{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:25:00Z","timestamp":1750220700089,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,2,23]],"date-time":"2020-02-23T00:00:00Z","timestamp":1582416000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000005","name":"U.S. Department of Defense","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000005","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,2,23]]},"DOI":"10.1145\/3366428.3380770","type":"proceedings-article","created":{"date-parts":[[2020,2,19]],"date-time":"2020-02-19T22:50:35Z","timestamp":1582152635000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["The Minos Computing Library"],"prefix":"10.1145","author":[{"given":"Roberto","family":"Gioiosa","sequence":"first","affiliation":[{"name":"Pacific Northwest National Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Burcu O.","family":"Mutlu","sequence":"additional","affiliation":[{"name":"Pacific Northwest National Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seyong","family":"Lee","sequence":"additional","affiliation":[{"name":"Oak Ridge National Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeffrey S.","family":"Vetter","sequence":"additional","affiliation":[{"name":"Oak Ridge National Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giulio","family":"Picierro","sequence":"additional","affiliation":[{"name":"University of Rome Tor Vergata, Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco","family":"Cesati","sequence":"additional","affiliation":[{"name":"University of Rome Tor Vergata, Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,2,23]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Mart\u00edn Abadi Ashish Agarwal Paul Barham Eugene Brevdo Zhifeng Chen Craig Citro Greg S. Corrado Andy Davis Jeffrey Dean Matthieu Devin Sanjay Ghemawat Ian Goodfellow Andrew Harp Geoffrey Irving Michael Isard Yangqing Jia Rafal Jozefowicz Lukasz Kaiser Manjunath Kudlur Josh Levenberg Dan Man\u00e9 Rajat Monga Sherry Moore Derek Murray Chris Olah Mike Schuster Jonathon Shlens Benoit Steiner Ilya Sutskever Kunal Talwar Paul Tucker Vincent Vanhoucke Vijay Vasudevan Fernanda Vi\u00e9gas Oriol Vinyals Pete Warden Martin Wattenberg Martin Wicke Yuan Yu and Xiaoqiang Zheng. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. http:\/\/tensorflow.org\/ Software available from tensorflow.org.  Mart\u00edn Abadi Ashish Agarwal Paul Barham Eugene Brevdo Zhifeng Chen Craig Citro Greg S. Corrado Andy Davis Jeffrey Dean Matthieu Devin Sanjay Ghemawat Ian Goodfellow Andrew Harp Geoffrey Irving Michael Isard Yangqing Jia Rafal Jozefowicz Lukasz Kaiser Manjunath Kudlur Josh Levenberg Dan Man\u00e9 Rajat Monga Sherry Moore Derek Murray Chris Olah Mike Schuster Jonathon Shlens Benoit Steiner Ilya Sutskever Kunal Talwar Paul Tucker Vincent Vanhoucke Vijay Vasudevan Fernanda Vi\u00e9gas Oriol Vinyals Pete Warden Martin Wattenberg Martin Wicke Yuan Yu and Xiaoqiang Zheng. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. http:\/\/tensorflow.org\/ Software available from tensorflow.org."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.1631"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2436256.2436271"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.71"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2400682.2400716"},{"volume-title":"ACM SIGPLAN symposium on Principles and Practice of Parallel Programming (PPOPP). ACM New York, NY, USA, 207--216","author":"Blumofe R.","key":"e_1_3_2_1_6_1","unstructured":"R. Blumofe , C. Joerg , B. Kuszmaul , C. Leiserson , K. Randall , and Y. Zhou . 1995. Cilk: An efficient multithreaded runtime system . In ACM SIGPLAN symposium on Principles and Practice of Parallel Programming (PPOPP). ACM New York, NY, USA, 207--216 . R. Blumofe, C. Joerg, B. Kuszmaul, C. Leiserson, K. Randall, and Y. Zhou. 1995. Cilk: An efficient multithreaded runtime system. In ACM SIGPLAN symposium on Principles and Practice of Parallel Programming (PPOPP). ACM New York, NY, USA, 207--216."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2012.58"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/99.660313"},{"key":"e_1_3_2_1_9_1","unstructured":"B. Dally. 2010. GPU Computing to Exascale and Beyond.  B. Dally. 2010. GPU Computing to Exascale and Beyond."},{"volume-title":"ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI). ACM Press New York, NY, USA, 212--223","author":"Frigo M.","key":"e_1_3_2_1_10_1","unstructured":"M. Frigo , C. E. Leiserson , and K. H. Randall . 1998. The implementation of the Cilk-5 multithreaded language . In ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI). ACM Press New York, NY, USA, 212--223 . M. Frigo, C. E. Leiserson, and K. H. Randall. 1998. The implementation of the Cilk-5 multithreaded language. In ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI). ACM Press New York, NY, USA, 212--223."},{"volume-title":"d.]. Threading Building Blocks. [Online]. Available: https:\/\/software.intel.com\/en-us\/intel-tbb. (Accessed","year":"2019","key":"e_1_3_2_1_11_1","unstructured":"Intel. [n. d.]. Threading Building Blocks. [Online]. Available: https:\/\/software.intel.com\/en-us\/intel-tbb. (Accessed Feb. 1, 2019 ). Intel. [n. d.]. Threading Building Blocks. [Online]. Available: https:\/\/software.intel.com\/en-us\/intel-tbb. (Accessed Feb. 1, 2019)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-014-0320-y"},{"volume-title":"Proceedings of the 8th International Conference on Partitioned Global Address Space Programming Models. ACM, 6.","author":"Kaiser H.","key":"e_1_3_2_1_13_1","unstructured":"H. Kaiser , T. Heller , B. Adelstein-Lelbach , A. Serio , and D. Fey . 2014. 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. ACM, 6. H. Kaiser, T. Heller, B. Adelstein-Lelbach, A. Serio, and D. Fey. 2014. 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. ACM, 6."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"L. V. Kale and S. Krishnan. 1993. CHARM++: a portable concurrent object oriented system based on C++. Vol. 28. ACM.  L. V. Kale and S. Krishnan. 1993. CHARM++: a portable concurrent object oriented system based on C++. Vol. 28. ACM.","DOI":"10.1145\/167962.165874"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1941553.1941591"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178493"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2788396"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"J. Nickolls and I. Buck. 2007. NVIDIA CUDA software and GPU parallel computing architecture. In Microprocessor Forum.  J. Nickolls and I. Buck. 2007. NVIDIA CUDA software and GPU parallel computing architecture. In Microprocessor Forum.","DOI":"10.1109\/HOTCHIPS.2007.7482491"},{"key":"e_1_3_2_1_19_1","unstructured":"OpenACC. 2015. OpenACC: Directives for Accelerators.  OpenACC. 2015. OpenACC: Directives for Accelerators."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.53"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503285"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2043556.2043579"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522715"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2012.23"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15291-7_26"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/2220077.2220227"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.2172\/1473756"},{"key":"e_1_3_2_1_28_1","unstructured":"Wikipedia. [n. d.]. NVLink. [Online]. Available: https:\/\/en.wikipedia.org\/wiki\/NVLink. (Accessed Feb. 1 2019).  Wikipedia. [n. d.]. NVLink. [Online]. Available: https:\/\/en.wikipedia.org\/wiki\/NVLink. (Accessed Feb. 1 2019)."}],"event":{"name":"PPoPP '20: 25th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"],"location":"San Diego California","acronym":"PPoPP '20"},"container-title":["Proceedings of the 13th Annual Workshop on General Purpose Processing using Graphics Processing Unit"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3366428.3380770","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3366428.3380770","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3366428.3380770","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:32:53Z","timestamp":1750199573000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3366428.3380770"}},"subtitle":["efficient parallel programming for extremely heterogeneous systems"],"short-title":[],"issued":{"date-parts":[[2020,2,23]]},"references-count":28,"alternative-id":["10.1145\/3366428.3380770","10.1145\/3366428"],"URL":"https:\/\/doi.org\/10.1145\/3366428.3380770","relation":{},"subject":[],"published":{"date-parts":[[2020,2,23]]},"assertion":[{"value":"2020-02-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}