{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T22:50:19Z","timestamp":1742943019895,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030328122"},{"type":"electronic","value":"9783030328139"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","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":[[2019]]},"DOI":"10.1007\/978-3-030-32813-9_19","type":"book-chapter","created":{"date-parts":[[2019,10,15]],"date-time":"2019-10-15T15:01:33Z","timestamp":1571151693000},"page":"233-247","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Benchmarking SpMV Methods on Many-Core Platforms"],"prefix":"10.1007","author":[{"given":"Biwei","family":"Xie","sequence":"first","affiliation":[]},{"given":"Zhen","family":"Jia","sequence":"additional","affiliation":[]},{"given":"Yungang","family":"Bao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,10,8]]},"reference":[{"key":"19_CR1","unstructured":"Ravishankar, M., et al.: Distributed memory code generation for mixed irregular\/regular computations. In: Proceedings of the 20th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2015, pp. 65\u201375. ACM, New York (2015). http:\/\/doi.acm.org\/10.1145\/2688500.2688515"},{"key":"19_CR2","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1145\/2737924.2738003","volume":"506","author":"A Venkat","year":"2015","unstructured":"Venkat, A., Hall, M., Strout, M.: Loop and data transformations for sparse matrix code. SIGPLAN Not. 506, 521\u2013532 (2015). https:\/\/doi.org\/10.1145\/2737924.2738003","journal-title":"SIGPLAN Not."},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Bigdatabench: a big data benchmark suite from internet services. In: Proceedings of the 20th IEEE International Symposium on High Performance Computer Architecture, HPCA 2014, pp. 488\u2013499, Feburary 2014","DOI":"10.1109\/HPCA.2014.6835958"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Jia, Z., Wang, L., Zhan, J., Zhang, L., Luo, C.: Characterizing data analysis workloads in data centers. In: Proceedings of the IEEE International Symposium on Workload Characterization, IISWC 2013, pp. 66\u201376, September 2013","DOI":"10.1109\/IISWC.2013.6704671"},{"key":"19_CR5","unstructured":"Liu, C., Xie, B., Liu, X., Xue, W., Yang, H., Liu, X.: Towards efficient SpMV on sunway manycore architectures. In: Proceedings of the 2018 International Conference on Supercomputing, ICS 2018, pp. 363\u2013373. ACM, New York (2018). http:\/\/doi.acm.org\/10.1145\/3205289.3205313"},{"key":"19_CR6","unstructured":"Buono, D., et al.: Optimizing sparse matrix-vector multiplication for large-scale data analytics. In: Proceedings of the 30th International Conference on Supercomputing, ICS 2016, pp. 37:1\u201337:12. ACM, New York (2016). http:\/\/doi.acm.org\/10.1145\/2925426.2926278"},{"key":"19_CR7","unstructured":"Pinar, A., Heath, M.T.: Improving performance of sparse matrix-vector multiplication. In: Proceedings of the 13th ACM\/IEEE Conference on Supercomputing, ICS 1999. ACM, New York (1999). http:\/\/doi.acm.org\/10.1145\/331532.331562"},{"key":"19_CR8","first-page":"1","volume":"99","author":"L Yavits","year":"2017","unstructured":"Yavits, L., Ginosar, R.: Accelerator for sparse machine learning. IEEE Comput. Archit. Lett. 99, 1 (2017)","journal-title":"IEEE Comput. Archit. Lett."},{"key":"19_CR9","doi-asserted-by":"publisher","unstructured":"Greathouse, J.L., Daga, M.: Efficient sparse matrix-vector multiplication on GPUs using the CSR storage format. In: Proceedings of the ACM\/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2014, pp. 769\u2013780. IEEE Press, Piscataway (2014). https:\/\/doi.org\/10.1109\/SC.2014.68","DOI":"10.1109\/SC.2014.68"},{"key":"19_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/978-3-642-38750-0_12","volume-title":"Supercomputing","author":"W Abu-Sufah","year":"2013","unstructured":"Abu-Sufah, W., Abdel Karim, A.: Auto-tuning of sparse matrix-vector multiplication on graphics processors. In: Kunkel, J.M., Ludwig, T., Meuer, H.W. (eds.) ISC 2013. LNCS, vol. 7905, pp. 151\u2013164. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-38750-0_12"},{"key":"19_CR11","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, PLDI 2013, pp. 117\u2013126. ACM, New York (2013). http:\/\/doi.acm.org\/10.1145\/2462156.2462181"},{"key":"19_CR12","unstructured":"Elafrou, A., Goumas, G., Koziris, N.: A lightweight optimization selection method for sparse matrix-vector multiplication. arXiv e-prints, November 2015"},{"key":"19_CR13","unstructured":"Yan, S., Li, C., Zhang, Y., Zhou, H.: YASPMV: yet another SpMV framework on GPUs. In: Proceedings of the 19th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2014, pp. 107\u2013118. ACM, New York (2014). http:\/\/doi.acm.org\/10.1145\/2555243.2555255"},{"key":"19_CR14","unstructured":"Sedaghati, N., Mu, T., Pouchet, L.-N., Parthasarathy, S., Sadayappan, P.: Automatic selection of sparse matrix representation on GPUs. In: Proceedings of the 29th ACM on International Conference on Supercomputing, ICS 2015, pp. 99\u2013108. ACM, New York (2015). http:\/\/doi.acm.org\/10.1145\/2751205.2751244"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Li, J., Liao, C., Shen, X.: Bridging the gap between deep learning and sparse matrix format selection. In: Proceedings of the 23rd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2018, pp. 94\u2013108. ACM, New York (2018)","DOI":"10.1145\/3178487.3178495"},{"key":"19_CR16","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/MM.2016.25","volume":"362","author":"A Sodani","year":"2016","unstructured":"Sodani, A., et al.: Knights landing: second-generation Intel Xeon Phi product. IEEE Micro 362, 34\u201346 (2016). https:\/\/doi.org\/10.1109\/MM.2016.25","journal-title":"IEEE Micro"},{"key":"19_CR17","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1007\/978-3-319-06486-4_7","volume-title":"High-Performance Computing on the Intel\u00ae Xeon Phi\u2122","author":"E Wang","year":"2014","unstructured":"Wang, E., et al.: Intel math kernel library. In: Wang, E. (ed.) High-Performance Computing on the Intel\u00ae Xeon Phi\u2122, pp. 167\u2013188. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-06486-4_7"},{"key":"19_CR18","unstructured":"CUDA CUSPARSE Library: NVIDIA, August 2010"},{"key":"19_CR19","unstructured":"Dalton, S., Bell, N., Olson, L., Garland, M.: CUSP: generic parallel algorithms for sparse matrix and graph computations, version 0.5.0. (2014). http:\/\/cusplibrary.github.io\/"},{"key":"19_CR20","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1006\/jsco.1996.0125","volume":"243\u20134","author":"W Bosma","year":"1997","unstructured":"Bosma, W., Cannon, J., Playoust, C.: The magma algebra system I: the user language. J. Symb. Comput. 243\u20134, 235\u2013265 (1997). https:\/\/doi.org\/10.1006\/jsco.1996.0125","journal-title":"J. Symb. Comput."},{"key":"19_CR21","unstructured":"Ashari, A., Sedaghati, N., Eisenlohr, J., Sadayappan, P.: An efficient two-dimensional blocking strategy for sparse matrix-vector multiplication on GPUs. In: Proceedings of the 28th ACM International Conference on Supercomputing, ICS 2014, pp. 273\u2013282. ACM, New York (2014). http:\/\/doi.acm.org\/10.1145\/2597652.2597678"},{"key":"19_CR22","unstructured":"Liu, X., Smelyanskiy, M., Chow, E., Dubey, P.: Efficient sparse matrix-vector multiplication on x86-based many-core processors. In: Proceedings of the 27th ACM International Conference on Supercomputing, ICS 2013, pp. 273\u2013282. ACM, New York (2013). http:\/\/doi.acm.org\/10.1145\/2464996.2465013"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Xie, B., et al.: CVR: efficient vectorization of spmv on x86 processors. In: Proceedings of the 16th IEEE\/ACM International Symposium on Code Generation and Optimization, CGO 2018 (2018)","DOI":"10.1145\/3168818"},{"key":"19_CR24","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, ICS 2015, pp. 339\u2013350. ACM, New York (2015)","DOI":"10.1145\/2751205.2751209"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Tang, W.T., et al.: Optimizing and auto-tuning scale-free sparse matrix-vector multiplication on Intel Xeon Phi. In: Proceedings of the 13th IEEE\/ACM International Symposium on Code Generation and Optimization, CGO 2015, pp. 136\u2013145. IEEE Computer Society, Washington (2015)","DOI":"10.1109\/CGO.2015.7054194"},{"key":"19_CR26","unstructured":"Bell, N., Garland, M.: Implementing sparse matrix-vector multiplication on throughput-oriented processors. In: Proceedings of the ACM\/IEEE Conference on High Performance Computing Networking, Storage and Analysis, SC 2009, pp. 18:1\u201318:11. ACM, New York (2009). http:\/\/doi.acm.org\/10.1145\/1654059.1654078"},{"key":"19_CR27","doi-asserted-by":"publisher","unstructured":"Merrill, D., Garland, M.: Merge-based parallel sparse matrix-vector multiplication. In: Proceedings of the ACM\/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2016, pp. 58:1\u201358:12. IEEE, Piscataway (2016). https:\/\/doi.org\/10.1109\/SC.2016.57","DOI":"10.1109\/SC.2016.57"},{"key":"19_CR28","unstructured":"Davis, T.A.: The University of Florida sparse matrix collection. NA DIGEST (1997)"}],"container-title":["Lecture Notes in Computer Science","Benchmarking, Measuring, and Optimizing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-32813-9_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,19]],"date-time":"2021-02-19T03:57:01Z","timestamp":1613707021000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-32813-9_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030328122","9783030328139"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-32813-9_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"8 October 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Bench","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Benchmarking, Measuring and Optimization","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Seattle, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bench2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/prof.ict.ac.cn\/Bench18\/","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":"CyberDhair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"51","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":"20","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":"39% - 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":"3","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}