{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T03:36:36Z","timestamp":1769225796862,"version":"3.49.0"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T00:00:00Z","timestamp":1769040000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T00:00:00Z","timestamp":1769040000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1931384"],"award-info":[{"award-number":["1931384"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1931387"],"award-info":[{"award-number":["1931387"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1931347"],"award-info":[{"award-number":["1931347"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1927880"],"award-info":[{"award-number":["1927880"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-026-04729-8","type":"journal-article","created":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T16:23:11Z","timestamp":1769098991000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Constraints and Mutexflows for Scalable Block-Sparse Matrix Multiplication Using Template Task Graphs"],"prefix":"10.1007","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2041-7877","authenticated-orcid":false,"given":"Joseph","family":"Schuchart","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aurelien","family":"Bouteiller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Herault","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edvard","family":"Valeev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George","family":"Bosilca","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert J.","family":"Harrison","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,22]]},"reference":[{"issue":"5","key":"4729_CR1","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.parco.2014.03.012","volume":"40","author":"U Bor\u0161tnik","year":"2014","unstructured":"Bor\u0161tnik U, VandeVondele J, Weber V, Hutter J. Sparse matrix multiplication: the distributed block-compressed sparse row library. Parallel Comput. 2014;40(5):47\u201358. https:\/\/doi.org\/10.1016\/j.parco.2014.03.012.","journal-title":"Parallel Comput"},{"key":"4729_CR2","unstructured":"Calvin JA, Valeev EF. TiledArray: A general-purpose scalable block-sparse tensor framework. https:\/\/github.com\/valeevgroup\/tiledarray."},{"key":"4729_CR3","doi-asserted-by":"publisher","unstructured":"Schuchart J, Nookala P, Javanmard MM, Herault T, Valeev EF, Bosilca G, Harrison RJ. 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":"4729_CR4","doi-asserted-by":"crossref","unstructured":"Schuchart J, Bouteiller A, Herault T, Valeev E, Bosilca G, Harrison RJ. Scalable block-sparse matrix multiplication using template task graphs 2025.","DOI":"10.1007\/978-3-031-97196-9_10"},{"issue":"3","key":"4729_CR5","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, Copty N, Duran A, Hoeflinger J, Lin Y, Massaioli F, et al. The design of OpenMP tasks. IEEE Trans Parallel Distrib Syst. 2008;20(3):404\u201318.","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"4729_CR6","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. 2011;23.","DOI":"10.1002\/cpe.1631"},{"key":"4729_CR7","doi-asserted-by":"publisher","unstructured":"Bueno J, Planas J, Duran A, Badia RM, Martorell X, Ayguad\u00e9 E, Labarta J. Productive programming of GPU clusters with OmpSs. Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium, IPDPS 2012, 2012;557\u2013568 https:\/\/doi.org\/10.1109\/IPDPS.2012.58.","DOI":"10.1109\/IPDPS.2012.58"},{"key":"4729_CR8","doi-asserted-by":"publisher","unstructured":"Bauer M, Treichler S, Slaughter E, Aiken A. Legion: Expressing locality and independence with logical regions. In: SC \u201912: 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":"4729_CR9","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, 2017;1\u20138.","DOI":"10.1145\/3148226.3148233"},{"key":"4729_CR10","doi-asserted-by":"publisher","unstructured":"Bauer M, Lee W, Slaughter E, Jia Z, Di\u00a0Renzo M, Papadakis M, Shipman G, McCormick P, Garland M, Aiken A. Scaling implicit parallelism via dynamic control replication. In: Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming. PPoPP \u201921. Association for Computing Machinery, New York, NY, USA 2021. https:\/\/doi.org\/10.1145\/3437801.3441587 .","DOI":"10.1145\/3437801.3441587"},{"key":"4729_CR11","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, 2014;1\u201311 .","DOI":"10.1145\/2676870.2676883"},{"key":"4729_CR12","doi-asserted-by":"crossref","unstructured":"Harrison RJ, Beylkin G, Bischoff FA, Calvin JA, Fann GI, Fosso-Tande J, Galindo D, Hammond JR, Hartman-Baker R, Hill JC, Jia J, Kottmann JS, Ou M-Y, Ratcliff LE, Reuter MG, Richie-Halford AC, Romero NA, Sekino H, Shelton WA, Sundahl BE, Thornton WS, Valeev EF, V\u00e1zquez-Mayagoitia \u00c1, Vence N, Yokoi Y. MADNESS: A multiresolution, adaptive numerical environment for scientific simulation. SIAM J. Sci. Comput. 2016;38(5).","DOI":"10.1137\/15M1026171"},{"key":"4729_CR13","doi-asserted-by":"crossref","unstructured":"Kale LV, 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":"4729_CR14","doi-asserted-by":"publisher","unstructured":"Zheng Y, Kamil A, Driscoll MB, Shan H, Yelick K. UPC++: A PGAS Extension for C++. In: 2014 IEEE 28th International Parallel and Distributed Processing Symposium, 2014;1105\u20131114. https:\/\/doi.org\/10.1109\/IPDPS.2014.115.","DOI":"10.1109\/IPDPS.2014.115"},{"key":"4729_CR15","doi-asserted-by":"publisher","unstructured":"Danalis A, Bosilca G, Bouteiller A, Herault T, Dongarra J. PTG: An abstraction for unhindered parallelism. Proceedings of WOLFHPC\u201914 2014 https:\/\/doi.org\/10.1109\/WOLFHPC.2014.8.","DOI":"10.1109\/WOLFHPC.2014.8"},{"key":"4729_CR16","doi-asserted-by":"crossref","unstructured":"Gursoy A, Kale LV. Dagger: combining benefits of synchronous and asynchronous communication styles. In: Proceedings of 8th International Parallel Processing Symposium, 1994;590\u2013596 . IEEE","DOI":"10.1109\/IPPS.1994.288244"},{"key":"4729_CR17","doi-asserted-by":"crossref","unstructured":"Kukanov A, Voss MJ. The foundations for scalable multi-core software in intel threading building blocks. Intel Technology Journal 2007(4).","DOI":"10.1535\/itj.1104.05"},{"key":"4729_CR18","doi-asserted-by":"crossref","unstructured":"Van De\u00a0Geijn RA, Watts J. Summa: scalable universal matrix multiplication algorithm. Concurrency: Practice and Experience 1997;9(4):255\u2013274","DOI":"10.1002\/(SICI)1096-9128(199704)9:4<255::AID-CPE250>3.0.CO;2-2"},{"key":"4729_CR19","doi-asserted-by":"publisher","unstructured":"Herault T, Robert Y, Bosilca G, Harrison RJ, Lewis CA, Valeev EF, Dongarra JJ. Distributed-memory multi-GPU block-sparse tensor contraction for electronic structure. In: 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS), 2021;537\u2013546 . https:\/\/doi.org\/10.1109\/IPDPS49936.2021.00062.","DOI":"10.1109\/IPDPS49936.2021.00062"},{"key":"4729_CR20","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 \u201924, 2024;1156\u20131165. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3673038.3673159.","DOI":"10.1145\/3673038.3673159"},{"key":"4729_CR21","unstructured":"Dijkstra EW. Over de sequentialiteit van procesbeschrijvingen (ewd-35) 1963."},{"key":"4729_CR22","unstructured":"OpenMP OpenMP Application Programming Interface, Version 5.2 2021. https:\/\/www.openmp.org\/wp-content\/uploads\/OpenMP-API-Specification-5-2.pdf."}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-026-04729-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-026-04729-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-026-04729-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T23:05:08Z","timestamp":1769209508000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-026-04729-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,22]]},"references-count":22,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["4729"],"URL":"https:\/\/doi.org\/10.1007\/s42979-026-04729-8","relation":{},"ISSN":["2661-8907"],"issn-type":[{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,22]]},"assertion":[{"value":"4 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no Conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval and Consent to Participate"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}}],"article-number":"133"}}