{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:09:40Z","timestamp":1750306180824,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2016,9,11]],"date-time":"2016-09-11T00:00:00Z","timestamp":1473552000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"ERC Advanced Grant","award":["GA 321253"],"award-info":[{"award-number":["GA 321253"]}]},{"name":"FP7\/2007-2013","award":["610402","2013 BP_B 00243"],"award-info":[{"award-number":["610402","2013 BP_B 00243"]}]},{"name":"H2020\/2014-2020","award":["671697"],"award-info":[{"award-number":["671697"]}]},{"name":"Spanish Ministry of Science and Innovation","award":["TIN2015-65316-P"],"award-info":[{"award-number":["TIN2015-65316-P"]}]},{"name":"Severo Ochoa","award":["SEV2015-0493"],"award-info":[{"award-number":["SEV2015-0493"]}]},{"name":"Generalitat de Catalunya","award":["2014-SGR-1051 and 2014-SGR-1272"],"award-info":[{"award-number":["2014-SGR-1051 and 2014-SGR-1272"]}]},{"name":"Spanish Ministry of Economy and Competitiveness","award":["JCI-2012-15047"],"award-info":[{"award-number":["JCI-2012-15047"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2016,9,11]]},"DOI":"10.1145\/2967938.2967962","type":"proceedings-article","created":{"date-parts":[[2016,8,31]],"date-time":"2016-08-31T12:32:08Z","timestamp":1472646728000},"page":"275-286","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Reducing Cache Coherence Traffic with Hierarchical Directory Cache and NUMA-Aware Runtime Scheduling"],"prefix":"10.1145","author":[{"given":"Paul","family":"Caheny","sequence":"first","affiliation":[{"name":"Barcelona Supercomputing Center, Barcelona, Spain"}]},{"given":"Marc","family":"Casas","sequence":"additional","affiliation":[{"name":"Barcelona Supercomputing Center, Barcelona, Spain"}]},{"given":"Miquel","family":"Moret\u00f3","sequence":"additional","affiliation":[{"name":"Barcelona Supercomputing Center, Barcelona, Spain"}]},{"given":"Herv\u00e9","family":"Gloaguen","sequence":"additional","affiliation":[{"name":"Bull Atos Technologies, Les Clayes-sousBois, France"}]},{"given":"Maxime","family":"Saintes","sequence":"additional","affiliation":[{"name":"Bull Atos Technologies, Les Clayes-sous-Bois, France"}]},{"given":"Eduard","family":"Ayguad\u00e9","sequence":"additional","affiliation":[{"name":"Barcelona Supercomputing Center, Barcelona, Spain"}]},{"given":"Jes\u00fas","family":"Labarta","sequence":"additional","affiliation":[{"name":"Barcelona Supercomputing Center, Barcelona, Spain"}]},{"given":"Mateo","family":"Valero","sequence":"additional","affiliation":[{"name":"Barcelona Supercomputing Center, Barcelona, Spain"}]}],"member":"320","published-online":{"date-parts":[[2016,9,11]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Data center optimization with bullion. 2015.  Data center optimization with bullion. 2015."},{"key":"e_1_3_2_1_2_1","volume-title":"Dense matrix computations on NUMA architectures with distance-aware work stealing. Supercomputing Frontiers and Innovations, 2(1)","author":"Al-Omairy R.","year":"2015","unstructured":"R. Al-Omairy , G. Miranda , H. Ltaief , R. Badia , X. Martorell , J. Labarta , and D. Keyes . Dense matrix computations on NUMA architectures with distance-aware work stealing. Supercomputing Frontiers and Innovations, 2(1) , 2015 . R. Al-Omairy, G. Miranda, H. Ltaief, R. Badia, X. Martorell, J. Labarta, and D. Keyes. Dense matrix computations on NUMA architectures with distance-aware work stealing. Supercomputing Frontiers and Innovations, 2(1), 2015."},{"key":"e_1_3_2_1_3_1","first-page":"103","volume-title":"European Workshop on OpenMP, EWOMP '04","author":"Balart J.","year":"2004","unstructured":"J. Balart , A. Duran , M. Gonz\u00e7alez , X. Martorell , E. Ayguad\u00e9 , and J. Labarta . Nanos mercurium: a research compiler for openmp . In European Workshop on OpenMP, EWOMP '04 , pages 103 -- 109 , 2004 . J. Balart, A. Duran, M. Gonz\u00e7alez, X. Martorell, E. Ayguad\u00e9, and J. Labarta. Nanos mercurium: a research compiler for openmp. In European Workshop on OpenMP, EWOMP '04, pages 103--109, 2004."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454128"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2464996.2465017"},{"key":"e_1_3_2_1_6_1","volume-title":"Programming with POSIX Threads","author":"Butenhof D. R.","year":"1997","unstructured":"D. R. Butenhof . Programming with POSIX Threads . Addison-Wesley Longman Publishing Co., Inc. , Boston, MA, USA , 1997 . D. R. Butenhof. Programming with POSIX Threads. Addison-Wesley Longman Publishing Co., Inc., Boston, MA, USA, 1997."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522319"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-48096-0_2"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2011.21"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2641764"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0129626411000151"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSD.2014.15"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669165"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/998680.1006711"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555774"},{"key":"e_1_3_2_1_16_1","volume-title":"Weaving high performance multiprocessor fabric: architectural insights into the Intel QuickPath Interconnect","author":"Maddox R.","year":"2009","unstructured":"R. Maddox , G. Singh , and R. Safranek . Weaving high performance multiprocessor fabric: architectural insights into the Intel QuickPath Interconnect . Intel Press , 2009 . R. Maddox, G. Singh, and R. Safranek. Weaving high performance multiprocessor fabric: architectural insights into the Intel QuickPath Interconnect. Intel Press, 2009."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2013.64"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.71"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2209249.2209269"},{"key":"e_1_3_2_1_20_1","first-page":"19","volume-title":"IEEE Computer Society Technical Committee on Computer Architecture (TCCA) Newsletter","author":"McCalpin J.","year":"1995","unstructured":"J. McCalpin . Memory bandwidth and machine balance in current high performance computers . IEEE Computer Society Technical Committee on Computer Architecture (TCCA) Newsletter , pages 19 -- 25 , December 1995 . J. McCalpin. Memory bandwidth and machine balance in current high performance computers. IEEE Computer Society Technical Committee on Computer Architecture (TCCA) Newsletter, pages 19--25, December 1995."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2009.22"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40698-0_12"},{"volume-title":"Application program interface, version 4.0","year":"2013","key":"e_1_3_2_1_23_1","unstructured":"OpenMP : Application program interface, version 4.0 . 2013 . OpenMP: Application program interface, version 4.0. 2013."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1393921.1393988"},{"key":"e_1_3_2_1_25_1","volume-title":"Computer Architecture: A Quantitative Approach","author":"Patterson D.","year":"1990","unstructured":"D. Patterson and J. Hennessy . Computer Architecture: A Quantitative Approach . Morgan Kaufmann Publishers Inc ., San Francisco, CA, USA, 1990 . D. Patterson and J. Hennessy. Computer Architecture: A Quantitative Approach. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 1990."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2010.79"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.14529\/jsfi140102"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24595-9_5"},{"key":"e_1_3_2_1_29_1","volume-title":"Intel memory latency checker v2","author":"Viswanathan V.","year":"2013","unstructured":"V. Viswanathan , K. Kumar , and T. Willhalm . Intel memory latency checker v2 , 2013 . V. Viswanathan, K. Kumar, and T. Willhalm. Intel memory latency checker v2, 2013."}],"event":{"name":"PACT '16: International Conference on Parallel Architectures and Compilation","sponsor":["IFIP WG 10.3 IFIP WG 10.3","IEEE TCCA IEEE Computer Society Technical Committee on Computer Architecture","SIGARCH ACM Special Interest Group on Computer Architecture","IEEE CS TCPP IEEE Computer Society Technical Committee on Parallel Processing"],"location":"Haifa Israel","acronym":"PACT '16"},"container-title":["Proceedings of the 2016 International Conference on Parallel Architectures and Compilation"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2967938.2967962","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2967938.2967962","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:49:59Z","timestamp":1750218599000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2967938.2967962"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,9,11]]},"references-count":29,"alternative-id":["10.1145\/2967938.2967962","10.1145\/2967938"],"URL":"https:\/\/doi.org\/10.1145\/2967938.2967962","relation":{},"subject":[],"published":{"date-parts":[[2016,9,11]]},"assertion":[{"value":"2016-09-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}