{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T01:58:03Z","timestamp":1769824683609,"version":"3.49.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"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":[[2019,10]]},"DOI":"10.1109\/ipccc47392.2019.8958760","type":"proceedings-article","created":{"date-parts":[[2020,1,17]],"date-time":"2020-01-17T02:04:32Z","timestamp":1579226672000},"page":"1-8","source":"Crossref","is-referenced-by-count":7,"title":["GPUs Cache Performance Estimation using Reuse Distance Analysis"],"prefix":"10.1109","author":[{"given":"Yehia","family":"Arafa","sequence":"first","affiliation":[]},{"given":"Gopinath","family":"Chennupati","sequence":"additional","affiliation":[]},{"given":"Atanu","family":"Barai","sequence":"additional","affiliation":[]},{"given":"Abdel-Hameed A.","family":"Badawy","sequence":"additional","affiliation":[]},{"given":"Nandakishore","family":"Santhi","sequence":"additional","affiliation":[]},{"given":"Stephan","family":"Eidenbenz","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/PCCC.2016.7820638"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1145\/1854273.1854318","article-title":"Ocelot: A dynamic optimization framework for bulk-synchronous applications in heterogeneous systems","author":"diamos","year":"2010","journal-title":"Proceedings of the 19th International Conference on Parallel Architectures and Compilation Techniques (PACT)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2017.2695178"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/PCCC.2017.8280444"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1993744.1993748"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2010.5470780"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2011.16"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3316480.3325518"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2004.1291352"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/782814.782836"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750375"},{"key":"ref11","year":"2018","journal-title":"Cuda toolkit documentation v9 1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339595"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"ref14","year":"2014","journal-title":"NVIDIA Visual Profiler User's Guide"},{"key":"ref15","year":"2014","journal-title":"NVIDIAMaxwell GPU Architecture"},{"key":"ref16","year":"2018","journal-title":"CUDA Programming Guide"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2010.69"},{"key":"ref18","author":"brehob","year":"1999","journal-title":"An Analytical Model of Locality and Caching"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WSC.2017.8247842"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1065895.1065906"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.2013.6691165"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/781131.781159"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751237"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2145816.2145820"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1552309.1552310"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835955"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2012.328"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2716282.2716291"},{"key":"ref9","first-page":"617","article-title":"Reuse distance as a metric for cache behavior","author":"beyls","year":"2001","journal-title":"Proceedings of the IASTED Conference on Parallel and Distributed Computing and Systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2019.8916466"},{"key":"ref20","first-page":"114","article-title":"A scalable analytical memory model for CPU performance prediction","author":"chennupati","year":"2017","journal-title":"Proceedings of the second international workshop on Performance modeling, benchmarking and simulation of high performance computing systems - PMBS '11"},{"key":"ref22","article-title":"Dissecting the NVIDIA volta GPU architecture via microbenchmarking","volume":"abs 1804 6826","author":"jia","year":"2018","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2019.2904497"},{"key":"ref24","author":"cheng","year":"2014","journal-title":"Professional CUDA C Programming"},{"key":"ref23","year":"2012","journal-title":"Kepler GPU Architecture"},{"key":"ref26","author":"wang","year":"2015","journal-title":"Mitigating gpu memory divergence for data-intensive applications"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3291051"}],"event":{"name":"2019 IEEE 38th International Performance Computing and Communications Conference (IPCCC)","location":"London, UK","start":{"date-parts":[[2019,10,29]]},"end":{"date-parts":[[2019,10,31]]}},"container-title":["2019 IEEE 38th International Performance Computing and Communications Conference (IPCCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8955479\/8958711\/08958760.pdf?arnumber=8958760","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T20:23:04Z","timestamp":1658262184000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8958760\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/ipccc47392.2019.8958760","relation":{},"subject":[],"published":{"date-parts":[[2019,10]]}}}