{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T20:19:35Z","timestamp":1743020375890,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030692438"},{"type":"electronic","value":"9783030692445"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-69244-5_28","type":"book-chapter","created":{"date-parts":[[2021,2,20]],"date-time":"2021-02-20T16:36:12Z","timestamp":1613838972000},"page":"318-329","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Dynamic Parameter Tuning Method for High Performance SpMM"],"prefix":"10.1007","author":[{"given":"Bin","family":"Qi","sequence":"first","affiliation":[]},{"given":"Kazuhiko","family":"Komatsu","sequence":"additional","affiliation":[]},{"given":"Masayuki","family":"Sato","sequence":"additional","affiliation":[]},{"given":"Hiroaki","family":"Kobayashi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,2,21]]},"reference":[{"issue":"4","key":"28_CR1","doi-asserted-by":"publisher","first-page":"C123","DOI":"10.1137\/110838844","volume":"34","author":"N Bell","year":"2012","unstructured":"Bell, N., Dalton, S., Olson, L.: Exposing fine-grained parallelism in algebraic multigrid methods. SIAM J. Sci. Comput. 34(4), C123\u2013C152 (2012). https:\/\/doi.org\/10.1137\/110838844","journal-title":"SIAM J. Sci. Comput."},{"key":"28_CR2","doi-asserted-by":"publisher","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, pp. 233\u2013244. SPAA 2009, Association for Computing Machinery, New York, NY, USA (2009). https:\/\/doi.org\/10.1145\/1583991.1584053","DOI":"10.1145\/1583991.1584053"},{"issue":"4","key":"28_CR3","doi-asserted-by":"publisher","first-page":"923","DOI":"10.1109\/TPDS.2018.2871189","volume":"30","author":"Y Chen","year":"2019","unstructured":"Chen, Y., Li, K., Yang, W., Xiao, G., Xie, X., Li, T.: Performance-aware model for sparse matrix-matrix multiplication on the sunway taihulight supercomputer. IEEE Trans. Parallel Distrib. Syst. 30(4), 923\u2013938 (2019). https:\/\/doi.org\/10.1109\/TPDS.2018.2871189","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"28_CR4","doi-asserted-by":"publisher","unstructured":"Dalton, S., Olson, L., Bell, N.: Optimizing sparse matrix\u2013matrix multiplication for the gpu. ACM Trans. Math. Softw. 41(4) (2015). https:\/\/doi.org\/10.1145\/2699470","DOI":"10.1145\/2699470"},{"key":"28_CR5","doi-asserted-by":"publisher","unstructured":"Davis, T.A., Hu, Y.: The university of florida sparse matrix collection. ACM Trans. Math. Softw. textbf38(1) (2011). https:\/\/doi.org\/10.1145\/2049662.2049663","DOI":"10.1145\/2049662.2049663"},{"key":"28_CR6","doi-asserted-by":"publisher","unstructured":"Deveci, M., Trott, C., Rajamanickam, S.: Performance-portable sparse matrix-matrix multiplication for many-core architectures. In: 2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 693\u2013702 (2017). https:\/\/doi.org\/10.1109\/IPDPSW.2017.8","DOI":"10.1109\/IPDPSW.2017.8"},{"key":"28_CR7","unstructured":"Forum, M.P.: MPI: a message-passing interface standard. Technical report, USA (1994)"},{"key":"28_CR8","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/MCSE.2008.45","volume":"10","author":"J Gilbert","year":"2008","unstructured":"Gilbert, J., Reinhardt, S., Shah, V.: A unified framework for numerical and combinatorial computing. Comput. Sci. Eng. 10, 20\u201325 (2008). https:\/\/doi.org\/10.1109\/MCSE.2008.45","journal-title":"Comput. Sci. Eng."},{"key":"28_CR9","doi-asserted-by":"publisher","unstructured":"Gilbert, J.R., Moler, C., Schreiber, R.: Sparse matrices in matlab: design and implementation. SIAM J. Matrix Anal. Appl. 13(1), 333\u2013356 (1992). https:\/\/doi.org\/10.1137\/0613024","DOI":"10.1137\/0613024"},{"key":"28_CR10","unstructured":"Graf, D., Labib, K., Uzna\u0144ski, P.: Hamming distance completeness and sparse matrix multiplication (2018)"},{"key":"28_CR11","doi-asserted-by":"publisher","unstructured":"Green, O., Mccoll, R., Bader, D.: GPU merge path: a GPU merging algorithm (2014). https:\/\/doi.org\/10.1145\/2304576.2304621","DOI":"10.1145\/2304576.2304621"},{"key":"28_CR12","doi-asserted-by":"publisher","unstructured":"Gremse, F., H\u00f6fter, A., Schwen, L.O., Kiessling, F., Naumann, U.:Gpu-accelerated sparse matrix-matrix multiplication by iterative row merging. SIAM J. Sci. Comput. 37(1), C54\u2013C71 (2015).https:\/\/doi.org\/10.1137\/130948811","DOI":"10.1137\/130948811"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Komatsu, K., et al.: Performance evaluation of a vector supercomputer sx-aurora tsubasa. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis. SC 2018, IEEE Press (2018)","DOI":"10.1109\/SC.2018.00057"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, F., Araki, T., Qiu, J.: Generalized sparse matrix-matrix multiplication for vector engines and graph applications. In: 2019 IEEE\/ACM Workshop on Memory Centric High Performance Computing (MCHPC). pp. 33\u201342 (2019)","DOI":"10.1109\/MCHPC49590.2019.00012"},{"issue":"1","key":"28_CR15","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1109\/TPDS.2014.2308221","volume":"26","author":"K Li","year":"2015","unstructured":"Li, K., Yang, W., Li, K.: Performance analysis and optimization for SPMV on GPU using probabilistic modeling. IEEE Trans. Parallel and Distrib. Syst. 26(1), 196\u2013205 (2015). https:\/\/doi.org\/10.1109\/TPDS.2014.2308221","journal-title":"IEEE Trans. Parallel and Distrib. Syst."},{"key":"28_CR16","doi-asserted-by":"publisher","unstructured":"Liu, W., Vinter, B.: A framework for general sparse matrix-matrix multiplication on GPUs and heterogeneous processors. J. Parallel Distrib. Comput. 85, 47\u201361 (2015). https:\/\/doi.org\/10.1016\/j.jpdc.2015.06.010","DOI":"10.1016\/j.jpdc.2015.06.010"},{"key":"28_CR17","doi-asserted-by":"publisher","unstructured":"Matam, K., Krishna Bharadwaj Indarapu, S.R., Kothapalli, K.: Sparse matrix-matrix multiplication on modern architectures. In: 2012 19th International Conference on High Performance Computing, pp. 1\u201310 (2012). https:\/\/doi.org\/10.1109\/HiPC.2012.6507483","DOI":"10.1109\/HiPC.2012.6507483"},{"key":"28_CR18","doi-asserted-by":"publisher","unstructured":"Nagasaka, Y., Nukada, A., Matsuoka, S.: High-performance and memory-saving sparse general matrix-matrix multiplication for NVIDIA pascal GPU. In: 2017 46th International Conference on Parallel Processing (ICPP), pp. 101\u2013110 (2017). https:\/\/doi.org\/10.1109\/ICPP.2017.19","DOI":"10.1109\/ICPP.2017.19"},{"key":"28_CR19","unstructured":"Vingelmann, P., Fitzek, F.H.: NVIDIA Cuda, release: 10.2.89 (2020). https:\/\/developer.nvidia.com\/cuda-toolkit"},{"issue":"7","key":"28_CR20","doi-asserted-by":"publisher","first-page":"1905","DOI":"10.1109\/TKDE.2016.2545664","volume":"28","author":"C Ordonez","year":"2016","unstructured":"Ordonez, C., Zhang, Y., Cabrera, W.: The gamma matrix to summarize dense and sparse data sets for big data analytics. IEEE Trans. Knowl. Data Eng. 28(7), 1905\u20131918 (2016). https:\/\/doi.org\/10.1109\/TKDE.2016.2545664","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"28_CR21","doi-asserted-by":"publisher","unstructured":"Parger, M., Winter, M., Mlakar, D., Steinberger, M.: Speck: accelerating GPU sparse matrix-matrix multiplication through lightweight analysis. In: Proceedings of the 25th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 362\u2013375. PPoPP 2020, Association for Computing Machinery, New York, NY, USA (2020). https:\/\/doi.org\/10.1145\/3332466.3374521","DOI":"10.1145\/3332466.3374521"},{"key":"28_CR22","doi-asserted-by":"publisher","unstructured":"Satish, N., Harris, M., Garland, M.: Designing efficient sorting algorithms for manycore GPUs. In: 2009 IEEE International Symposium on Parallel Distributed Processing, pp. 1\u201310 (2009). https:\/\/doi.org\/10.1109\/IPDPS.2009.5161005","DOI":"10.1109\/IPDPS.2009.5161005"},{"key":"28_CR23","doi-asserted-by":"publisher","unstructured":"Schaub, M.T., Trefois, M., van Dooren, P., Delvenne, J.C.: Sparse matrix factorizations for fast linear solvers with application to laplacian systems. SIAM J. Matrix Anal. Appl. 38(2), 505\u2013529 (2017). https:\/\/doi.org\/10.1137\/16m1077398","DOI":"10.1137\/16m1077398"},{"key":"28_CR24","doi-asserted-by":"publisher","unstructured":"Xie, Z., Tan, G., Liu, W., Sun, N.: IA-SPGEMM: an input-aware auto-tuning framework for parallel sparse matrix-matrix multiplication. In: Proceedings of the ACM International Conference on Supercomputing, pp. 94\u2013105. ICS 2019, Association for Computing Machinery, New York, NY, USA (2019). https:\/\/doi.org\/10.1145\/3330345.3330354","DOI":"10.1145\/3330345.3330354"},{"issue":"9","key":"28_CR25","doi-asserted-by":"publisher","first-page":"2623","DOI":"10.1109\/TC.2014.2366731","volume":"64","author":"W Yang","year":"2015","unstructured":"Yang, W., Li, K., Mo, Z., Li, K.: Performance optimization using partitioned SPMV on GPUs and multicore CPUs. IEEE Trans. Comput. 64(9), 2623\u20132636 (2015). https:\/\/doi.org\/10.1109\/TC.2014.2366731","journal-title":"IEEE Trans. Comput."}],"container-title":["Lecture Notes in Computer Science","Parallel and Distributed Computing, Applications and Technologies"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69244-5_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,20]],"date-time":"2021-02-20T16:48:17Z","timestamp":1613839697000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69244-5_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030692438","9783030692445"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69244-5_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"21 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PDCAT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Parallel and Distributed Computing: Applications and Technologies","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenzhen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 December 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pdcat2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/hpcc.siat.ac.cn\/meeting\/pdcat-paap2020\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OCS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"109","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"34","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"31% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"6","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}