Efficient multi-GPU implementations of preconditioned conjugate gradient method. Adv. Eng. Softw. 207 (2025)","DOI":"10.1016\/j.advengsoft.2025.103936"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Merrill, D., Garland, M.: Merge-based parallel sparse matrix-vector multiplication. In: SC \u201916: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 678\u2013689 (2016)","DOI":"10.1109\/SC.2016.57"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Monakov, A., Lokhmotov, A., Avetisyan, A.: Automatically tuning sparse matrix-vector multiplication for GPU architectures. In: International Conference on High-Performance Embedded Architectures and Compilers, pp. 111\u2013125. Springer (2010)","DOI":"10.1007\/978-3-642-11515-8_10"},{"key":"26_CR25","unstructured":"NVIDIA: Volta Architecture Whitepaper, NVIDIA White Paper (2017)"},{"key":"26_CR26","unstructured":"NVIDIA: NVIDIA A100 Tensor Core GPU Architecture, NVIDIA White Paper (2020)"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Tezcan, E., Torun, T., Ko\u015far, F., Kaya, K., Unat, D.: Mixed and multi-precision SPMV for GPUs with row-wise precision selection. In: 2022 IEEE 34th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD), pp. 31\u201340 (2022)","DOI":"10.1109\/SBAC-PAD55451.2022.00014"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"Won, J., Mendis, C., Emer, J.S., Amarasinghe, S.: WACO: learning workload-aware co-optimization of the format and schedule of a sparse tensor program. In: Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, vol. 2, pp. 920\u2013934 (2023)","DOI":"10.1145\/3575693.3575742"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Zhang, G., Wu, Y., Hong, R., Yang, Y., Fu, Y.: Block-wise dynamic mixed-precision for sparse matrix-vector multiplication on GPUS. J. Supercomput. 80(10), 13681\u201313713 (2024)","DOI":"10.1007\/s11227-024-05949-6"}],"container-title":["Lecture Notes in Computer Science","Advanced Parallel Processing Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-4805-6_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T13:47:11Z","timestamp":1787492831000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-4805-6_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,24]]},"ISBN":["9789819248049","9789819248056"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-4805-6_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,24]]},"assertion":[{"value":"24 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"APPT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Advanced Parallel Processing Technologies","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brussels","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Belgium","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"appt2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.appt-conference.com\/2026","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}