{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T06:32:22Z","timestamp":1729665142728,"version":"3.28.0"},"reference-count":36,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,4]]},"DOI":"10.1109\/ispass.2016.7482093","type":"proceedings-article","created":{"date-parts":[[2016,6,2]],"date-time":"2016-06-02T17:06:06Z","timestamp":1464887166000},"page":"183-193","source":"Crossref","is-referenced-by-count":24,"title":["A comprehensive performance analysis of HSA and OpenCL 2.0"],"prefix":"10.1109","author":[{"given":"Saoni","family":"Mukherjee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paul","family":"Blinzer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amir Kavyan","family":"Ziabari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Kaeli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","first-page":"51","article-title":"Viennacl-a high level linear algebra library for gpus and multi-core cpus","author":"rupp","year":"2010","journal-title":"Proc GPUScA"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2013.7478286"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"1075","DOI":"10.1002\/j.1538-7305.1983.tb03115.x","article-title":"On the application of vector quantization and hidden Markov models to speaker-independent, isolated word recognition","volume":"62","author":"lawrence","year":"1983","journal-title":"Bell System Technical Journal the"},{"journal-title":"Polybench benchmark","year":"0","author":"pouchet","key":"ref30"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICPPW.2014.59"},{"key":"ref35","article-title":"Parboil: A revised benchmark suite for scientific and commercial throughput computing","author":"john","year":"2012","journal-title":"Center for Reliable and High-Performance Computing"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1109\/MCSE.2010.69","article-title":"OpenCL: A parallel programming standard for heterogeneous computing systems","volume":"12","author":"john","year":"2010","journal-title":"Computing in Science & Engineering"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2188286.2188341"},{"article-title":"Heterogeneous Computing with OpenCL","year":"2011","author":"benedict","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5213922"},{"journal-title":"Khronos OpenCL Working Group","article-title":"The OpenCL Specification Version 2.0","year":"2013","key":"ref13"},{"journal-title":"The HSA Foundation","year":"0","key":"ref14"},{"article-title":"Heterogeneous Systems Architecture: A New Compute Platform Infrastructure","year":"2015","author":"hwu","key":"ref15"},{"journal-title":"ISO Jtc SC22\/WG14 ISO\/IEC 9899","article-title":"Information technology - Programming languages - C","year":"2011","key":"ref16"},{"article-title":"Heterogeneous Computing with OpenCL 2.0","year":"2015","author":"kaeli","key":"ref17"},{"journal-title":"Khronos Group","year":"0","key":"ref18"},{"key":"ref19","article-title":"Heterogeneous system architecture: A technical review","author":"kyriazis","year":"2012","journal-title":"AMD Fusion Developer Summit"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11331-9_60"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177699147"},{"key":"ref27","article-title":"Signals and systems","volume":"2","author":"alan","year":"1983"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1007\/s11390-014-1439-4","article-title":"Harnessing the Power of GPUs to Speed Up Feature Selection for Outlier Detection","volume":"29","author":"fatemeh","year":"2014","journal-title":"Journal of Computer Science and Technology"},{"year":"0","key":"ref6","article-title":"CLBench - The first professional OpenCL benchmark for measuring and comparing the processing power of different hardware architectures"},{"key":"ref29","article-title":"A course in digital signal processing","volume":"1","author":"porat","year":"1997"},{"key":"ref5","first-page":"44","article-title":"Rodinia: A benchmark suite for heterogeneous computing","author":"shuai","year":"2009","journal-title":"Workload Characterization 2009 IISWC 2009 IEEE International Symposium on"},{"key":"ref8","first-page":"63","article-title":"The scalable heterogeneous computing (shoc) benchmark suite","author":"anthony","year":"2010","journal-title":"Proceedings of the 3rd Workshop on General-Purpose Computation on Graphics Processing Units"},{"journal-title":"CLOC","year":"0","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2858788.2688521"},{"journal-title":"Advanced Micro Devices","article-title":"Kaveri OpenCL Programmer Guide","year":"0","key":"ref9"},{"journal-title":"Luxmark benchmark","year":"0","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2726935.2726940"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2012.6408674"},{"key":"ref21","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume":"1","author":"macqueen","year":"1967","journal-title":"Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2791321.2791331"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2013.6691571"},{"journal-title":"OpenCL Benchmarks","year":"0","key":"ref26"},{"journal-title":"CUDA Nvidia","article-title":"Compute unified device architecture programming guide","year":"2007","key":"ref25"}],"event":{"name":"2016 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","start":{"date-parts":[[2016,4,17]]},"location":"Uppsala, Sweden","end":{"date-parts":[[2016,4,19]]}},"container-title":["2016 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7480598\/7482062\/07482093.pdf?arnumber=7482093","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,24]],"date-time":"2017-06-24T15:36:17Z","timestamp":1498318577000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7482093\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,4]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/ispass.2016.7482093","relation":{},"subject":[],"published":{"date-parts":[[2016,4]]}}}