{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,3,30]],"date-time":"2022-03-30T16:53:25Z","timestamp":1648659205381},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2018,7,1]],"date-time":"2018-07-01T00:00:00Z","timestamp":1530403200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Topics Comput."],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1109\/tetc.2016.2546554","type":"journal-article","created":{"date-parts":[[2016,4,5]],"date-time":"2016-04-05T20:08:25Z","timestamp":1459886905000},"page":"382-394","source":"Crossref","is-referenced-by-count":0,"title":["Pro++: A Profiling Framework for Primitive-Based GPU Programming"],"prefix":"10.1109","volume":"6","author":[{"given":"Nicola","family":"Bombieri","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Federico","family":"Busato","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Franco","family":"Fummi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","author":"malcolm","year":"2014","journal-title":"Arrayfire a gpu acceleration platform"},{"key":"ref38","author":"baxter","year":"2014","journal-title":"Modern GPU"},{"key":"ref33","first-page":"1","article-title":"Inter-block GPU communication via fast barrier synchronization","author":"xiao","year":"2010","journal-title":"Proc IEEE Int Symp Parallel Distrib Process"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2330597"},{"key":"ref31","author":"cheng","year":"2014","journal-title":"Professional CUDA C Programming"},{"key":"ref30","author":"kirk","year":"2012","journal-title":"Programming Massively Parallel Processors A Hands-on Approach"},{"key":"ref37","author":"harris","year":"2014","journal-title":"CUDPP CUDA Data Parallel Primitives Library"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1572769.1572795"},{"key":"ref35","author":"merrill","year":"2015","journal-title":"CUB"},{"key":"ref34","author":"hoberock","year":"2014","journal-title":"Thrust A Parallel Template Library"},{"key":"ref10","year":"2016","journal-title":"Software\/Hardware Generation for DSP Algorithms"},{"key":"ref40","author":"ruetsch","year":"2016","journal-title":"Optimizing Matrix Transpose in CUDA"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2329494"},{"key":"ref12","year":"2016","journal-title":"GPU-Accelerated Libraries"},{"key":"ref13","year":"2016","journal-title":"CLPP-OpenCL"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MCSoC.2015.16"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2308216"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICPPW.2012.59"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.2853"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.3217"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1555815.1555775"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ISPA.2011.36"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.7873\/DATE.2013.279"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1735688.1735696"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CODES-ISSS.2013.6658999"},{"key":"ref6","year":"2016","journal-title":"Directives for Accelerators"},{"key":"ref29","year":"2016","journal-title":"CUDA C Best Practice Guide"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2228360.2228382"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MCSoC.2013.31"},{"key":"ref7","first-page":"1","article-title":"HMPP: A hybrid multi-core parallel programming environment","author":"dolbeau","year":"2007","journal-title":"Proc Workshop General Purpose Process Graph Process Units (GPGPU)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/PADSW.2014.7097850"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2584665"},{"key":"ref1","year":"2016","journal-title":"Harmonizing the Industry Around Heterogeneous Computing"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/HIPC.2009.5433179"},{"key":"ref22","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":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2145816.2145819"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOTS.2010.43"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2012.6507475"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1145\/2370816.2370865","article-title":"Multi2Sim: A Simulation Framework for CPU-GPU Computing","author":"rafael ubal","year":"2012","journal-title":"In International Conference on Parallel Architectures and Compilation Techniques (PACT)"}],"container-title":["IEEE Transactions on Emerging Topics in Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6245516\/8453960\/07447754.pdf?arnumber=7447754","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T10:45:58Z","timestamp":1643193958000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7447754\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":40,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tetc.2016.2546554","relation":{},"ISSN":["2168-6750","2376-4562"],"issn-type":[{"value":"2168-6750","type":"electronic"},{"value":"2376-4562","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,7]]}}}