{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:13:14Z","timestamp":1785499994750,"version":"3.56.0"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030479558","type":"print"},{"value":"9783030479565","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,7,31]],"date-time":"2020-07-31T00:00:00Z","timestamp":1596153600000},"content-version":"vor","delay-in-days":212,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-47956-5_6","type":"book-chapter","created":{"date-parts":[[2020,7,30]],"date-time":"2020-07-30T17:26:56Z","timestamp":1596130016000},"page":"103-142","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["DASH: Distributed Data Structures and Parallel Algorithms in a Global Address Space"],"prefix":"10.1007","author":[{"given":"Karl","family":"F\u00fcrlinger","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jos\u00e9","family":"Gracia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Kn\u00fcpfer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"Fuchs","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Denis","family":"H\u00fcnich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pascal","family":"Jungblut","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roger","family":"Kowalewski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joseph","family":"Schuchart","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,7,31]]},"reference":[{"key":"6_CR1","doi-asserted-by":"publisher","unstructured":"Agullo, E., Aumage, O., Faverge, M., Furmento, N., Pruvost, F., Sergent, M., Thibault, S.P.: Achieving high performance on supercomputers with a sequential task-based programming model. IEEE Trans. Parallel Distrib. Syst. (2018). \nhttps:\/\/doi.org\/10.1109\/TPDS.2017.2766064","DOI":"10.1109\/TPDS.2017.2766064"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Axtmann, M., Bingmann, T., Sanders, P., Schulz, C.: Practical massively parallel sorting. In: Proceedings of the 27th ACM symposium on Parallelism in Algorithms and Architectures, pp. 13\u201323. ACM, New York (2015)","DOI":"10.1145\/2755573.2755595"},{"key":"6_CR3","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1109\/TPDS.2008.105","volume":"20","author":"E Ayguade","year":"2009","unstructured":"Ayguade, E., Copty, N., Duran, A., Hoeflinger, J., Lin, Y., Massaioli, F., Teruel, X., Unnikrishnan, P., Zhang, G.: The design of OpenMP tasks. IEEE Trans. Parallel Distrib. Syst. 20, 404\u2013418 (2009). \nhttps:\/\/doi.org\/10.1109\/TPDS.2008.105","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Bauer, M., Treichler, S., Slaughter, E., Aiken, A.: Legion: expressing locality and independence with logical regions. In: 2012 International Conference for High Performance Computing, Networking, Storage and Analysis (SC), pp. 1\u201311 (2012). \nhttps:\/\/doi.org\/10.1109\/SC.2012.71","DOI":"10.1109\/SC.2012.71"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Blelloch, G.E., Leiserson, C.E., Maggs, B.M., Plaxton, C.G., Smith, S.J., Zagha, M.: A comparison of sorting algorithms for the connection machine cm-2. In: Proceedings of the Third Annual ACM Symposium on Parallel Algorithms and Architectures, pp. 3\u201316. ACM, New York (1991)","DOI":"10.1145\/113379.113380"},{"key":"6_CR6","volume-title":"Cilk: An Efficient Multithreaded Runtime System","author":"RD Blumofe","year":"1995","unstructured":"Blumofe, R.D., Joerg, C.F., Kuszmaul, B.C., Leiserson, C.E., Randall, K.H., Zhou, Y.: Cilk: An Efficient Multithreaded Runtime System, vol. 30. ACM, New York (1995)"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Bosilca, G., Bouteiller, A., Danalis, A., Herault, T., Lemariner, P., Dongarra, J.: Dague: a generic distributed dag engine for high performance computing. In: Proceedings of the Workshops of the 25th IEEE International Symposium on Parallel and Distributed Processing (IPDPS 2011 Workshops), pp. 1151\u20131158 (2011)","DOI":"10.1109\/IPDPS.2011.281"},{"key":"6_CR8","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1177\/1094342007078442","volume":"21","author":"BL Chamberlain","year":"2007","unstructured":"Chamberlain, B.L., Callahan, D., Zima, H.P.: Parallel programmability and the Chapel language. Int. J. High Perform. Comput. Appl. 21, 291\u2013312 (2007)","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"6_CR9","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1145\/1103845.1094852","volume":"40","author":"P Charles","year":"2005","unstructured":"Charles, P., Grothoff, C., Saraswat, V., Donawa, C., Kielstra, A., Ebcioglu, K., Von Praun, C., Sarkar, V.: X10: an object-oriented approach to non-uniform cluster computing. ACM SIGPLAN Not. 40, 519\u2013538 (2005)","journal-title":"ACM SIGPLAN Not."},{"key":"6_CR10","volume-title":"The Go Programming Language","author":"AA Donovan","year":"2015","unstructured":"Donovan, A.A., Kernighan, B.W.: The Go Programming Language, 1st edn. Addison-Wesley Professional, Boston (2015)","edition":"1"},{"key":"6_CR11","doi-asserted-by":"publisher","unstructured":"Fuchs, T., F\u00fcrlinger, K.: A multi-dimensional distributed array abstraction for PGAS. In: Proceedings of the 18th IEEE International Conference on High Performance Computing and Communications (HPCC 2016), Sydney, pp. 1061\u20131068 (2016). \nhttps:\/\/doi.org\/10.1109\/HPCC-SmartCity-DSS.2016.0150","DOI":"10.1109\/HPCC-SmartCity-DSS.2016.0150"},{"key":"6_CR12","doi-asserted-by":"publisher","unstructured":"F\u00fcrlinger, K., Fuchs, T., Kowalewski, R.: DASH: a C+\u2009+ PGAS library for distributed data structures and parallel algorithms. In: Proceedings of the 18th IEEE International Conference on High Performance Computing and Communications (HPCC 2016), Sydney, pp. 983\u2013990 (2016). \nhttps:\/\/doi.org\/10.1109\/HPCC-SmartCity-DSS.2016.0140","DOI":"10.1109\/HPCC-SmartCity-DSS.2016.0140"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"F\u00fcrlinger, K., Kowalewski, R., Fuchs, T., Lehmann, B.: Investigating the performance and productivity of DASH using the cowichan problems. In: Proceedings of the International Conference on High Performance Computing in Asia-Pacific Region Workshops, Tokyo (2018). \nhttps:\/\/doi.org\/10.1145\/3176364.3176366","DOI":"10.1145\/3176364.3176366"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Grossman, M., Kumar, V., Budimli\u0107, Z., Sarkar, V.: Integrating asynchronous task parallelism with OpenSHMEM. In: Workshop on OpenSHMEM and Related Technologies, pp. 3\u201317. Springer, Berlin (2016)","DOI":"10.1007\/978-3-319-50995-2_1"},{"key":"6_CR15","unstructured":"Harsh, V., Kal\u00e9, L.V., Solomonik, E.: Histogram sort with sampling. CoRR abs\/1803.01237 (2018). \nhttp:\/\/arxiv.org\/abs\/1803.01237"},{"key":"6_CR16","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1145\/297096.297128","volume":"3","author":"DR Helman","year":"1998","unstructured":"Helman, D.R., J\u00e1J\u00e1, J., Bader, D.A.: A new deterministic parallel sorting algorithm with an experimental evaluation. ACM J. Exp. Algorithmics 3, 4 (1998)","journal-title":"ACM J. Exp. Algorithmics"},{"key":"6_CR17","doi-asserted-by":"publisher","unstructured":"Kaiser, H., Brodowicz, M., Sterling, T.: Parallex an advanced parallel execution model for scaling-impaired applications. In: 2009 International Conference on Parallel Processing Workshops (2009). \nhttps:\/\/doi.org\/10.1109\/ICPPW.2009.14","DOI":"10.1109\/ICPPW.2009.14"},{"key":"6_CR18","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, PGAS \u201914. ACM, New York (2014). \nhttp:\/\/doi.acm.org\/10.1145\/2676870.2676883"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Karlin, I., Keasler, J., Neely, R.: Lulesh 2.0 updates and changes. Technical Report. LLNL-TR-641973 (2013)","DOI":"10.2172\/1090032"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Kowalewski, R., Jungblut, P., F\u00fcrlinger, K.: Engineering a distributed histogram sort. In: 2019 IEEE International Conference on Cluster Computing (CLUSTER). IEEE, Piscataway (2019)","DOI":"10.1109\/CLUSTER.2019.8891005"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Kumar, V., Zheng, Y., Cav\u00e9, V., Budimli\u0107, Z., Sarkar, V.: HabaneroUPC+\u2009+: a compiler-free PGAS library. In: Proceedings of the 8th International Conference on Partitioned Global Address Space Programming Models, PGAS \u201914. ACM, New York (2014). \nhttps:\/\/doi.org\/10.1145\/2676870.2676879","DOI":"10.1145\/2676870.2676879"},{"key":"6_CR22","unstructured":"Matthes, A., Widera, R., Zenker, E., Worpitz, B., Huebl, A., Bussmann, M.: Tuning and optimization for a variety of many-core architectures without changing a single line of implementation code using the alpaka library (2017). \nhttps:\/\/arxiv.org\/abs\/1706.10086"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Nanz, S., West, S., Da Silveira, K.S., Meyer, B.: Benchmarking usability and performance of multicore languages. In: 2013 ACM\/IEEE International Symposium on Empirical Software Engineering and Measurement, pp. 183\u2013192. IEEE, Piscataway (2013)","DOI":"10.1109\/ESEM.2013.10"},{"key":"6_CR24","unstructured":"OpenMP Architecture Review Board: OpenMP Application Programming Interface, Version 5.0 (2018). \nhttps:\/\/www.openmp.org\/wp-content\/uploads\/OpenMP-API-Specification-5.0.pdf"},{"key":"6_CR25","unstructured":"Reinders, J.: Intel Threading Building Blocks: Outfitting C+\u2009+ for Multi-Core Processor Parallelism. O\u2019Reilly & Associates, Sebastopol (2007)"},{"key":"6_CR26","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1109\/MCSE.2013.21","volume":"15","author":"AD Robison","year":"2013","unstructured":"Robison, A.D.: Composable parallel patterns with intel cilk plus. Comput. Sci. Eng. 15, 66\u201371 (2013). \nhttps:\/\/doi.org\/10.1109\/MCSE.2013.21","journal-title":"Comput. Sci. Eng."},{"key":"6_CR27","unstructured":"Saraswat, V., Almasi, G., Bikshandi, G., Cascaval, C., Cunningham, D., Grove, D., Kodali, S., Peshansky, I., Tardieu, O.: The asynchronous partitioned global address space model. In: The First Workshop on Advances in Message Passing, pp. 1\u20138 (2010)"},{"issue":"3-4","key":"6_CR28","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1007\/PL00008268","volume":"24","author":"E Saukas","year":"1999","unstructured":"Saukas, E., Song, S.: A note on parallel selection on coarse-grained multicomputers. Algorithmica 24(3-4), 371\u2013380 (1999)","journal-title":"Algorithmica"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Shirako, J., Peixotto, D.M., Sarkar, V., Scherer, W.N.: Phasers: a unified deadlock-free construct for collective and point-to-point synchronization. In: Proceedings of the 22nd Annual International Conference on Supercomputing, ICS \u201908. ACM, New York (2008). \nhttps:\/\/doi.org\/10.1145\/1375527.1375568","DOI":"10.1145\/1375527.1375568"},{"key":"6_CR30","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: SC15: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201312 (2015). \nhttps:\/\/doi.org\/10.1145\/2807591.2807629","DOI":"10.1145\/2807591.2807629"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Sundar, H., Malhotra, D., Biros, G.: Hyksort: a new variant of hypercube quicksort on distributed memory architectures. In: Proceedings of the 27th international ACM conference on International Conference on Supercomputing, pp. 293\u2013302. ACM, New York (2013)","DOI":"10.1145\/2464996.2465442"},{"key":"6_CR32","doi-asserted-by":"publisher","first-page":"2421","DOI":"10.1002\/cpe.2831","volume":"24","author":"E Tejedor","year":"2012","unstructured":"Tejedor, E., Farreras, M., Grove, D., Badia, R.M., Almasi, G., Labarta, J.: A high-productivity task-based programming model for clusters. Concurr. Comp. Pract. Exp. 24, 2421\u20132448 (2012). \nhttps:\/\/doi.org\/10.1002\/cpe.2831","journal-title":"Concurr. Comp. Pract. Exp."},{"issue":"1","key":"6_CR33","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1177\/1094342005051521","volume":"19","author":"R Thakur","year":"2005","unstructured":"Thakur, R., Rabenseifner, R., Gropp, W.: Optimization of collective communication operations in MPICH. Int. J. High Perform. Comput. Appl. 19(1), 49\u201366 (2005). \nhttps:\/\/doi.org\/10.1177\/1094342005051521","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"6_CR34","doi-asserted-by":"publisher","first-page":"C617","DOI":"10.1137\/140989716","volume":"37","author":"M Tillenius","year":"2015","unstructured":"Tillenius, M.: SuperGlue: a shared memory framework using data versioning for dependency-aware task-based parallelization. SIAM J. Sci. Comput. 37, C617\u2013C642 (2015). \nhttp:\/\/epubs.siam.org\/doi\/10.1137\/140989716","journal-title":"SIAM J. Sci. Comput."},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Tsugane, K., Lee, J., Murai, H., Sato, M.: Multi-tasking execution in pgas language xcalablemp and communication optimization on many-core clusters. In: Proceedings of the International Conference on High Performance Computing in Asia-Pacific Region. ACM, New York (2018). \nhttps:\/\/doi.org\/10.1145\/3149457.3154482","DOI":"10.1145\/3149457.3154482"},{"key":"6_CR36","volume-title":"Assessing and comparing the usability of parallel programming systems","author":"GV Wilson","year":"1995","unstructured":"Wilson, G.V., Irvin, R.B.: Assessing and comparing the usability of parallel programming systems. University of Toronto. Computer Systems Research Institute (1995)"}],"container-title":["Lecture Notes in Computational Science and Engineering","Software for Exascale Computing - SPPEXA 2016-2019"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-47956-5_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,7,30]],"date-time":"2020-07-30T17:28:13Z","timestamp":1596130093000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-47956-5_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030479558","9783030479565"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-47956-5_6","relation":{},"ISSN":["1439-7358","2197-7100"],"issn-type":[{"value":"1439-7358","type":"print"},{"value":"2197-7100","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"31 July 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}