{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T11:48:30Z","timestamp":1763466510520,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2014,10,6]],"date-time":"2014-10-06T00:00:00Z","timestamp":1412553600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2014,10,6]]},"DOI":"10.1145\/2676870.2676881","type":"proceedings-article","created":{"date-parts":[[2015,1,5]],"date-time":"2015-01-05T13:32:15Z","timestamp":1420464735000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Native Mode-Based Optimizations of Remote Memory Accesses in OpenSHMEM for Intel Xeon Phi"],"prefix":"10.1145","author":[{"given":"Naveen","family":"Namashivayam","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Houston, Houston, Texas"}]},{"given":"Sayan","family":"Ghosh","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Houston, Houston, Texas"}]},{"given":"Dounia","family":"Khaldi","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Houston, Houston, Texas"}]},{"given":"Deepak","family":"Eachempati","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Houston, Houston, Texas"}]},{"given":"Barbara","family":"Chapman","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Houston, Houston, Texas"}]}],"member":"320","published-online":{"date-parts":[[2014,10,6]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"HPCTools PGAS-Microbenchmarks. https:\/\/github.com\/uhhpctools\/pgas-microbench.  HPCTools PGAS-Microbenchmarks. https:\/\/github.com\/uhhpctools\/pgas-microbench."},{"key":"e_1_3_2_1_2_1","unstructured":"OpenSHMEM NAS Parallel Benchmarks Version 1.0a. http:\/\/www.openshmem.org\/site\/Downloads\/Examples.  OpenSHMEM NAS Parallel Benchmarks Version 1.0a. http:\/\/www.openshmem.org\/site\/Downloads\/Examples."},{"key":"e_1_3_2_1_3_1","unstructured":"OSU Micro-benchmarks. http:\/\/mvapich.cse.ohio-state.edu\/benchmarks\/.  OSU Micro-benchmarks. http:\/\/mvapich.cse.ohio-state.edu\/benchmarks\/."},{"key":"e_1_3_2_1_4_1","unstructured":"STAMPEDE - Dell PowerEdge C8220 Cluster with Intel Xeon Phi coprocessors. http:\/\/www.tacc.utexas.edu\/resources\/hpc.  STAMPEDE - Dell PowerEdge C8220 Cluster with Intel Xeon Phi coprocessors. http:\/\/www.tacc.utexas.edu\/resources\/hpc."},{"key":"e_1_3_2_1_5_1","volume-title":"http:\/\/upc.gwu.edu\/documentation.html","author":"Application Programming SHMEM","year":"2012","unstructured":"Open SHMEM Application Programming Interface (version 1.0). http:\/\/upc.gwu.edu\/documentation.html , 2012 . OpenSHMEM Application Programming Interface (version 1.0). http:\/\/upc.gwu.edu\/documentation.html, 2012."},{"key":"e_1_3_2_1_6_1","volume-title":"NAS Parallel Benchmarks","author":"Bailey David H","year":"2011","unstructured":"David H Bailey . NAS Parallel Benchmarks . Springer , 2011 . David H Bailey. NAS Parallel Benchmarks. Springer, 2011."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.642949"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2020373.2020375"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-012-0230-9"},{"key":"e_1_3_2_1_10_1","first-page":"38","volume-title":"Mey. OpenMP Programming on Intel Xeon Phi Coprocessors: An Early Performance Comparison. In Proceedings of the Many-core Applications Research Community (MARC) Symposium at RWTH Aachen University","author":"Cramer T.","year":"2012","unstructured":"T. Cramer , D. Schmidl , M. Klemm , and D. an Mey. OpenMP Programming on Intel Xeon Phi Coprocessors: An Early Performance Comparison. In Proceedings of the Many-core Applications Research Community (MARC) Symposium at RWTH Aachen University , pages 38 -- 44 , November 2012 . T. Cramer, D. Schmidl, M. Klemm, and D. an Mey. OpenMP Programming on Intel Xeon Phi Coprocessors: An Early Performance Comparison. In Proceedings of the Many-core Applications Research Community (MARC) Symposium at RWTH Aachen University, pages 38--44, November 2012."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.v22:6"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-05215-1_4"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2493123.2462903"},{"key":"e_1_3_2_1_14_1","volume-title":"Panda. UPC on MIC: Early Experiences with Native and Symmetric Modes. In PGAS '13: Proceedings of the Seventh Conference on Partitioned Global Address Space Programing Models. ACM","author":"Luo Miao","year":"2013","unstructured":"Miao Luo , Mingzhe Li , Akshay Venkatesh , Xiaoyi Lu , and Dhabaleswar K . Panda. UPC on MIC: Early Experiences with Native and Symmetric Modes. In PGAS '13: Proceedings of the Seventh Conference on Partitioned Global Address Space Programing Models. ACM , 2013 . Miao Luo, Mingzhe Li, Akshay Venkatesh, Xiaoyi Lu, and Dhabaleswar K. Panda. UPC on MIC: Early Experiences with Native and Symmetric Modes. In PGAS '13: Proceedings of the Seventh Conference on Partitioned Global Address Space Programing Models. ACM, 2013."},{"volume-title":"STREAM: Sustainable Memory Bandwidth in High Performance Computers. Technical report","author":"McCalpin J. D.","key":"e_1_3_2_1_15_1","unstructured":"J. D. McCalpin . STREAM: Sustainable Memory Bandwidth in High Performance Computers. Technical report , University of Virginia , {Online}. Available: http:\/\/www.cs.virginia.edu\/stream\/, 1991-2007. J. D. McCalpin. STREAM: Sustainable Memory Bandwidth in High Performance Computers. Technical report, University of Virginia, {Online}. Available: http:\/\/www.cs.virginia.edu\/stream\/, 1991-2007."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/289918.289920"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503288"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2493123.2462916"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/XSW.2013.8"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1007\/978-3-540-39924-7_38","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface. Number 2840 in LNCS","author":"Thakur Rajeev","year":"2003","unstructured":"Rajeev Thakur . Improving the Performance of Collective Operations in MPICH . In Recent Advances in Parallel Virtual Machine and Message Passing Interface. Number 2840 in LNCS , Springer Verlag ( 2003 ) 257--267 10th European PVM\/MPI User's Group Meeting, pages 257 -- 267 . Springer Verlag , 2003. Rajeev Thakur. Improving the Performance of Collective Operations in MPICH. In Recent Advances in Parallel Virtual Machine and Message Passing Interface. Number 2840 in LNCS, Springer Verlag (2003) 257--267 10th European PVM\/MPI User's Group Meeting, pages 257--267. Springer Verlag, 2003."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005051521"},{"key":"e_1_3_2_1_22_1","first-page":"10","volume-title":"Panda. Fast Collective Operations Using Shared and Remote Memory Access Protocols on Clusters. In Parallel and Distributed Processing Symposium, 2003. Proceedings. International","author":"Tipparaju V.","year":"2003","unstructured":"V. Tipparaju , Jarek Nieplocha , and Dhabaleswar K . Panda. Fast Collective Operations Using Shared and Remote Memory Access Protocols on Clusters. In Parallel and Distributed Processing Symposium, 2003. Proceedings. International , pages 10 pp.--, April 2003 . V. Tipparaju, Jarek Nieplocha, and Dhabaleswar K. Panda. Fast Collective Operations Using Shared and Remote Memory Access Protocols on Clusters. In Parallel and Distributed Processing Symposium, 2003. Proceedings. International, pages 10 pp.--, April 2003."}],"event":{"name":"PGAS '14: 8th International Conference on Partitioned Global Address Space Programming Models","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","University of Oregon University of Oregon"],"location":"Eugene OR USA","acronym":"PGAS '14"},"container-title":["Proceedings of the 8th International Conference on Partitioned Global Address Space Programming Models"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2676870.2676881","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2676870.2676881","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T06:11:56Z","timestamp":1750227116000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2676870.2676881"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,10,6]]},"references-count":22,"alternative-id":["10.1145\/2676870.2676881","10.1145\/2676870"],"URL":"https:\/\/doi.org\/10.1145\/2676870.2676881","relation":{},"subject":[],"published":{"date-parts":[[2014,10,6]]},"assertion":[{"value":"2014-10-06","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}