{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T07:58:36Z","timestamp":1767945516989,"version":"3.49.0"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031695827","type":"print"},{"value":"9783031695834","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-69583-4_1","type":"book-chapter","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T19:02:05Z","timestamp":1724612525000},"page":"3-16","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Accelerated Block-Sparsity-Aware Matrix Reordering for\u00a0Leveraging Tensor Cores in\u00a0Sparse Matrix-Multivector Multiplication"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1870-4763","authenticated-orcid":false,"given":"Eunji","family":"Lee","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4540-2117","authenticated-orcid":false,"given":"Yoonsang","family":"Han","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4992-6181","authenticated-orcid":false,"given":"Gordon Euhyun","family":"Moon","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,26]]},"reference":[{"key":"1_CR1","unstructured":"Ahrens, P., Boman, E.G.: On optimal partitioning for sparse matrices in variable block row format. arXiv preprint arXiv:2005.12414 (2020)"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Bulu\u00e7, A., Fineman, J.T., Frigo, M., Gilbert, J.R., Leiserson, C.E.: Parallel sparse matrix-vector and matrix-transpose-vector multiplication using compressed sparse blocks. In: Proceedings of the Twenty-First Annual Symposium on Parallelism in Algorithms and Architectures, pp. 233\u2013244 (2009)","DOI":"10.1145\/1583991.1584053"},{"issue":"5","key":"1_CR3","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1145\/1837853.1693471","volume":"45","author":"JW Choi","year":"2010","unstructured":"Choi, J.W., Singh, A., Vuduc, R.W.: Model-driven autotuning of sparse matrix-vector multiply on GPUs. ACM Sigplan Notices 45(5), 115\u2013126 (2010)","journal-title":"ACM Sigplan Notices"},{"issue":"1","key":"1_CR4","first-page":"1","volume":"38","author":"TA Davis","year":"2011","unstructured":"Davis, T.A., Hu, Y.: The university of florida sparse matrix collection. ACM Trans. Math. Softw. (TOMS) 38(1), 1\u201325 (2011)","journal-title":"ACM Trans. Math. Softw. (TOMS)"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Gale, T., Zaharia, M., Young, C., Elsen, E.: Sparse GPU kernels for deep learning. In: SC20: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201314. IEEE (2020)","DOI":"10.1109\/SC41405.2020.00021"},{"issue":"1","key":"1_CR6","first-page":"10882","volume":"22","author":"T Hoefler","year":"2021","unstructured":"Hoefler, T., Alistarh, D., Ben-Nun, T., Dryden, N., Peste, A.: Sparsity in deep learning: pruning and growth for efficient inference and training in neural networks. J. Mach. Learn. Res. 22(1), 10882\u201311005 (2021)","journal-title":"J. Mach. Learn. Res."},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Hong, C., Sukumaran-Rajam, A., Nisa, I., Singh, K., Sadayappan, P.: Adaptive sparse tiling for sparse matrix multiplication. In: Proceedings of the 24th Symposium on Principles and Practice of Parallel Programming, pp. 300\u2013314 (2019)","DOI":"10.1145\/3293883.3295712"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Huang, G., Dai, G., Wang, Y., Yang, H.: Ge-spmm: general-purpose sparse matrix-matrix multiplication on GPUs for graph neural networks. In: SC20: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201312. IEEE (2020)","DOI":"10.1109\/SC41405.2020.00076"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Jiang, P., Hong, C., Agrawal, G.: A novel data transformation and execution strategy for accelerating sparse matrix multiplication on GPUs. In: Proceedings of the 25th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 376\u2013388 (2020)","DOI":"10.1145\/3332466.3374546"},{"key":"1_CR10","unstructured":"Jouppi, N.P., et\u00a0al.: In-datacenter performance analysis of a tensor processing unit. In: Proceedings of the 44th Annual International Symposium on Computer Architecture, pp. 1\u201312 (2017)"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Labini, P.S., Bernaschi, M., Nutt, W., Silvestri, F., Vella, F.: Blocking sparse matrices to leverage dense-specific multiplication. In: 2022 IEEE\/ACM Workshop on Irregular Applications: Architectures and Algorithms (IA3), pp. 19\u201324. IEEE (2022)","DOI":"10.1109\/IA356718.2022.00009"},{"issue":"2","key":"1_CR12","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1109\/TPDS.2015.2401575","volume":"27","author":"D Langr","year":"2015","unstructured":"Langr, D., Tvrdik, P.: Evaluation criteria for sparse matrix storage formats. IEEE Trans. Parallel Distrib. Syst. 27(2), 428\u2013440 (2015)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Lee, E., Han, Y., Moon, G.E.: Accelerated block-sparsity-aware matrix reordering for leveraging tensor cores in sparse matrix-multivector multiplication. In: 30th International European Conference on Parallel and Distributed Computing. Zenodo (2024). https:\/\/doi.org\/10.5281\/zenodo.11579181","DOI":"10.1109\/IPDPSW63119.2024.00199"},{"key":"1_CR14","unstructured":"Nvidia: Nvidia A100 tensor core GPU architecture. Technical report (2020). https:\/\/www.nvidia.com\/content\/dam\/en-zz\/Solutions\/Data-Center\/nvidia-ampere-architecture-whitepaper.pdf"},{"key":"1_CR15","unstructured":"Nvidia: Accelerating matrix multiplication with block sparse format and nvidia tensor cores. Technical report (2021). https:\/\/developer.nvidia.com\/blog\/accelerating-matrix-multiplication-with-block-sparse-format-and-nvidia-tensor-cores\/"},{"key":"1_CR16","unstructured":"Nvidia: The api reference guide for cublas, the cuda basic linear algebra subroutine library. Technical report (2024). https:\/\/docs.nvidia.com\/cuda\/cublas\/"},{"key":"1_CR17","unstructured":"Nvidia: The api reference guide for cusparse, the cuda sparse matrix library. Technical report (2024). https:\/\/docs.nvidia.com\/cuda\/cusparse\/index.html"},{"key":"1_CR18","unstructured":"Nvidia: Cuda c++ programming guide. Technical report (2024). https:\/\/docs.nvidia.com\/cuda\/pdf\/CUDA_C_Programming_Guide.pdf"},{"issue":"4","key":"1_CR19","doi-asserted-by":"publisher","first-page":"1107","DOI":"10.1137\/S1064827501393393","volume":"24","author":"Y Saad","year":"2003","unstructured":"Saad, Y.: Finding exact and approximate block structures for ilu preconditioning. SIAM J. Sci. Comput. 24(4), 1107\u20131123 (2003)","journal-title":"SIAM J. Sci. Comput."},{"key":"1_CR20","unstructured":"Wang, Y., Feng, B., Wang, Z., Huang, G., Ding, Y.: TC-GNN: bridging sparse GNN computation and dense tensor cores on GPUs. In: 2023 USENIX Annual Technical Conference (USENIX ATC 2023), pp. 149\u2013164 (2023)"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2024: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-69583-4_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T19:02:30Z","timestamp":1724612550000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-69583-4_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031695827","9783031695834"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-69583-4_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"26 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Madrid","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.euro-par.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}