{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:44:34Z","timestamp":1740123874193,"version":"3.37.3"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"5-6","license":[{"start":{"date-parts":[[2018,12,7]],"date-time":"2018-12-07T00:00:00Z","timestamp":1544140800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,12,7]],"date-time":"2018-12-07T00:00:00Z","timestamp":1544140800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1337135"],"award-info":[{"award-number":["1337135"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006168","name":"National Nuclear Security Administration","doi-asserted-by":"publisher","award":["DE-NA0002375"],"award-info":[{"award-number":["DE-NA0002375"]}],"id":[{"id":"10.13039\/100006168","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006228","name":"Oak Ridge National Laboratory","doi-asserted-by":"publisher","award":["CSC188"],"award-info":[{"award-number":["CSC188"]}],"id":[{"id":"10.13039\/100006228","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006132","name":"Office of Science","doi-asserted-by":"publisher","award":["DE-AC05-00OR22725"],"award-info":[{"award-number":["DE-AC05-00OR22725"]}],"id":[{"id":"10.13039\/100006132","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Parallel Prog"],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1007\/s10766-018-0619-1","type":"journal-article","created":{"date-parts":[[2018,12,7]],"date-time":"2018-12-07T06:46:12Z","timestamp":1544165172000},"page":"1086-1116","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Automatic Halo Management for the Uintah GPU-Heterogeneous Asynchronous Many-Task Runtime"],"prefix":"10.1007","volume":"47","author":[{"given":"Brad","family":"Peterson","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alan","family":"Humphrey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Sunderland","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Sutherland","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tony","family":"Saad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harish","family":"Dasari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Berzins","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,12,7]]},"reference":[{"key":"619_CR1","unstructured":"Scientific Computing and Imaging Institute. Uintah Web Page (2015). http:\/\/www.uintah.utah.edu\/"},{"key":"619_CR2","doi-asserted-by":"crossref","unstructured":"Humphrey, A., Meng, Q., Berzins, M., Harman, T.: Radiation modeling using the uintah heterogeneous CPU\/GPU runtime system. In: Proceedings of the 1st Conference of the Extreme Science and Engineering Discovery Environment (XSEDE 2012). ACM (2012)","DOI":"10.1145\/2335755.2335791"},{"key":"619_CR3","doi-asserted-by":"crossref","unstructured":"Peterson, B., Dasari, H., Humphrey, A., Sutherland, J., Saad, T., Berzins, M.: Reducing overhead in the uintah framework to support short-lived tasks on GPU-heterogeneous architectures. In: Proceedings of the 5th International Workshop on Domain-Specific Languages and High-Level Frameworks for High Performance Computing, WOLFHPC \u201915, pp. 4:1\u20134:8. ACM, New York (2015)","DOI":"10.1145\/2830018.2830023"},{"key":"619_CR4","doi-asserted-by":"crossref","unstructured":"Meng, Q., Humphrey, A., Berzins, M.: The Uintah framework: a unified heterogeneous task scheduling and runtime system. In: Digital Proceedings of Supercomputing 12\u2014WOLFHPC Workshop. IEEE (2012)","DOI":"10.1109\/SCC.2012.6674233"},{"key":"619_CR5","unstructured":"Berzins, M.: Status of Release of the Uintah Computational Framework. Technical report UUSCI-2012-001. Scientific Computing and Imaging Institute (2012)"},{"key":"619_CR6","unstructured":"Kashiwa, B.A., Gaffney, E.S.: Design Basis for CFDLIB. Technical report LA-UR-03-1295. Los Alamos National Laboratory (2003)"},{"key":"619_CR7","first-page":"509","volume":"2","author":"SG Bardenhagen","year":"2001","unstructured":"Bardenhagen, S.G., Guilkey, J.E., Roessig, K.M., Brackbill, J.U., Witzel, W.M., Foster, J.C.: An improved contact algorithm for the material point method and application to stress propagation in granular material. Comput. Model. Eng. Sci. 2, 509\u2013522 (2001)","journal-title":"Comput. Model. Eng. Sci."},{"key":"619_CR8","volume-title":"Fluid Structure Interaction II","author":"JE Guilkey","year":"2003","unstructured":"Guilkey, J.E., Harman, T.B., Xia, A., Kashiwa, B.A., McMurtry, P.A.: An Eulerian-Lagrangian approach for large deformation fluid-structure interaction problems, part 1: algorithm development. In: Chakrabarti, S.K., Brebbia, C.A., Almorza, D., Gonzalez-Palma, R. (eds.) Fluid Structure Interaction II. WIT Press, Cadiz (2003)"},{"key":"619_CR9","volume-title":"Transport Phenomena in Fires","author":"J Spinti","year":"2008","unstructured":"Spinti, J., Thornock, J., Eddings, E., Smith, P.J., Sarofim, A.: Heat transfer to objects in pool fires. In: Faghri, M., Sund\u00e9n, B. (eds.) Transport Phenomena in Fires. WIT Press, Southampton (2008)"},{"key":"619_CR10","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1016\/j.jocs.2016.04.010","volume":"17","author":"T Saad","year":"2016","unstructured":"Saad, T., Sutherland, J.C.: Wasatch: an architecture-proof multiphysics development environment using a domain specific language and graph theory. J. Comput. Sci. 17, 639\u2013646 (2016)","journal-title":"J. Comput. Sci."},{"key":"619_CR11","doi-asserted-by":"crossref","unstructured":"Meng, Q., Berzins, M., Schmidt, J.: Using hybrid parallelism to improve memory use in the uintah framework. In: Proceedings of the 2011 TeraGrid Conference (TG11), Salt Lake City, Utah (2011)","DOI":"10.1145\/2016741.2016767"},{"key":"619_CR12","doi-asserted-by":"crossref","unstructured":"Meng, Q., Humphrey, A., Schmidt, J., Berzins, M.: Investigating applications portability with the Uintah DAG-based runtime system on PetaScale supercomputers. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, SC \u201913, pp. 96:1\u201396:12. ACM, New York (2013)","DOI":"10.1145\/2503210.2503250"},{"key":"619_CR13","doi-asserted-by":"crossref","unstructured":"Peterson, B., Humphrey, A., Schmidt, J., Berzins, M.: Addressing global data dependencies in heterogeneous asynchronous runtime systems on GPUs. In: Submitted\u2014Third International Workshop on Extreme Scale Programming Models and Middleware, ESPM2. IEEE Press (2017)","DOI":"10.1145\/3152041.3152082"},{"key":"619_CR14","doi-asserted-by":"crossref","unstructured":"Bauer, M., Treichler, Sean, S., Elliott, A., Alex: Legion: expressing locality and independence with logical regions. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, SC \u201912, pp. 66:1\u201366:11. IEEE Computer Society Press, Los Alamitos (2012)","DOI":"10.1109\/SC.2012.71"},{"issue":"10","key":"619_CR15","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1145\/167962.165874","volume":"28","author":"LV Kale","year":"1993","unstructured":"Kale, L.V., Krishnan, S.: CHARM++: a portable concurrent object oriented system based on C++. SIGPLAN Not. 28(10), 91\u2013108 (1993)","journal-title":"SIGPLAN Not."},{"issue":"2","key":"619_CR16","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1002\/cpe.1631","volume":"23","author":"C\u00e9dric Augonnet","year":"2011","unstructured":"Augonnet, C\u00e9dric, Thibault, Samuel, Namyst, Raymond, Wacrenier, Pierre-Andr\u00e9: StarPU: a unified platform for task scheduling on heterogeneous multicore architectures. Concurr. Comput. Pract. Exp. 23(2), 187\u2013198 (2011)","journal-title":"Concurr. Comput. Pract. Exp."},{"issue":"1\u20132","key":"619_CR17","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.parco.2011.10.003","volume":"38","author":"George Bosilca","year":"2012","unstructured":"Bosilca, George, Bouteiller, Aurelien, Danalis, Anthony, Herault, Thomas, Lemarinier, Pierre, Dongarra, Jack: DAGuE: A Generic Distributed DAG Engine for High Performance Computing. Parallel Comput. 38(1\u20132), 37\u201351 (2012)","journal-title":"Parallel Comput."},{"key":"619_CR18","doi-asserted-by":"crossref","unstructured":"Humphrey, A., Sunderland, D., Harman, T., Berzins, M.: Radiative heat transfer calculation on 16384 GPUs using a reverse Monte Carlo ray tracing approach with adaptive mesh refinement. In: 2016 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 1222\u20131231 (2016)","DOI":"10.1109\/IPDPSW.2016.93"},{"issue":"5","key":"619_CR19","doi-asserted-by":"publisher","first-page":"S101","DOI":"10.1137\/15M1023270","volume":"38","author":"M Berzins","year":"2016","unstructured":"Berzins, M., Beckvermit, J., Harman, T., Bezdjian, A., Humphrey, A., Meng, Q., Schmidt, J., Wight, C.: Extending the Uintah framework through the petascale modeling of detonation in arrays of high explosive devices. SIAM J. Sci. Comput. 38(5), S101\u2013S122 (2016)","journal-title":"SIAM J. Sci. Comput."},{"key":"619_CR20","unstructured":"Bourd, A.: The OpenCL Specification (2017). https:\/\/www.khronos.org\/registry\/OpenCL\/specs\/opencl-2.2.pdf"},{"key":"619_CR21","unstructured":"OpenACC member companies and CAPS Enterprise and CRAY Inc and The Portland Group Inc (PGI) and NVIDIA. OpenACC 2.5 Specification (2015). https:\/\/www.openacc.org\/specification"},{"key":"619_CR22","unstructured":"OpenMP Architecture Review Board. Openmp application program interface version 4.0 (2013)"},{"key":"619_CR23","doi-asserted-by":"crossref","unstructured":"Keasler, J., Hornung, R.: The RAJA Portability Layer: Overview and Status. Technical report LLNL-TR-661403, Lawrence Livermore National Laboratory (2014)","DOI":"10.2172\/1169830"},{"key":"619_CR24","doi-asserted-by":"crossref","unstructured":"Edwards, H.C., Sunderland, D.: Kokkos array performance-portable manycore programming model. In: Proceedings of the 2012 International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM \u201912, pp. 1\u201310. ACM, New York (2012)","DOI":"10.1145\/2141702.2141703"},{"key":"619_CR25","unstructured":"Srman, T.: Comparison of Technologies for General-Purpose Computing on Graphics Processing Units. Master\u2019s thesis, Department of Electrical Engineering, Linkping University (2016)"},{"key":"619_CR26","first-page":"253","volume-title":"OpenMP: Memory, Devices, and Tasks: 12th International Workshop on OpenMP, IWOMP 2016, Nara, Japan, October 5\u20137, 2016, Proceedings","author":"M Martineau","year":"2016","unstructured":"Martineau, M., Price, J., McIntosh-Smith, S., Gaudin, W.: Pragmatic performance portability with OpenMP 4.x. In: Maruyama, N., de Supinski, B.R., Wahib, M. (eds.) OpenMP: Memory, Devices, and Tasks: 12th International Workshop on OpenMP, IWOMP 2016, Nara, Japan, October 5\u20137, 2016, Proceedings, pp. 253\u2013267. Springer, Cham (2016)"},{"key":"619_CR27","doi-asserted-by":"crossref","unstructured":"Landaverde, R., Zhang, T., Coskun, A.K., Herbordt, M.C.: An investigation of unified memory access performance in CUDA. In: 2014 IEEE High Performance Extreme Computing Conference (HPEC), pp. 1\u20136 (2014)","DOI":"10.1109\/HPEC.2014.7040988"},{"key":"619_CR28","unstructured":"Nvidia. CUDA C Programming Guide v8.0 Web page\u2014J. Unified Memory Programming (2017). http:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide\/index.html#um-unified-memory-programming-hd"},{"issue":"1","key":"619_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2382585.2382586","volume":"39","author":"PK Notz","year":"2012","unstructured":"Notz, P.K., Pawlowski, R.P., Sutherland, J.C.: Graph-based software design for managing complexity and enabling concurrency in multiphysics PDE software. ACM Trans. Math. Softw. TOMS 39(1), 1 (2012)","journal-title":"ACM Trans. Math. Softw. TOMS"},{"key":"619_CR30","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1016\/j.jss.2016.01.023","volume":"125","author":"C Earl","year":"2017","unstructured":"Earl, C., Might, M., Bagusetty, A., Sutherland, J.C.: Nebo: an efficient, parallel, and portable domain-specific language for numerically solving partial differential equations. J. Syst. Softw. 125, 389\u2013400 (2017)","journal-title":"J. Syst. Softw."},{"key":"619_CR31","doi-asserted-by":"crossref","unstructured":"Sutherland, J.C., Saad, T.: The discrete operator approach to the numerical solution of partial differential equations. In: 20th AIAA Computational Fluid Dynamics Conference, pp. AIAA\u20132011\u20133377, Honolulu, Hawaii, USA (2011)","DOI":"10.2514\/6.2011-3377"},{"key":"619_CR32","unstructured":"Nvidia. Nvlink web page (2015). http:\/\/www.nvidia.com\/object\/nvlink.html"},{"key":"619_CR33","doi-asserted-by":"crossref","unstructured":"Wu, W., Bosilca, G., vandeVaart, R., Jeaugey, S., Dongarra, J.: GPU-aware non-contiguous data movement in open MPI. In: Proceedings of the 25th ACM International Symposium on High-Performance Parallel and Distributed Computing, HPDC \u201916, pp. 231\u2013242. ACM, New York (2016)","DOI":"10.1145\/2907294.2907317"},{"key":"619_CR34","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1007\/978-3-319-29778-1_11","volume-title":"Languages and Compilers for Parallel Computing","author":"Bin Ren","year":"2016","unstructured":"Ren, B., Ravi, N., Yang, Y., Feng, M., Agrawal, G., Chakradhar, S.: Automatic and efficient data host-device communication for many-core coprocessors. In: Revised Selected Papers of the 28th International Workshop on Languages and Compilers for Parallel Computing\u2014LCPC 2015, vol. 9519, p. 173\u2013190. Springer, New York (2016)"},{"key":"619_CR35","first-page":"212","volume-title":"High Performance Computing, Volume 9137 of Lecture Notes in Computer Science","author":"A Humphrey","year":"2015","unstructured":"Humphrey, A., Harman, T., Berzins, M., Smith, P.: A scalable algorithm for radiative heat transfer using reverse Monte Carlo ray tracing. In: Kunkel, J.M., Ludwig, T. (eds.) High Performance Computing, Volume 9137 of Lecture Notes in Computer Science, pp. 212\u2013230. Springer, New York (2015)"},{"issue":"4","key":"619_CR36","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1080\/10407799708915117","volume":"31","author":"SP Burns","year":"1997","unstructured":"Burns, S.P., Christen, M.A.: Spatial domain-based parallelism in large-scale, participating-media, radiative transport applications. Numer. Heat Transf. B Fundam. 31(4), 401\u2013421 (1997)","journal-title":"Numer. Heat Transf. B Fundam."},{"key":"619_CR37","doi-asserted-by":"crossref","unstructured":"Slaughter, E., Lee, W., Treichler, S., Bauer, M., Aiken, A.: Regent: a high-productivity programming language for HPC with logical regions. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC \u201915, pp. 81:1\u201381:12. ACM, New York (2015)","DOI":"10.1145\/2807591.2807629"},{"key":"619_CR38","doi-asserted-by":"crossref","unstructured":"Bosilca, G., Bouteiller, A., H\u00e9rault, T., Lemarinier, P., Saengpatsa, N.O., Tomov, S., Dongarra, J.J.: Performance portability of a GPU enabled factorization with the DAGuE framework. In: 2011 IEEE International Conference on Cluster Computing, pp. 395\u2013402 (2011)","DOI":"10.1109\/CLUSTER.2011.51"},{"key":"619_CR39","unstructured":"Bauer, M.E.: Legion: programming distributed heterogeneous architectures with logical regions. Ph.D. thesis, Stanford University (2014)"},{"key":"619_CR40","doi-asserted-by":"crossref","unstructured":"Bhatele, A., Yeom, J.-S., Jain, N., Kuhlman, C.J., Livnat, Y., Bisset, K.R., Kale, L.V., Marathe, M.V.: Massively parallel simulations of spread of infectious diseases over realistic social networks. In: Proceedings of the 17th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGrid \u201917, pp. 689\u2013694. IEEE Press, Piscataway (2017)","DOI":"10.1109\/CCGRID.2017.141"},{"key":"619_CR41","doi-asserted-by":"crossref","unstructured":"Agullo, E., Aumage, O., Faverge, M., Furmento, N., Pruvost, F., Sergent, M., Thibault, S.: Achieving high performance on supercomputers with a sequential task-based programming model. In: [Research Report] RR-8927, Inria Bordeaux Sud-Ouest, Bordeaux INP, CNRS, Universit\u00e9 de Bordeaux, CEA, p. 27 (2016)","DOI":"10.1109\/TPDS.2017.2766064"},{"key":"619_CR42","doi-asserted-by":"crossref","unstructured":"Danalis, A., Bosilca, G., Bouteiller, A., Herault, T., Dongarra, J.: PTG: an abstraction for unhindered parallelism. In: Proceedings of the Fourth International Workshop on Domain-Specific Languages and High-Level Frameworks for High Performance Computing, WOLFHPC \u201914, pp. 21\u201330. IEEE Press, Piscataway (2014)","DOI":"10.1109\/WOLFHPC.2014.8"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-018-0619-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10766-018-0619-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-018-0619-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,13]],"date-time":"2024-07-13T03:22:44Z","timestamp":1720840964000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10766-018-0619-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,7]]},"references-count":42,"journal-issue":{"issue":"5-6","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["619"],"URL":"https:\/\/doi.org\/10.1007\/s10766-018-0619-1","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"type":"print","value":"0885-7458"},{"type":"electronic","value":"1573-7640"}],"subject":[],"published":{"date-parts":[[2018,12,7]]},"assertion":[{"value":"15 May 2016","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 November 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 December 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}