{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T16:28:13Z","timestamp":1730219293085,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"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":[[2019,2]]},"DOI":"10.1109\/empdp.2019.8671606","type":"proceedings-article","created":{"date-parts":[[2019,3,22]],"date-time":"2019-03-22T02:40:56Z","timestamp":1553222456000},"page":"260-265","source":"Crossref","is-referenced-by-count":1,"title":["The Pipeline Performance Model: A Generic Executable Performance Model for GPUs"],"prefix":"10.1109","author":[{"given":"Jan G.","family":"Cornelis","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"Lemeire","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2011.5749745"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.59"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2017.7926956"},{"key":"ref13","article-title":"Analyzing CUDA workloads using a detailed GPU simulator","author":"ali","year":"2009","journal-title":"IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)"},{"key":"ref14","article-title":"Benchmarks based on anti-parallel patterns for the evaluation of GPUs","author":"cornelis","year":"2011","journal-title":"PARCO"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2015.7095801"},{"journal-title":"Understanding Latency Hiding on GPUs","year":"2016","author":"volkov","key":"ref16"},{"journal-title":"Computer Architecture A Quantitative Approach The Morgan Kaufmann Series in Computer Architecture and Design","year":"2017","author":"hennessy","key":"ref17"},{"journal-title":"CUDA C Programming guide NVIDIA Corporation","year":"2018","key":"ref18"},{"journal-title":"AMD GRAPHICS CORES NEXT (GCN) ARCHI-TECTURE AMD Corporation","year":"2012","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32820-6_90"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/PDP.2015.51"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2212908.2212937"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1837853.1693470"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555775"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2010.69"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1365490.1365500"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2370036.2145819"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/PDP.2016.120"},{"key":"ref21","article-title":"The program dependence graph and its use in optimization","volume":"9","author":"jeanne","year":"1987","journal-title":"ACM Trans Program Lang Syst"}],"event":{"name":"2019 27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)","start":{"date-parts":[[2019,2,13]]},"location":"Pavia, Italy","end":{"date-parts":[[2019,2,15]]}},"container-title":["2019 27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8663972\/8671541\/08671606.pdf?arnumber=8671606","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T20:20:18Z","timestamp":1658262018000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8671606\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/empdp.2019.8671606","relation":{},"subject":[],"published":{"date-parts":[[2019,2]]}}}