{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:36:06Z","timestamp":1750221366769,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,11,12]],"date-time":"2017-11-12T00:00:00Z","timestamp":1510444800000},"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":[[2017,11,12]]},"DOI":"10.1145\/3152041.3152087","type":"proceedings-article","created":{"date-parts":[[2017,10,31]],"date-time":"2017-10-31T14:58:58Z","timestamp":1509461938000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Verification of the Extended Roofline Model for Asynchronous Many Task Runtimes"],"prefix":"10.1145","author":[{"given":"Joshua","family":"Suetterlein","sequence":"first","affiliation":[{"name":"Pacific Northwest National Lab, Richland, Washington"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joshua","family":"Landwehr","sequence":"additional","affiliation":[{"name":"Trovaris, Seattle, Washington"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andres","family":"Marquez","sequence":"additional","affiliation":[{"name":"Pacific Northwest National Lab, Richland, Washington"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joseph","family":"Manzano","sequence":"additional","affiliation":[{"name":"Pacific Northwest National Lab, Richland, Washington"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin J.","family":"Barker","sequence":"additional","affiliation":[{"name":"Pacific Northwest National Lab, Richland, Washington"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guang R.","family":"Gao","sequence":"additional","affiliation":[{"name":"University of Delaware, Newark, Delaware"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2017,11,12]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"An early performance comparison","author":"Openmp","year":"2012","unstructured":"Openmp programming on Intel xeon phi tm coprocessors : An early performance comparison , Aachen , 2012 . Publikationsserver der RWTH Aachen University . Openmp programming on Intel xeon phi tm coprocessors: An early performance comparison, Aachen, 2012. Publikationsserver der RWTH Aachen University."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.71"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.77"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1155\/2013\/428078"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-06720-5_15"},{"key":"e_1_3_2_1_7_1","volume-title":"Applying the roofline performance model to the intel xeon phi knights landing processor","author":"Doerfler Douglas","year":"2016","unstructured":"Douglas Doerfler , Jack Deslippe , Samuel Williams , Leonid Oliker , Brandon Cook , Thorsten Kurth , Mathieu Lobet , Tareq Malas , Jean-Luc Vay , and Henri Vincenti . Applying the roofline performance model to the intel xeon phi knights landing processor . 2016 . Douglas Doerfler, Jack Deslippe, Samuel Williams, Leonid Oliker, Brandon Cook, Thorsten Kurth, Mathieu Lobet, Tareq Malas, Jean-Luc Vay, and Henri Vincenti. Applying the roofline performance model to the intel xeon phi knights landing processor. 2016."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2693656"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2007.370484"},{"key":"e_1_3_2_1_11_1","unstructured":"et.al. J. Landwehr. The high performance open community runtime: Explorations on asynchronous many task runtime systems. http:\/\/sc16.supercomputing.org\/sc-archive\/tech_poster\/tech_poster_pages\/post215.html 2016.  et.al. J. Landwehr. The high performance open community runtime: Explorations on asynchronous many task runtime systems. http:\/\/sc16.supercomputing.org\/sc-archive\/tech_poster\/tech_poster_pages\/post215.html 2016."},{"key":"e_1_3_2_1_12_1","first-page":"920","volume-title":"GPURoofline: A Model for Guiding Performance Optimizations on GPUs","author":"Jia Haipeng","year":"2012","unstructured":"Haipeng Jia , Yunquan Zhang , Guoping Long , Jianliang Xu , Shengen Yan , and Yan Li . GPURoofline: A Model for Guiding Performance Optimizations on GPUs , pages 920 -- 932 . Springer Berlin Heidelberg, Berlin , Heidelberg , 2012 . Haipeng Jia, Yunquan Zhang, Guoping Long, Jianliang Xu, Shengen Yan, and Yan Li. GPURoofline: A Model for Guiding Performance Optimizations on GPUs, pages 920--932. Springer Berlin Heidelberg, Berlin, Heidelberg, 2012."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPPW.2009.14"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3075564.3077425"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185475.2185478"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2016.89"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3093336.3037709"},{"key":"e_1_3_2_1_18_1","first-page":"129","volume-title":"Terry J. Ligocki, Matthew J. Cordery, Nicholas J. Wright, Mary W. Hall, and Leonid Oliker. Roofline Model Toolkit: A Practical Tool for Architectural and Program Analysis","author":"Lo Yu Jung","year":"2015","unstructured":"Yu Jung Lo , Samuel Williams , Brian Van Straalen , Terry J. Ligocki, Matthew J. Cordery, Nicholas J. Wright, Mary W. Hall, and Leonid Oliker. Roofline Model Toolkit: A Practical Tool for Architectural and Program Analysis , pages 129 -- 148 . Springer International Publishing , Cham , 2015 . Yu Jung Lo, Samuel Williams, Brian Van Straalen, Terry J. Ligocki, Matthew J. Cordery, Nicholas J. Wright, Mary W. Hall, and Leonid Oliker. Roofline Model Toolkit: A Practical Tool for Architectural and Program Analysis, pages 129--148. Springer International Publishing, Cham, 2015."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2014.6844463"},{"key":"e_1_3_2_1_21_1","first-page":"1","volume-title":"Progress in computer research","author":"Silc Jurij","year":"2001","unstructured":"Jurij Silc , Borut Robic , and Theo Ungerer . Progress in computer research . chapter Asynchrony in Parallel Computing: From Dataflow to Multithreading, pages 1 -- 33 . Nova Science Publishers, Inc. , Commack, NY, USA , 2001 . Jurij Silc, Borut Robic, and Theo Ungerer. Progress in computer research. chapter Asynchrony in Parallel Computing: From Dataflow to Multithreading, pages 1--33. Nova Science Publishers, Inc., Commack, NY, USA, 2001."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2016.191"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2016.47"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1964218.1964232"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"e_1_3_2_1_26_1","volume-title":"Fpga-roofline: An insightful model for fpga-based hardware accelerators in modern embedded systems. Master's thesis","author":"Yali Moein Pahlavan","year":"2014","unstructured":"Moein Pahlavan Yali . Fpga-roofline: An insightful model for fpga-based hardware accelerators in modern embedded systems. Master's thesis , Virginia Polytechnic Institute and State University , 12 2014 . Moein Pahlavan Yali. Fpga-roofline: An insightful model for fpga-based hardware accelerators in modern embedded systems. Master's thesis, Virginia Polytechnic Institute and State University, 12 2014."}],"event":{"name":"SC '17: The International Conference for High Performance Computing, Networking, Storage and Analysis","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","IEEE CS"],"location":"Denver CO USA","acronym":"SC '17"},"container-title":["Proceedings of the Third International Workshop on Extreme Scale Programming Models and Middleware"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3152041.3152087","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3152041.3152087","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:26:26Z","timestamp":1750213586000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3152041.3152087"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11,12]]},"references-count":23,"alternative-id":["10.1145\/3152041.3152087","10.1145\/3152041"],"URL":"https:\/\/doi.org\/10.1145\/3152041.3152087","relation":{},"subject":[],"published":{"date-parts":[[2017,11,12]]},"assertion":[{"value":"2017-11-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}