{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T04:56:21Z","timestamp":1790744181221,"version":"4.1.0"},"publisher-location":"Cham","reference-count":32,"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_12","type":"book-chapter","created":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:07:34Z","timestamp":1759277254000},"page":"140-153","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Comparing and\u00a0Contrasting User and\u00a0Runtime Directed Data Placement Strategies for\u00a0Owner-Compute, Multi-accelerator Distributed Task Based Scheduling"],"prefix":"10.1007","author":[{"given":"Aurelien","family":"Bouteiller","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinglei","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joseph","family":"Schuchart","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Herault","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,1]]},"reference":[{"key":"12_CR1","first-page":"1","volume":"99","author":"G Bosilca","year":"2013","unstructured":"Bosilca, G., Bouteiller, A., Danalis, A., Faverge, M., Herault, T., Dongarra, J.: PaRSEC: a programming paradigm exploiting heterogeneity for enhancing scalability. Comput. Sci. Eng. 99, 1 (2013)","journal-title":"Comput. Sci. Eng."},{"issue":"1","key":"12_CR2","first-page":"147","volume":"39","author":"A Bouteiller","year":"2025","unstructured":"Bouteiller, A., Herault, T., Cao, Q., Schuchart, J., Bosilca, G.: PaRSEC: scalability, flexibility, and hybrid architecture support for task-based applications in ECP. IJHPCA 39(1), 147\u2013166 (2025)","journal-title":"IJHPCA"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Cao, Q., Bosilca, G., Wu, W., Zhong, D., Bouteiller, A., Dongarra, J.: Flexible data redistribution in a task-based runtime system. In: 2020 IEEE CLUSTER, pp. 221\u2013225, September 2020","DOI":"10.1109\/CLUSTER49012.2020.00032"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Allen, T., Ge, R.: In-depth analyses of unified virtual memory system for gpu accelerated computing. In: Proceedings of Supercomputing, SC 2021. ACM (2021)","DOI":"10.1145\/3458817.3480855"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Bosilca, G., et al.: Flexible development of dense linear algebra algorithms on massively parallel architectures with DPLASMA. In: IPDPS Workshops, IEEE (2011)","DOI":"10.1109\/IPDPS.2011.299"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Atchley, S., Zimmer, C., Lange, J., Bernholdt, D., et\u00a0al.: Frontier: exploring exascale. In: Proceedings of Supercomputing, SC 2023. ACM (2023)","DOI":"10.1145\/3581784.3607089"},{"key":"12_CR7","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, ScalA 2017 (2017)","DOI":"10.1145\/3148226.3148233"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Danalis, A., Bosilca, G., Bouteiller, A., Herault, T., Dongarra, J.: PTG: an abstraction for unhindered parallelism. In: WOLFHPC, pp. 21\u201330 (2014)","DOI":"10.1109\/WOLFHPC.2014.8"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Bosilca, G., Harrison, R.J., Herault, T., Javanmard, M.M., Nookala, P., Valeev, E.F.: The template task graph (TTG)-an emerging practical dataflow programming paradigm for scientific simulation at extreme scale. In: International Workshop on Extreme Scale Programming Models and Middleware, IEEE (2020)","DOI":"10.1109\/ESPM251964.2020.00011"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Herault, T., Robert, Y., Bosilca, G., Dongarra, J.: Generic matrix multiplication for multi-GPU accelerated distributed-memory platforms over PaRSEC. In: 2019 IEEE\/ACM 10th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems (ScalA), pp. 33\u201341. IEEE (2019)","DOI":"10.1109\/ScalA49573.2019.00010"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Herault, T., et al.: Distributed-memory multi-GPU block-sparse tensor contraction for electronic structure. In: International Parallel and Distributed Processing Symposium (IPDPS), pp. 537\u2013546. IEEE (2021)","DOI":"10.1109\/IPDPS49936.2021.00062"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Cao, Q., et al.: Performance analysis of tile low-rank cholesky factorization using PaRSEC instrumentation tools. In: ProTools, pp. 25\u201332 (2019)","DOI":"10.1109\/ProTools49597.2019.00009"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Cao, Q., et al.: Extreme-scale task-based cholesky factorization toward climate and weather prediction applications. In: PASC, pp. 1\u201311 (2020)","DOI":"10.1145\/3394277.3401846"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Cao, Q., et al.: Leveraging PaRSEC runtime support to tackle challenging 3D data-sparse matrix problems. In: IPDPS, pp. 79\u201389. IEEE (2021)","DOI":"10.1109\/IPDPS49936.2021.00017"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Cao, Q., et al.: Reshaping geostatistical modeling and prediction for extreme-scale environmental applications. In: Supercomputing (2022)","DOI":"10.1109\/SC41404.2022.00007"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Cao, Q., et al.: A framework to exploit data sparsity in tile low-rank Cholesky factorization. In: IPDPS, pp. 414\u2013424 (2022)","DOI":"10.1109\/IPDPS53621.2022.00047"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Cao, Q., Abdulah, S., Ltaief, H., Genton, M.G., Keyes, D., et\u00a0al.: Reducing data motion and energy consumption of geospatial modeling applications using automated precision conversion. In: CLUSTER, pp. 330\u2013342 (2023)","DOI":"10.1109\/CLUSTER52292.2023.00035"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Ltaief, H., et al.: Toward capturing genetic epistasis from multivariate genome-wide association studies using mixed-precision kernel ridge regression. In: Supercomptuing, pp. 1\u201312 (2024)","DOI":"10.1109\/SC41406.2024.00012"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Abdulah, S., et al.: Boosting earth system model outputs and saving petabytes in their storage using exascale climate emulators. In: Supercomputing, pp. 1\u201312 (2024)","DOI":"10.1109\/SC41406.2024.00008"},{"issue":"8","key":"12_CR20","first-page":"1856","volume":"33","author":"Q Cao","year":"2021","unstructured":"Cao, Q., Bosilca, G., Losada, N., Wu, W., Zhong, D., Dongarra, J.: Evaluating data redistribution in PaRSEC. IPDPS 33(8), 1856\u20131872 (2021)","journal-title":"IPDPS"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Blackford, L.S., et al.: ScaLAPACK Users\u2019 Guide. SIAM (1997)","DOI":"10.1137\/1.9780898719642"},{"issue":"1","key":"12_CR22","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.parco.2008.10.002","volume":"35","author":"A Buttari","year":"2009","unstructured":"Buttari, A., Langou, J., Kurzak, J., Dongarra, J.: A class of parallel tiled linear algebra algorithms for multicore architectures. Par. Comp. 35(1), 38\u201353 (2009)","journal-title":"Par. Comp."},{"issue":"1","key":"12_CR23","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1006\/jpdc.1997.1351","volume":"45","author":"L Prylli","year":"1997","unstructured":"Prylli, L., Tourancheau, B.: Fast runtime block cyclic data redistribution on multiprocessors. J. Parall. Distrib. Comput. 45(1), 63\u201372 (1997)","journal-title":"J. Parall. Distrib. Comput."},{"key":"12_CR24","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1016\/j.future.2021.08.014","volume":"127","author":"L Chunlin","year":"2022","unstructured":"Chunlin, L., Qianqian, C., Youlong, L.: Optimal data placement strategy considering capacity limitation and load balancing in geographically distributed cloud. FGCS 127, 142\u2013159 (2022)","journal-title":"FGCS"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Sun, Q., et al.: In-staging data placement for asynchronous coupling of task-based scientific workflows. In: ESPM2, pp. 2\u20139 (2016)","DOI":"10.1109\/ESPM2.2016.006"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Klinkenberg, J., et al.: Phase-based data placement optimization in heterogeneous memory. In: CLUSTER, pp. 382\u2013393 (2024)","DOI":"10.1109\/CLUSTER59578.2024.00040"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Lifflander, J., et al.: A communication- and memory-aware model for load balancing tasks. https:\/\/arxiv.org\/abs\/2404.16793 (2024)","DOI":"10.2172\/2563863"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Gonthier, M., Marchal, L., Thibault, S.: Memory-aware scheduling of tasks sharing data on multiple GPUs with dynamic runtime systems. In: IPDPS, pp. 694\u2013704, May 2022","DOI":"10.1109\/IPDPS53621.2022.00073"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Haidar, A., Abdelfatah, A., Tomov, S., Dongarra, J.: High-performance cholesky factorization for GPU-only execution. In: GPGPU-10, pp. 42\u201352 (2017)","DOI":"10.1145\/3038228.3038237"},{"key":"12_CR30","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.parco.2018.10.007","volume":"83","author":"T Cojean","year":"2019","unstructured":"Cojean, T., Guermouche, A., Hugo, A., Namyst, R., Wacrenier, P.A.: Resource aggregation for task-based cholesky factorization on top of modern architectures. Parallel Comput. 83, 73\u201392 (2019)","journal-title":"Parallel Comput."},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Kwasniewski, G., Kabi\u0107, M., Besta, M., VandeVondele, J., et\u00a0al.: Red-blue pebbling revisited: near optimal parallel matrix-matrix multiplication. SC 2019 (2019)","DOI":"10.1145\/3295500.3356181"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Anastasiadis, P., Papadopoulou, N., Koziris, N., Goumas, G.: Uncut-GEMMs: communication-aware matrix multiplication on multi-GPU nodes. In: CLUSTER, pp. 143\u2013154, September 2024","DOI":"10.1109\/CLUSTER59578.2024.00020"}],"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_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T03:40:27Z","timestamp":1781667627000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-97196-9_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,1]]},"ISBN":["9783031971952","9783031971969"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-97196-9_12","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"}}]}}