{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T23:52:36Z","timestamp":1773273156291,"version":"3.50.1"},"reference-count":37,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,4]]},"DOI":"10.1109\/ispass.2017.7975269","type":"proceedings-article","created":{"date-parts":[[2017,7,13]],"date-time":"2017-07-13T20:47:13Z","timestamp":1499978833000},"page":"43-54","source":"Crossref","is-referenced-by-count":56,"title":["Chai: Collaborative heterogeneous applications for integrated-architectures"],"prefix":"10.1109","author":[{"given":"Juan","family":"Gomez-Luna","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Izzat El","family":"Hajj","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li-Wen","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Victor","family":"Garcia-Flores","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon Garcia","family":"de Gonzalo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas B.","family":"Jablin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonio J.","family":"Pena","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen-mei","family":"Hwu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830818"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2017.7863729"},{"key":"ref31","first-page":"1","article-title":"Evaluating the effect of last-level cache sharing on integrated GPU-CPU systems with heterogeneous applications","author":"garcia-flores","year":"2016","journal-title":"Proc of the IEEE International Symposium on Workload Characterization"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2903150.2903152"},{"key":"ref37","author":"tang","year":"0","journal-title":"Controlled kernel launch for dynamic parallelism in GPUs"},{"key":"ref36","first-page":"1","article-title":"KLAP: Kernel launch aggregation and promotion for optimizing dynamic parallelism","author":"el hajj","year":"2016","journal-title":"The 49th Annual IEEE\/ACM International Symposium on Microarchitecture 2016"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2016.98"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2872887.2750393"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2016.7581262"},{"key":"ref11","first-page":"5:1","article-title":"Exploring the features of OpenCL 2.0","author":"mukherjee","year":"2015","journal-title":"Proceedings of the 3rd International Workshop on OpenCL"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2016.7482093"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2015.40"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"ref15","first-page":"210","article-title":"In-place data sliding algorithms for many-core architectures","author":"luna","year":"2015","journal-title":"44th International Conference on Parallel Processing"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339606"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2010.5470413"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1837274.1837289"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s00450-012-0209-1"},{"key":"ref4","article-title":"Parboil: A revised benchmark suite for scientific and commercial throughput computing","author":"stratton","year":"2012","journal-title":"IMPACT Technical Report"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2212908.2212924"},{"key":"ref3","article-title":"CUDA C programming guide v. 8.0","year":"2016","journal-title":"Nvidia"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1735688.1735702"},{"key":"ref29","first-page":"1","article-title":"Understanding co-run performance on CPU-GPU integrated processors: observations, insights, directions","author":"zhu","year":"2016","journal-title":"Frontiers of Computer Science"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2012.6402918"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2668930.2688046"},{"key":"ref2","article-title":"The OpenCL specification","year":"2015","journal-title":"Version 2 0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2458523.2458529"},{"key":"ref1","author":"hwu","year":"2015","journal-title":"Heterogeneous System Architecture A new compute platform infrastructure"},{"key":"ref20","article-title":"gem5-gpu: A heterogeneous CPU-GPU simulator","volume":"13","author":"power","year":"2014","journal-title":"Computer Architecture Letters"},{"key":"ref22","article-title":"App profiler settings","year":"0","journal-title":"AMD"},{"key":"ref21","article-title":"ROCm: Platform for GPU enabled HPC and ultrascale computing","year":"2016","journal-title":"RadeonOpenCompute"},{"key":"ref24","article-title":"Memory system on Fusion APUs. The benefits of zero copy","year":"2011","journal-title":"AMD"},{"key":"ref23","author":"kelley","year":"0"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2014.6983050"},{"key":"ref25","article-title":"Compile problem","year":"2016","journal-title":"bshaozi"}],"event":{"name":"2017 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","location":"Santa Rosa, CA","start":{"date-parts":[[2017,4,24]]},"end":{"date-parts":[[2017,4,25]]}},"container-title":["2017 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7965804\/7975258\/07975269.pdf?arnumber=7975269","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,2,2]],"date-time":"2020-02-02T11:26:42Z","timestamp":1580642802000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7975269\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,4]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/ispass.2017.7975269","relation":{},"subject":[],"published":{"date-parts":[[2017,4]]}}}