{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T10:48:57Z","timestamp":1753181337280,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030581435"},{"type":"electronic","value":"9783030581442"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58144-2_19","type":"book-chapter","created":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T12:03:48Z","timestamp":1598961828000},"page":"295-309","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Toward Supporting Multi-GPU Targets via Taskloop and User-Defined Schedules"],"prefix":"10.1007","author":[{"given":"Vivek","family":"Kale","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbin","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anthony","family":"Curtis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abid M.","family":"Malik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Barbara","family":"Chapman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oscar","family":"Hernandez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,9,1]]},"reference":[{"key":"19_CR1","unstructured":"OpenMP 5.0 Reference Guide. https:\/\/www.openmp.org\/wp-content\/uploads\/OpenMPRef-5.0-1119-01-TSK-web.pdf"},{"key":"19_CR2","unstructured":"OpenMP Verification and Validation Suite. https:\/\/github.com\/SOLLVE\/sollve_vv"},{"key":"19_CR3","unstructured":"Parallel Computational Pattern: Monte Carle Methods. https:\/\/patterns.eecs.berkeley.edu\/?page_id=186"},{"key":"19_CR4","unstructured":"Perlmutter User Guide. https:\/\/www.nersc.gov\/systems\/perlmutter\/"},{"key":"19_CR5","unstructured":"Summit User Guide. https:\/\/docs.olcf.ornl.gov\/systems\/summit_user_guide.html"},{"key":"19_CR6","unstructured":"The LLVM Compiler Infrastructure. http:\/\/llvm.org\/"},{"key":"19_CR7","unstructured":"Optimizing MPI Communication on Multi-GPU Systems Using CUDA Inter-Process Communication (2012)"},{"key":"19_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/978-3-319-69953-0_7","volume-title":"Supercomputing Frontiers","author":"K Matsumura","year":"2018","unstructured":"Matsumura, K., Sato, M., Boku, T., Podobas, A., Matsuoka, S.: MACC: an OpenACC transpiler for automatic multi-GPU use. In: Yokota, R., Wu, W. (eds.) SCFA 2018. LNCS, vol. 10776, pp. 109\u2013127. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-69953-0_7"},{"key":"19_CR9","unstructured":"Beyer, J., de Supinski, B.R.: IWOMP 2016 tutorial: OpenMP accelerator model (2016). http:\/\/iwomp2016.riken.jp\/wp-content\/uploads\/2016\/10\/tutorial-accelerator.pdf"},{"issue":"1","key":"19_CR10","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1006\/jpdc.1996.0107","volume":"37","author":"RD Blumofe","year":"1995","unstructured":"Blumofe, R.D., Joerg, C.F., Kuszmaul, B.C., Leiserson, C.E., Randall, K.H., Zhou, Y.: Cilk: an efficient multithreaded runtime system. J. Parallel Distrib. Comput. 37(1), 55\u201369 (1995)","journal-title":"J. Parallel Distrib. Comput."},{"key":"19_CR11","unstructured":"Bull, J.M.: Measuring synchronisation and scheduling overheads in OpenMP. In: Proceedings of First European Workshop on OpenMP, pp. 99\u2013105, Lund, Sweden (1999)"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Ciorba, F.M., Iwainsky, C., Buder, P.: OpenMP loop scheduling revisited: making a case for more schedules. ArXiv arxiv:1809.03188 (2018)","DOI":"10.1007\/978-3-319-98521-3_2"},{"key":"19_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1007\/978-3-030-28596-8_20","volume-title":"OpenMP: Conquering the Full Hardware Spectrum","author":"J Criado","year":"2019","unstructured":"Criado, J., et al.: Optimization of condensed matter physics application with OpenMP tasking model. In: Fan, X., de Supinski, B.R., Sinnen, O., Giacaman, N. (eds.) IWOMP 2019. LNCS, vol. 11718, pp. 291\u2013305. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-28596-8_20"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Donfack, S., Grigori, L., Gropp, W.D., Kale, V.: Hybrid static\/dynamic scheduling for already optimized dense matrix factorization. In: 2012 IEEE 26th International Parallel and Distributed Processing Symposium, pp. 496\u2013507 (2012)","DOI":"10.1109\/IPDPS.2012.53"},{"key":"19_CR15","doi-asserted-by":"publisher","first-page":"1145","DOI":"10.1002\/jcc.20634","volume":"28","author":"R Huey","year":"2007","unstructured":"Huey, R., Morris, G.M., Olson, A.J., Goodsell, D.S.: A semiempirical free energy force field with charge-based desolvation. J. Comput. Chem. 28, 1145\u20131152 (2007)","journal-title":"J. Comput. Chem."},{"issue":"7","key":"19_CR16","doi-asserted-by":"publisher","first-page":"3607","DOI":"10.1109\/TAP.2013.2258882","volume":"61","author":"J Guan","year":"2013","unstructured":"Guan, J., Yan, S., Jin, J.M.: An OpenMP-CUDA implementation of multilevel fast multipole algorithm for electromagnetic simulation on multi-GPU computing systems. IEEE Trans. Antennas Propag. 61(7), 3607\u20133616 (2013)","journal-title":"IEEE Trans. Antennas Propag."},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Kal\u00e9, L., Krishnan, S.: CHARM++: a portable concurrent object oriented system based on C++. In: Paepcke, A. (ed.) Proceedings of OOPSLA 1993, pp. 91\u2013108. ACM Press (September 1993)","DOI":"10.1145\/167962.165874"},{"key":"19_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1007\/978-3-030-28596-8_13","volume-title":"OpenMP: Conquering the Full Hardware Spectrum","author":"V Kale","year":"2019","unstructured":"Kale, V., Iwainsky, C., Klemm, M., M\u00fcller Kornd\u00f6rfer, J.H., Ciorba, F.M.: Toward a standard interface for user-defined scheduling in OpenMP. In: Fan, X., de Supinski, B.R., Sinnen, O., Giacaman, N. (eds.) IWOMP 2019. LNCS, vol. 11718, pp. 186\u2013200. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-28596-8_13"},{"issue":"19","key":"19_CR19","doi-asserted-by":"publisher","first-page":"195901","DOI":"10.1088\/1361-648x\/aab9c3","volume":"30","author":"J Kim","year":"2018","unstructured":"Kim, J., et al.: QMCPACK: an open source ab initio quantum Monte Carlo package for the electronic structure of atoms, molecules and solids. J. Phys.: Condens. Matter 30(19), 195901 (2018). https:\/\/doi.org\/10.1088\/1361-648x\/aab9c3","journal-title":"J. Phys.: Condens. Matter"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Komoda, T., Miwa, S., Nakamura, H., Maruyama, N.: Integrating multi-GPU execution in an OpenACC compiler. In: 2013 42nd International Conference on Parallel Processing, pp. 260\u2013269 (2013)","DOI":"10.1109\/ICPP.2013.35"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Leopold Grinberg, C.B., Haque, R.: Hands on with openmp4.5 and unified memory: developing applications for IBM\u2019s hybrid CPU + GPU systems (Part ii) (2017)","DOI":"10.1007\/978-3-319-65578-9_2"},{"issue":"16","key":"19_CR22","doi-asserted-by":"publisher","first-page":"2785","DOI":"10.1002\/jcc.21256","volume":"30","author":"GM Morris","year":"2009","unstructured":"Morris, G.M., et al.: Autodock4 and AutoDockTools4: automated docking with selective receptor flexibility. J. Comput. Chem. 30(16), 2785\u20132791 (2009)","journal-title":"J. Comput. Chem."},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Nakao, M., Murai, H., Iwashita, H., Tabuchi, A., Boku, T., Sato, M.: Implementing lattice QCD application with XcalableACC language on accelerated cluster, pp. 429\u2013438 (2017)","DOI":"10.1109\/CLUSTER.2017.58"},{"issue":"2","key":"19_CR24","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1002\/jcc.21334","volume":"31","author":"O Trott","year":"2010","unstructured":"Trott, O., Olson, A.J.: AutoDock Vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization and multithreading. J. Comput. Chem. 31(2), 455\u2013461 (2010)","journal-title":"J. Comput. Chem."},{"key":"19_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1007\/978-3-319-07518-1_11","volume-title":"Supercomputing","author":"TRW Scogland","year":"2014","unstructured":"Scogland, T.R.W., Feng, W., Rountree, B., de Supinski, B.R.: CoreTSAR: adaptive worksharing for heterogeneous systems. In: Kunkel, J.M., Ludwig, T., Meuer, H.W. (eds.) ISC 2014. LNCS, vol. 8488, pp. 172\u2013186. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-07518-1_11"},{"issue":"2","key":"19_CR26","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1006\/jcis.1998.6036","volume":"213","author":"P Tandon","year":"1999","unstructured":"Tandon, P., Rosner, D.E.: Monte Carlo simulation of particle aggregation and simultaneous restructuring. J. Colloid Interface Sci. 213(2), 273\u2013286 (1999)","journal-title":"J. Colloid Interface Sci."},{"key":"19_CR27","unstructured":"Wolfe, M.: Scaling OpenACC applications across multiple GPUs (2014)"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Xu, R., Tian, X., Chandrasekaran, S., Chapman, B.: Multi-GPU support on single node using directive-based programming models (January 2016)","DOI":"10.1155\/2015\/621730"}],"container-title":["Lecture Notes in Computer Science","OpenMP: Portable Multi-Level Parallelism on Modern Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58144-2_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T23:54:00Z","timestamp":1723506840000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58144-2_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030581435","9783030581442"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58144-2_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"1 September 2020","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":"Austin, TX","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":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iwomp2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.iwomp.org\/","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":"25","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":"21","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":"84% - 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":"4","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":"5","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)"}},{"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)"}}]}}