{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T07:12:13Z","timestamp":1742973133980,"version":"3.40.3"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030953874"},{"type":"electronic","value":"9783030953881"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-95388-1_12","type":"book-chapter","created":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T08:20:55Z","timestamp":1645518055000},"page":"178-192","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["HaDPA: A Data-Partition Algorithm for Data Parallel Applications on Heterogeneous HPC Platforms"],"prefix":"10.1007","author":[{"given":"Jingbo","family":"Li","sequence":"first","affiliation":[]},{"given":"Li","family":"Han","sequence":"additional","affiliation":[]},{"given":"Yuqi","family":"Qu","sequence":"additional","affiliation":[]},{"given":"Xingjun","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,2,23]]},"reference":[{"issue":"6","key":"12_CR1","doi-asserted-by":"publisher","first-page":"5960","DOI":"10.1007\/s11227-020-03506-5","volume":"77","author":"J Li","year":"2020","unstructured":"Li, J., Zhang, X., Han, L., Ji, Z., Dong, X., Hu, C.: OKCM: improving parallel task scheduling in high-performance computing systems using online learning. J. Supercomput. 77(6), 5960\u20135983 (2020). https:\/\/doi.org\/10.1007\/s11227-020-03506-5","journal-title":"J. Supercomput."},{"key":"12_CR2","unstructured":"Top500 (2020). https:\/\/www.top500.org\/lists\/top500\/2020\/11. Accessed 16 June 2021"},{"issue":"10","key":"12_CR3","doi-asserted-by":"publisher","first-page":"2176","DOI":"10.1109\/TPDS.2018.2827055","volume":"29","author":"H Khaleghzadeh","year":"2018","unstructured":"Khaleghzadeh, H., Manumachu, R.R., Lastovetsky, A.L.: A novel data-partitioning algorithm for performance optimization of data-parallel applications on heterogeneous HPC platforms. IEEE Trans. Parallel Distrib. Syst. 29(10), 2176\u20132190 (2018)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"1","key":"12_CR4","doi-asserted-by":"publisher","first-page":"72","DOI":"10.3390\/app10010072","volume":"10","author":"J Li","year":"2020","unstructured":"Li, J., Zhang, X., Zhou, J., Dong, X., Zhang, C.: swHPFM: refactoring and optimizing the structured grid fluid mechanical algorithm on the sunway taihulight supercomputer. Appl. Sci. 10(1), 72\u201393 (2020)","journal-title":"Appl. Sci."},{"issue":"2","key":"12_CR5","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s11227-009-0350-1","volume":"58","author":"JA Mart\u00ednez","year":"2011","unstructured":"Mart\u00ednez, J.A., Garz\u00f3n, E.M., Plaza, A., Garc\u00eda, I.: Automatic tuning of iterative computation on heterogeneous multiprocessors with ADITHE. J. Supercomput. 58(2), 151\u2013159 (2011)","journal-title":"J. Supercomput."},{"key":"12_CR6","unstructured":"Song, F., Tomov, S., Dongarra, J.J.: Enabling and scaling matrix computations on heterogeneous multi-core and multi-gpu systems. In: International Conference on Supercomputing, ICS 2012, Venice, Italy, June 25\u201329, 2012, pp. 365\u2013376. ACM (2012)"},{"issue":"4","key":"12_CR7","doi-asserted-by":"publisher","first-page":"1119","DOI":"10.1109\/TPDS.2016.2608824","volume":"28","author":"AL Lastovetsky","year":"2017","unstructured":"Lastovetsky, A.L., Manumachu, R.R.: New model-based methods and algorithms for performance and energy optimization of data parallel applications on homogeneous multicore clusters. IEEE Trans. Parallel Distrib. Syst. 28(4), 1119\u20131133 (2017)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"1","key":"12_CR8","doi-asserted-by":"publisher","first-page":"35","DOI":"10.3233\/FI-2021-2012","volume":"179","author":"S Marrakchi","year":"2021","unstructured":"Marrakchi, S., Jemni, M.: Static scheduling with load balancing for solving triangular band linear systems on multicore processors. Fundam. Informaticae 179(1), 35\u201358 (2021)","journal-title":"Fundam. Informaticae"},{"issue":"3","key":"12_CR9","doi-asserted-by":"publisher","first-page":"1321","DOI":"10.1007\/s11227-017-2176-6","volume":"74","author":"H Khaleghzadeh","year":"2017","unstructured":"Khaleghzadeh, H., Deldari, H., Reddy, R., Lastovetsky, A.: Hierarchical multicore thread mapping via estimation of remote communication. J. Supercomput. 74(3), 1321\u20131340 (2017). https:\/\/doi.org\/10.1007\/s11227-017-2176-6","journal-title":"J. Supercomput."},{"issue":"2","key":"12_CR10","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1109\/TPDS.2020.3025102","volume":"32","author":"A Giordano","year":"2021","unstructured":"Giordano, A., Rango, A.D., Rongo, R., D\u2019Ambrosio, D., Spataro, W.: Dynamic load balancing in parallel execution of cellular automata. IEEE Trans. Parallel Distributed Syst. 32(2), 470\u2013484 (2021)","journal-title":"IEEE Trans. Parallel Distributed Syst."},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Li, M., Chen, C., Zhu, G., Savaria, Y.: Local queueing-based data-driven task scheduling for multicore systems. In: IEEE 61st International Midwest Symposium on Circuits and Systems, MWSCAS 2018, Windsor, ON, Canada, 5\u20138 August, 2018, pp. 897\u2013900. IEEE (2018)","DOI":"10.1109\/MWSCAS.2018.8623930"},{"issue":"1","key":"12_CR12","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1177\/1094342006074864","volume":"21","author":"AL Lastovetsky","year":"2007","unstructured":"Lastovetsky, A.L., Reddy, R.: Data partitioning with a functional performance model of heterogeneous processors. Int. J. High Perform. Comput. Appl. 21(1), 76\u201390 (2007)","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Culler, D.E., Karp, R.M., Patterson, D.A., and A.S.: Logp: Towards a realistic model of parallel computation. In: Proceedings of the Fourth ACM SIGPLAN Symposium on Principles & Practice of Parallel Programming (PPOPP), San Diego, California, USA, 19\u201322 May, 1993, pp. 1\u201312. ACM (1993)","DOI":"10.1145\/155332.155333"},{"issue":"1","key":"12_CR14","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1006\/jpdc.1997.1346","volume":"44","author":"AD Alexandrov","year":"1997","unstructured":"Alexandrov, A.D., Ionescu, M.F., Schauser, K.E., Scheiman, C.J.: Loggp: incorporating long messages into the logp model for parallel computation. J. Parallel Distributed Comput. 44(1), 71\u201379 (1997)","journal-title":"J. Parallel Distributed Comput."},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Yuan, L., Zhang, Y., Tang, Y., Rao, L., Sun, X.: Loggph: a parallel computational model with hierarchical communication awareness. In: 13th IEEE International Conference on Computational Science and Engineering, CSE 2010, Hong Kong, China, 11\u201313 December, 2010. pp. 268\u2013274. IEEE Computer Society (2010)","DOI":"10.1109\/CSE.2010.40"},{"issue":"10","key":"12_CR16","doi-asserted-by":"publisher","first-page":"1785","DOI":"10.1007\/s11432-009-0161-2","volume":"52","author":"W Chen","year":"2009","unstructured":"Chen, W., Zhai, J., Zhang, J., Zheng, W.: Loggpo: an accurate communication model for performance prediction of MPI programs. Sci. China Ser. F Inf. Sci. 52(10), 1785\u20131791 (2009)","journal-title":"Sci. China Ser. F Inf. Sci."},{"issue":"3","key":"12_CR17","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1109\/TC.2007.38","volume":"56","author":"KW Cameron","year":"2007","unstructured":"Cameron, K.W., Ge, R., Sun, X.: log$$_{\\text{ n }}{\\rm p}$$ and log$$_{\\text{3 }}{\\rm p}$$: accurate analytical models of point-to-point communication in distributed systems. IEEE Trans. Comput. 56(3), 314\u2013327 (2007)","journal-title":"IEEE Trans. Comput."},{"issue":"1","key":"12_CR18","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1007\/s11227-009-0296-3","volume":"60","author":"B Tu","year":"2012","unstructured":"Tu, B., Fan, J., Zhan, J., Zhao, X.: Performance analysis and optimization of MPI collective operations on multi-core clusters. J. Supercomput. 60(1), 141\u2013162 (2012)","journal-title":"J. Supercomput."},{"key":"12_CR19","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.parco.2015.02.006","volume":"46","author":"J Rico-Gallego","year":"2015","unstructured":"Rico-Gallego, J., Mart\u00edn, J.C.D.: $$\\tau $$-lop: modeling performance of shared memory MPI. Parallel Comput. 46, 14\u201331 (2015)","journal-title":"Parallel Comput."},{"key":"12_CR20","unstructured":"Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems 30, pp. 4765\u20134774. Curran Associates, Inc. (2017)"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-95388-1_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T08:29:14Z","timestamp":1645518554000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-95388-1_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030953874","9783030953881"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-95388-1_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"23 February 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2021","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":"ica3pp2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/nsclab.org\/ica3pp2021\/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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"403","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":"145","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":"36% - 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":"3.12","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":"2.27","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)"}}]}}