{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T05:12:55Z","timestamp":1768108375943,"version":"3.49.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/ipdpsw50202.2020.00067","type":"proceedings-article","created":{"date-parts":[[2020,7,28]],"date-time":"2020-07-28T22:51:02Z","timestamp":1595976662000},"page":"330-339","source":"Crossref","is-referenced-by-count":18,"title":["Performance Portability Evaluation of OpenCL Benchmarks across Intel and NVIDIA Platforms"],"prefix":"10.1109","author":[{"given":"Colleen","family":"Bertoni","sequence":"first","affiliation":[]},{"given":"JaeHyuk","family":"Kwack","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Applencourt","sequence":"additional","affiliation":[]},{"given":"Yasaman","family":"Ghadar","sequence":"additional","affiliation":[]},{"given":"Brian","family":"Homerding","sequence":"additional","affiliation":[]},{"given":"Christopher","family":"Knight","sequence":"additional","affiliation":[]},{"given":"Brice","family":"Videau","sequence":"additional","affiliation":[]},{"given":"Huihuo","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Vitali","family":"Morozov","sequence":"additional","affiliation":[]},{"given":"Scott","family":"Parker","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2017.08.007"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/L-CA.2013.6"},{"key":"ref13","year":"2019","journal-title":"Rodinia Web page"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2010.5650274"},{"key":"ref16","article-title":"The landscape of parallel computing research: A view from berkeley","author":"asanovic","year":"2006","journal-title":"Technical Report UCB\/EECS-2006-183 EECS Department University of Tech Rep"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2017.04.002"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3110355.3110356"},{"key":"ref19","year":"2019","journal-title":"Khronos Group Web page"},{"key":"ref4","year":"2019","journal-title":"khronos OpenCL web page"},{"key":"ref3","year":"0","journal-title":"Frontier"},{"key":"ref6","year":"0","journal-title":"OpenAccess"},{"key":"ref5","article-title":"The OpenMP API specification for parallel programming","year":"0"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/P3HPC.2018.00005"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2014.07.003"},{"key":"ref2","year":"0","journal-title":"Permutter"},{"key":"ref9","first-page":"7409","article-title":"A metric for performance portability","volume":"abs","author":"pennycook","year":"2016","journal-title":"ArXiv"},{"key":"ref1","year":"0","journal-title":"Aurora"},{"key":"ref20","year":"2019","journal-title":"Empirical Roofline Tool Web page"},{"key":"ref22","year":"0","journal-title":"Intel VTune Amplifier"},{"key":"ref21","first-page":"489","article-title":"Gpustream v2.0: Benchmarking the achievable memory bandwidth of manycore processors across diverse parallel programming models","author":"deakin","year":"2016","journal-title":"High Performance Computing"},{"key":"ref24","year":"0","journal-title":"Intel Software Development Emulator"},{"key":"ref23","year":"0","journal-title":"Intercept Layer for OpenCL Applications"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/pharmaceutics9020014"},{"key":"ref25","year":"0","journal-title":"Measuring arithmetic intensity"}],"event":{"name":"2020 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","location":"New Orleans, LA, USA","start":{"date-parts":[[2020,5,18]]},"end":{"date-parts":[[2020,5,22]]}},"container-title":["2020 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9142309\/9150133\/09150432.pdf?arnumber=9150432","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,9]],"date-time":"2022-07-09T02:21:51Z","timestamp":1657333311000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9150432\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/ipdpsw50202.2020.00067","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}