{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T09:49:01Z","timestamp":1766137741368,"version":"3.40.3"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030787127"},{"type":"electronic","value":"9783030787134"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-78713-4_12","type":"book-chapter","created":{"date-parts":[[2021,6,16]],"date-time":"2021-06-16T23:06:15Z","timestamp":1623884775000},"page":"217-236","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["COSTA: Communication-Optimal Shuffle and Transpose Algorithm with Process Relabeling"],"prefix":"10.1007","author":[{"given":"Marko","family":"Kabi\u0107","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"Pintarelli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anton","family":"Kozhevnikov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joost","family":"VandeVondele","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,6,17]]},"reference":[{"issue":"4","key":"12_CR1","doi-asserted-by":"publisher","first-page":"C143","DOI":"10.1137\/18M1189348","volume":"42","author":"A Azad","year":"2020","unstructured":"Azad, A., Bulu\u00e7, A., Li, X.S., Wang, X., Langguth, J.: A distributed-memory algorithm for computing a heavy-weight perfect matching on bipartite graphs. SIAM J. Sci. Comput. 42(4), C143\u2013C168 (2020)","journal-title":"SIAM J. Sci. Comput."},{"key":"12_CR2","first-page":"147","volume":"5","author":"G Birkhoff","year":"1946","unstructured":"Birkhoff, G.: Tres observaciones sabre el algebra lineal. Univ. Nac. Tucum\u00e1n Rev. Ser. A 5, 147\u2013151 (1946)","journal-title":"Univ. Nac. Tucum\u00e1n Rev. Ser. A"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Burkard, R., Dell\u2019Amico, M., Martello, S.: Assignment Problems: Revised Reprint. SIAM (2012)","DOI":"10.1137\/1.9781611972238"},{"key":"12_CR4","unstructured":"Choi, J., Dongarra, J.J., Pozo, R., Walker, D.W.: Scalapack: a scalable linear algebra library for distributed memory concurrent computers. In: The Fourth Symposium on the Frontiers of Massively Parallel Computation, pp. 120\u2013121. IEEE Computer Society (1992)"},{"key":"12_CR5","doi-asserted-by":"publisher","unstructured":"Date, K., Nagi, R.: GPU-accelerated Hungarian algorithms for the linear assignment problem. Parallel Comput. 57, 52\u201372 (2016). https:\/\/doi.org\/10.1016\/j.parco.2016.05.012, http:\/\/www.sciencedirect.com\/science\/article\/pii\/S016781911630045X","DOI":"10.1016\/j.parco.2016.05.012"},{"key":"12_CR6","doi-asserted-by":"publisher","unstructured":"Del Ben, M., Sch\u00fctt, O., Wentz, T., Messmer, P., Hutter, J., VandeVondele, J.: Enabling simulation at the fifth rung of DFT: large scale RPA calculations with excellent time to solution. Comput. Phys. Commun. 187, 120\u2013129 (2015). https:\/\/doi.org\/10.1016\/j.cpc.2014.10.021, http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0010465514003671","DOI":"10.1016\/j.cpc.2014.10.021"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Demmel, J., et al.: Communication-optimal parallel recursive rectangular matrix multiplication. In: 2013 IEEE 27th International Symposium on Parallel and Distributed Processing, pp. 261\u2013272. IEEE (2013)","DOI":"10.1109\/IPDPS.2013.80"},{"issue":"2","key":"12_CR8","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1137\/1037042","volume":"37","author":"JJ Dongarra","year":"1995","unstructured":"Dongarra, J.J., Walker, D.W.: Software libraries for linear algebra computations on high performance computers. SIAM Rev. 37(2), 151\u2013180 (1995). https:\/\/doi.org\/10.1137\/1037042","journal-title":"SIAM Rev."},{"key":"12_CR9","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4613-0303-9","volume-title":"Handbook of Combinatorial Optimization","author":"D Du","year":"1998","unstructured":"Du, D., Pardalos, P.M.: Handbook of Combinatorial Optimization, vol. 4. Springer Science & Business Media, Boston (1998). https:\/\/doi.org\/10.1007\/978-1-4613-0303-9"},{"key":"12_CR10","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.parco.2015.09.005","volume":"52","author":"J Herrmann","year":"2016","unstructured":"Herrmann, J., Bosilca, G., H\u00e9rault, T., Marchal, L., Robert, Y., Dongarra, J.: Assessing the cost of redistribution followed by a computational kernel: complexity and performance results. Parallel Comput. 52, 22\u201341 (2016)","journal-title":"Parallel Comput."},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Kabic, M., Pintarelli, S., Kozhevnikov, A., VandeVondele, J.: COSTA: communication-optimal shuffle and transpose algorithm (2020). https:\/\/github.com\/eth-cscs\/COSTA","DOI":"10.1007\/978-3-030-78713-4_12"},{"key":"12_CR12","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/978-0-387-09766-4_189","volume-title":"Encyclopedia of Parallel Computing","author":"T Kielmann","year":"2011","unstructured":"Kielmann, T., Gorlatch, S.: Bandwidth-Latency models (BSP, LogP). In: Paduda, D. (ed.) Encyclopedia of Parallel Computing, pp. 107\u2013112. Springer, Boston (2011). https:\/\/doi.org\/10.1007\/978-0-387-09766-4_189"},{"key":"12_CR13","unstructured":"Kozhevnikov, A., Schulthess, T.: Sirius library for electronic structure (2013). https:\/\/github.com\/electronic-structure\/SIRIUS"},{"issue":"1\u20132","key":"12_CR14","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Logistics Q. 2(1\u20132), 83\u201397 (1955)","journal-title":"Naval Res. Logistics Q."},{"issue":"19","key":"12_CR15","doi-asserted-by":"publisher","first-page":"194103","DOI":"10.1063\/5.0007045","volume":"152","author":"TD K\u00fchne","year":"2020","unstructured":"K\u00fchne, T.D., et al.: Cp2k: an electronic structure and molecular dynamics software package-quickstep: efficient and accurate electronic structure calculations. J. Chem. Phys. 152(19), 194103 (2020)","journal-title":"J. Chem. Phys."},{"key":"12_CR16","doi-asserted-by":"publisher","unstructured":"Kwasniewski, G., Kabi\u0107, M., Besta, M., VandeVondele, J., Solc\u00e0, R., Hoefler, T.: Red-blue pebbling revisited: near optimal parallel matrix-matrix multiplication. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, New York. SC 2019. Association for Computing Machinery (2019). https:\/\/doi.org\/10.1145\/3295500.3356181","DOI":"10.1145\/3295500.3356181"},{"key":"12_CR17","doi-asserted-by":"publisher","unstructured":"Lopes, P.A., Yadav, S.S., Ilic, A., Patra, S.K.: Fast block distributed CUDA implementation of the Hungarian algorithm. J. Parallel Distrib. Comput. 130, 50\u201362 (2019). https:\/\/doi.org\/10.1016\/j.jpdc.2019.03.014, http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0743731519302254","DOI":"10.1016\/j.jpdc.2019.03.014"},{"issue":"1","key":"12_CR18","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1137\/0105003","volume":"5","author":"J Munkres","year":"1957","unstructured":"Munkres, J.: Algorithms for the assignment and transportation problems. J. Soc. Ind. Appl. Math. 5(1), 32\u201338 (1957)","journal-title":"J. Soc. Ind. Appl. Math."},{"key":"12_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/3-540-61626-8_20","volume-title":"Euro-Par 1996 Parallel Processing","author":"L Prylli","year":"1996","unstructured":"Prylli, L., Tourancheau, B.: Efficient block cyclic data redistribution. In: Boug\u00e9, L., Fraigniaud, P., Mignotte, A., Robert, Y. (eds.) Euro-Par 1996. LNCS, vol. 1123, pp. 155\u2013164. Springer, Heidelberg (1996). https:\/\/doi.org\/10.1007\/3-540-61626-8_20"},{"key":"12_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1007\/11427186_41","volume-title":"Experimental and Efficient Algorithms","author":"J Schwartz","year":"2005","unstructured":"Schwartz, J., Steger, A., Wei\u00dfl, A.: Fast algorithms for weighted bipartite matching. In: Nikoletseas, S.E. (ed.) WEA 2005. LNCS, vol. 3503, pp. 476\u2013487. Springer, Heidelberg (2005). https:\/\/doi.org\/10.1007\/11427186_41"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-78713-4_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,29]],"date-time":"2023-03-29T07:06:21Z","timestamp":1680073581000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-78713-4_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030787127","9783030787134"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-78713-4_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"17 June 2021","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":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 June 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 July 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"36","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"supercomputing2021","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":"74","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":"24","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":"32% - 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":"4.28","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":"4.13","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":"In the ISC High Performance Workshop, there were 49 submissions, out of which 35  were accepted.","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)"}}]}}