{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T08:07:23Z","timestamp":1726042043504},"publisher-location":"Cham","reference-count":12,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030285951"},{"type":"electronic","value":"9783030285968"}],"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\/978-3-030-28596-8_18","type":"book-chapter","created":{"date-parts":[[2019,8,25]],"date-time":"2019-08-25T19:02:45Z","timestamp":1566759765000},"page":"262-273","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["OpenMP Task Generation for Batched Kernel APIs"],"prefix":"10.1007","author":[{"given":"Jinpil","family":"Lee","sequence":"first","affiliation":[]},{"given":"Yutaka","family":"Watanabe","sequence":"additional","affiliation":[]},{"given":"Mitsuhisa","family":"Sato","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,8,9]]},"reference":[{"key":"18_CR1","unstructured":"Argobots - Official Repository on Github. \n                      https:\/\/github.com\/pmodels\/argobots"},{"key":"18_CR2","unstructured":"Dongarra, J., et al.: Batched BLAS (basic linear algebra subprograms) 2018 specification, July 2018"},{"key":"18_CR3","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1016\/j.procs.2017.05.138","volume":"108","author":"Jack Dongarra","year":"2017","unstructured":"Dongarra, J., Hammarling, S., Higham, N.J., Relton, S.D., Valero-Lara, P., Zounon, M.: The design and performance of batched blas on modern high-performance computing systems. Procedia Comput. Sci. 108, 495\u2013504 (2017). \n                      https:\/\/doi.org\/10.1016\/j.procs.2017.05.138\n                      \n                    . \n                      http:\/\/www.sciencedirect.com\/science\/article\/pii\/S1877050917307056\n                      \n                    . International Conference on Computational Science, ICCS 2017, Zurich, Switzerland, 12\u201314 June 2017","journal-title":"Procedia Computer Science"},{"key":"18_CR4","unstructured":"Dongarra, J.J., et al.: A proposed API for batched basic linear algebra subprograms (2016)"},{"key":"18_CR5","unstructured":"Intel Math Kernel Library - Batched DGEMM Interface. \n                      https:\/\/software.intel.com\/en-us\/mkl-developer-reference-c-cblas-gemm-batch"},{"key":"18_CR6","doi-asserted-by":"publisher","unstructured":"Jin, C., Baskaran, M.: Analysis of explicit vs. implicit tasking in OpenMP using kripke, pp. 62\u201370, November 2018. \n                      https:\/\/doi.org\/10.1109\/ESPM2.2018.00012","DOI":"10.1109\/ESPM2.2018.00012"},{"key":"18_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1007\/978-3-642-40698-0_12","volume-title":"OpenMP in the Era of Low Power Devices and Accelerators","author":"A Muddukrishna","year":"2013","unstructured":"Muddukrishna, A., Jonsson, P.A., Vlassov, V., Brorsson, M.: Locality-aware task scheduling and data distribution on NUMA systems. In: Rendell, A.P., Chapman, B.M., M\u00fcller, M.S. (eds.) IWOMP 2013. LNCS, vol. 8122, pp. 156\u2013170. Springer, Heidelberg (2013). \n                      https:\/\/doi.org\/10.1007\/978-3-642-40698-0_12"},{"key":"18_CR8","unstructured":"NVIDIA cuBLAS - Batched DGEMM Interface. \n                      https:\/\/docs.nvidia.com\/cuda\/cublas\/index.html#cublas-lt-t-gt-gemmbatched"},{"key":"18_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/978-3-642-02303-3_6","volume-title":"Evolving OpenMP in an Age of Extreme Parallelism","author":"SL Olivier","year":"2009","unstructured":"Olivier, S.L., Prins, J.F.: Evaluating OpenMP 3.0 run time systems on unbalanced task graphs. In: M\u00fcller, M.S., de Supinski, B.R., Chapman, B.M. (eds.) IWOMP 2009. LNCS, vol. 5568, pp. 63\u201378. Springer, Heidelberg (2009). \n                      https:\/\/doi.org\/10.1007\/978-3-642-02303-3_6"},{"key":"18_CR10","unstructured":"Omni Compiler Infrastructure. \n                      https:\/\/omni-compiler.org\/"},{"key":"18_CR11","unstructured":"Relton, S.D., Valero-Lara, P., Zounon, M.: A comparison of potential interfaces for batched BLAS computations (2016)"},{"key":"18_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1007\/978-3-319-98521-3_7","volume-title":"Evolving OpenMP for Evolving Architectures","author":"Y Watanabe","year":"2018","unstructured":"Watanabe, Y., Lee, J., Boku, T., Sato, M.: Trade-off of offloading to FPGA in OpenMP task-based programming. In: de Supinski, B.R., Valero-Lara, P., Martorell, X., Mateo Bellido, S., Labarta, J. (eds.) IWOMP 2018. LNCS, vol. 11128, pp. 96\u2013110. Springer, Cham (2018). \n                      https:\/\/doi.org\/10.1007\/978-3-319-98521-3_7"}],"container-title":["Lecture Notes in Computer Science","OpenMP: Conquering the Full Hardware Spectrum"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-28596-8_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,25]],"date-time":"2019-08-25T19:35:02Z","timestamp":1566761702000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-28596-8_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030285951","9783030285968"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-28596-8_18","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":"9 August 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IWOMP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on OpenMP","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iwomp2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/parallel.auckland.ac.nz\/iwomp2019\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"23","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":"22","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":"96% - 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":"3.8","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":"0","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)"}}]}}