{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T06:29:05Z","timestamp":1793687345123,"version":"4.5.1"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030507428","type":"print"},{"value":"9783030507435","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-50743-5_16","type":"book-chapter","created":{"date-parts":[[2020,6,15]],"date-time":"2020-06-15T15:03:45Z","timestamp":1592233425000},"page":"309-327","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Sparse Linear Algebra on AMD and\u00a0NVIDIA GPUs \u2013 The Race Is On"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5229-3739","authenticated-orcid":false,"given":"Yuhsiang M.","family":"Tsai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1560-921X","authenticated-orcid":false,"given":"Terry","family":"Cojean","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2177-952X","authenticated-orcid":false,"given":"Hartwig","family":"Anzt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,6,15]]},"reference":[{"key":"16_CR1","unstructured":"Anzt, H., Chow, E., Dongarra, J.: On block-asynchronous execution on GPUs. Technical report 291, LAPACK Working Note (2016)"},{"issue":"1","key":"16_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3380930","volume":"7","author":"H Anzt","year":"2020","unstructured":"Anzt, H., et al.: Load-balancing sparse matrix vector product kernels on GPUs. ACM Trans. Parallel Comput. 7(1), 1\u201326 (2020). https:\/\/doi.org\/10.1145\/3380930","journal-title":"ACM Trans. Parallel Comput."},{"key":"16_CR3","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611971538","volume-title":"Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods","author":"R Barrett","year":"1994","unstructured":"Barrett, R., et al.: Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods, 2nd edn. SIAM, Philadelphia (1994)","edition":"2"},{"key":"16_CR4","doi-asserted-by":"publisher","unstructured":"Bell, N., Garland, M.: Implementing sparse matrix-vector multiplication on throughput-oriented processors. In: Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis, SC 2009, pp. 1\u201311. ACM, New York (2009). https:\/\/doi.org\/10.1145\/1654059.1654078","DOI":"10.1145\/1654059.1654078"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Dalton, S., Baxter, S., Merrill, D., Olson, L., Garland, M.: Optimizing sparse matrix operations on GPUs using merge path. In: 2015 IEEE International Parallel and Distributed Processing Symposium, pp. 407\u2013416, May 2015","DOI":"10.1109\/IPDPS.2015.98"},{"key":"16_CR6","doi-asserted-by":"publisher","unstructured":"Flegar, G., Anzt, H.: Overcoming load imbalance for irregular sparse matrices. In: Proceedings of the 7th Workshop on Irregular Applications: Architectures and Algorithms, IA3 2017, pp. 1\u20138. ACM, New York (2017). https:\/\/doi.org\/10.1145\/3149704.3149767","DOI":"10.1145\/3149704.3149767"},{"key":"16_CR7","unstructured":"Grossman, M., Thiele, C., Araya-Polo, M., Frank, F., Alpak, F.O., Sarkar, V.: A survey of sparse matrix-vector multiplication performance on large matrices. CoRR (2016). http:\/\/arxiv.org\/abs\/1608.00636"},{"key":"16_CR8","doi-asserted-by":"publisher","unstructured":"Higham, D., Higham, N.: Matlab Guide. Society for Industrial and Applied Mathematics (2005). https:\/\/doi.org\/10.1137\/1.9780898717891","DOI":"10.1137\/1.9780898717891"},{"key":"16_CR9","doi-asserted-by":"publisher","unstructured":"Hong, C., Sukumaran-Rajam, A., Nisa, I., Singh, K., Sadayappan, P.: Adaptive sparse tiling for sparse matrix multiplication. In: Proceedings of the 24th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2019, Washington, DC, USA, 16\u201320 February 2019, pp. 300\u2013314 (2019). https:\/\/doi.org\/10.1145\/3293883.3295712","DOI":"10.1145\/3293883.3295712"},{"key":"16_CR10","doi-asserted-by":"publisher","unstructured":"Hong, S., Kim, S.K., Oguntebi, T., Olukotun, K.: Accelerating CUDA graph algorithms at maximum warp. In: Proceedings of the 16th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPOPP 2011, San Antonio, TX, USA, 12\u201316 February 2011, pp. 267\u2013276 (2011). https:\/\/doi.org\/10.1145\/1941553.1941590","DOI":"10.1145\/1941553.1941590"},{"key":"16_CR11","volume-title":"Google\u2019s PageRank and Beyond: The Science of Search Engine Rankings","author":"AN Langville","year":"2012","unstructured":"Langville, A.N., Meyer, C.D.: Google\u2019s PageRank and Beyond: The Science of Search Engine Rankings. Princeton University Press, Princeton (2012)"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Merrill, D., Garland, M.: Merge-based parallel sparse matrix-vector multiplication. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2016, pp. 1\u201312. IEEE Press, Piscataway (2016). http:\/\/dl.acm.org\/citation.cfm?id=3014904.3014982","DOI":"10.1109\/SC.2016.57"},{"issue":"2","key":"16_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2717511","volume":"1","author":"D Merrill","year":"2015","unstructured":"Merrill, D., Garland, M., Grimshaw, A.S.: High-performance and scalable GPU graph traversal. ACM Trans. Parallel Comput. (TOPC) 1(2), 1\u201330 (2015). https:\/\/doi.org\/10.1145\/2717511","journal-title":"ACM Trans. Parallel Comput. (TOPC)"},{"key":"16_CR14","unstructured":"NVIDIA Corp.: Whitepaper: NVIDIA Tesla V100 GPU Architecture (2017)"},{"key":"16_CR15","unstructured":"SuiteSparse: Matrix Collection (2018). https:\/\/sparse.tamu.edu. Accessed Apr 2018"},{"key":"16_CR16","unstructured":"TechPowerUp: GPU database (2019). https:\/\/www.techpowerup.com\/gpu-specs\/"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-50743-5_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T15:03:52Z","timestamp":1702911832000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-50743-5_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030507428","9783030507435"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-50743-5_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"15 June 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISC High Performance","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on High Performance Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Frankfurt am Main","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"22 June 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 June 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"35","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"supercomputing2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.isc-hpc.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Linklings","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"87","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":"27","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":"3.73","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":"4.33","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}