{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T03:59:35Z","timestamp":1781668775522,"version":"3.54.5"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031971952","type":"print"},{"value":"9783031971969","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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":[[2026]]},"DOI":"10.1007\/978-3-031-97196-9_10","type":"book-chapter","created":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T22:25:26Z","timestamp":1759271126000},"page":"120-132","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Scalable Block-Sparse Matrix Multiplication Using Template Task Graphs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2041-7877","authenticated-orcid":false,"given":"Joseph","family":"Schuchart","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5108-509X","authenticated-orcid":false,"given":"Aurelien","family":"Bouteiller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6756-6189","authenticated-orcid":false,"given":"Thomas","family":"Herault","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9923-6256","authenticated-orcid":false,"given":"Edvard","family":"Valeev","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2411-8495","authenticated-orcid":false,"given":"George","family":"Bosilca","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8777-7466","authenticated-orcid":false,"given":"Robert J.","family":"Harrison","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,1]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Augonnet, C., Thibault, S., Namyst, R., Wacrenier, P.: StarPU: a unified platform for task scheduling on heterogeneous multicore architectures. Conc. Comp. Pract. Exper. 23 (2011)","DOI":"10.1002\/cpe.1631"},{"issue":"3","key":"10_CR2","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1109\/TPDS.2008.105","volume":"20","author":"E Ayguad\u00e9","year":"2008","unstructured":"Ayguad\u00e9, E., et al.: The design of OpenMP tasks. IEEE Trans. Parallel Distrib. Syst. 20(3), 404\u2013418 (2008)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"10_CR3","doi-asserted-by":"publisher","unstructured":"Bauer, M., Treichler, S., Slaughter, E., Aiken, A.: Legion: expressing locality and independence with logical regions. In: SC 2012: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (2012). https:\/\/doi.org\/10.1109\/SC.2012.71","DOI":"10.1109\/SC.2012.71"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Bor\u0161tnik, U., VandeVondele, J., Weber, V., Hutter, J.: Sparse matrix multiplication: The distributed block-compressed sparse row library. Parallel Comput. 40(5), 47\u201358 (2014). 10.1016\/j.parco.2014.03.012, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0167819114000428","DOI":"10.1016\/j.parco.2014.03.012"},{"key":"10_CR5","doi-asserted-by":"publisher","unstructured":"Bueno, J., et al.: Productive programming of GPU clusters with OmpSs. Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium, IPDPS 2012, pp. 557\u2013568 (2012).https:\/\/doi.org\/10.1109\/IPDPS.2012.58","DOI":"10.1109\/IPDPS.2012.58"},{"key":"10_CR6","unstructured":"Calvin, J.A., Valeev, E.F.: TiledArray: A general-purpose scalable block-sparse tensor framework. https:\/\/github.com\/valeevgroup\/tiledarray"},{"key":"10_CR7","doi-asserted-by":"publisher","unstructured":"Danalis, A., Bosilca, G., Bouteiller, A., Herault, T., Dongarra, J.: PTG: an abstraction for unhindered parallelism. In: Proceedings of WOLFHPC 2014 (2014). https:\/\/doi.org\/10.1109\/WOLFHPC.2014.8","DOI":"10.1109\/WOLFHPC.2014.8"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Gursoy, A., Kale, L.V.: Dagger: combining benefits of synchronous and asynchronous communication styles. In: Proceedings of 8th International Parallel Processing Symposium, pp. 590\u2013596. IEEE (1994)","DOI":"10.1109\/IPPS.1994.288244"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Harrison, R.J., et alY.: MADNESS: A multiresolution, adaptive numerical environment for scientific simulation. SIAM J. Sci. Comput. 38(5) (2016)","DOI":"10.1137\/15M1026171"},{"key":"10_CR10","doi-asserted-by":"publisher","unstructured":"Herault, T., et al.: Distributed-memory multi-GPU block-sparse tensor contraction for electronic structure. In: 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 537\u2013546 (2021).https:\/\/doi.org\/10.1109\/IPDPS49936.2021.00062","DOI":"10.1109\/IPDPS49936.2021.00062"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Hoque, R., Herault, T., Bosilca, G., Dongarra, J.: Dynamic task discovery in PaRSEC: a data-flow task-based runtime. In: Proceedings of the 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems, pp.\u00a01\u20138 (2017)","DOI":"10.1145\/3148226.3148233"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Kaiser, H., Heller, T., Adelstein-Lelbach, B., Serio, A., Fey, D.: Hpx: a task based programming model in a global address space. In: Proceedings of the 8th International Conference on Partitioned Global Address Space Programming Models, pp. 1\u201311 (2014)","DOI":"10.1145\/2676870.2676883"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Kale, L.V., Krishnan, S.: CHARM++: a portable concurrent object oriented system based on C++. In: Proceedings of the Conference on Object Oriented Programming Systems, Languages and Applications (1993)","DOI":"10.1145\/165854.165874"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Kukanov, A., Voss, M.J.: The foundations for scalable multi-core software in intel threading building blocks. Intel Technol. J. 11(4) (2007)","DOI":"10.1535\/itj.1104.05"},{"key":"10_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1007\/11818502_4","volume-title":"Advanced Topics in Exception Handling Techniques","author":"M Rintala","year":"2006","unstructured":"Rintala, M.: Handling multiple concurrent exceptions in C++ using futures. In: Dony, C., Knudsen, J.L., Romanovsky, A., Tripathi, A. (eds.) Advanced Topics in Exception Handling Techniques. LNCS, vol. 4119, pp. 62\u201380. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11818502_4"},{"key":"10_CR16","doi-asserted-by":"publisher","unstructured":"Schuchart, J., Nookala, P., Javanmard, M.M., Herault, T., Valeev, E.F., Bosilca, G., Harrison, R.J.: Generalized flow-graph programming using template task-graphs: initial implementation and assessment. In: 2022 IEEE International Parallel and Distributed Processing Symposium (IPDPS) (2022).https:\/\/doi.org\/10.1109\/IPDPS53621.2022.00086","DOI":"10.1109\/IPDPS53621.2022.00086"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Van De\u00a0Geijn, R.A., Watts, J.: Summa: scalable universal matrix multiplication algorithm. Concurrency: Pract. Exper. 9(4), 255\u2013274 (1997)","DOI":"10.1002\/(SICI)1096-9128(199704)9:4<255::AID-CPE250>3.0.CO;2-2"},{"key":"10_CR18","doi-asserted-by":"publisher","unstructured":"Zheng, Y., Kamil, A., Driscoll, M.B., Shan, H., Yelick, K.: UPC++: a PGAS Extension for C++. In: 2014 IEEE 28th International Parallel and Distributed Processing Symposium, pp. 1105\u20131114 (2014). https:\/\/doi.org\/10.1109\/IPDPS.2014.115","DOI":"10.1109\/IPDPS.2014.115"},{"key":"10_CR19","doi-asserted-by":"publisher","unstructured":"Zheng, Z., Chen, J., Zhao, Y., Song, L., Qin, X., An, H.: DB-SpGEMM: a massively distributed block-sparse matrix-matrix multiplication for linear-scaling DFT calculations. In: Proceedings of the 53rd International Conference on Parallel Processing,ICPP 2024. pp. 1156\u20131165. Association for Computing Machinery, New York (2024). https:\/\/doi.org\/10.1145\/3673038.3673159","DOI":"10.1145\/3673038.3673159"}],"container-title":["Lecture Notes in Computer Science","Asynchronous Many-Task Systems and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-97196-9_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T03:41:14Z","timestamp":1781667674000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-97196-9_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,1]]},"ISBN":["9783031971952","9783031971969"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-97196-9_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,1]]},"assertion":[{"value":"1 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"WAMTA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Workshop on Asynchronous Many-Task Systems and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"St. Louis, MO","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 February 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 February 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"wamta2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/wamta25.github.io\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}