{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:21:54Z","timestamp":1730298114034,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,6]]},"DOI":"10.1109\/snpd.2015.7176173","type":"proceedings-article","created":{"date-parts":[[2015,8,12]],"date-time":"2015-08-12T18:38:15Z","timestamp":1439404695000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Evaluation of global synchronization for iterative algebra algorithms on many-core"],"prefix":"10.1109","author":[{"given":"Ayaz","family":"ul Hasan Khan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mayez","family":"Al-Mouhamed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lutfi A.","family":"Firdaus","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Collective Communication and Barrier Synchronization on NVIDIA CUDA GPUs","year":"2009","author":"rivera-polanco","key":"ref10"},{"journal-title":"Programming Massively Parallel Processors A Hands-on Approach","year":"2010","author":"kirk","key":"ref11"},{"journal-title":"Intel Xeon Phi Coprocessor Instruction Set Architecture Reference Manual","year":"2012","key":"ref12"},{"journal-title":"Intel Knights Corner Software Developer Guide","year":"2012","key":"ref13"},{"journal-title":"An Overview of Programming for Intel Xeon Processors and Intel Xeon Phi Coprocessors","year":"2012","author":"reinders","key":"ref14"},{"article-title":"Optimizing Parallel Reduction in CUDA","year":"2008","author":"harris","key":"ref15"},{"key":"ref16","article-title":"Algorithmic strategies for optimizing the parallel reduction primitive in CUDA","author":"martin","year":"0","journal-title":"HPCS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1375527.1375559"},{"key":"ref18","first-page":"324327","article-title":"Implementation of Jacobi iterative method on graphics processor unit","author":"wang","year":"2009","journal-title":"Computational Intelligence and Intelligent Systems"},{"key":"ref19","first-page":"259262","article-title":"CUDA-based Jacobi iterative method","author":"zhang","year":"2009","journal-title":"IFCSTA International Forum on Computer Science-Technology and Applications"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77220-0_21"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1360612.1360618"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161066"},{"key":"ref5","first-page":"73","article-title":"Optimization principles and application performance evaluation of a multithreaded GPU using CUDA","author":"ryoo","year":"2008","journal-title":"Proc of the 13th ACM SIGPLAN Symp on Prin and practice of parallel programming"},{"key":"ref8","article-title":"On implementing graph cuts on CUDA","author":"hussein","year":"2007","journal-title":"First Workshop on General Purpose Processing on Graphics Processing Units"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5213922"},{"journal-title":"ATI ATI Stream SDK User Guide","year":"2008","key":"ref2"},{"journal-title":"NVIDIA CUDA Programming Guide 2 0 NVIDIA","year":"2008","key":"ref1"},{"key":"ref9","first-page":"1","article-title":"Inter-block GPU communication via fast barrier synchronization","author":"xiao","year":"2010","journal-title":"IPDPS"},{"key":"ref20","first-page":"1","article-title":"Novel GPU implementation of Jacobi algorithm for karhunen-Loeve transform of dense matrices","author":"torun","year":"2012","journal-title":"Ann Conf on Information Sciences and Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2010.5537722"},{"key":"ref21","article-title":"Efficient parallel scan algorithms for GPUs","author":"sengupta","year":"2008","journal-title":"Tech Rep NVR-2008-003"},{"key":"ref24","volume":"1110 4623","author":"stuart","year":"2011","journal-title":"Efficient Synchronization Primitives for GPUs"},{"key":"ref23","article-title":"Synchronize between blocks on CUDA GPU","author":"wang","year":"2010","journal-title":"Project Report"}],"event":{"name":"2015 IEEE\/ACIS 16th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel\/Distributed Computing (SNPD)","start":{"date-parts":[[2015,6,1]]},"location":"Takamatsu","end":{"date-parts":[[2015,6,3]]}},"container-title":["2015 IEEE\/ACIS 16th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel\/Distributed Computing (SNPD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7159154\/7176160\/07176173.pdf?arnumber=7176173","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,25]],"date-time":"2017-03-25T01:05:47Z","timestamp":1490403947000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7176173\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/snpd.2015.7176173","relation":{},"subject":[],"published":{"date-parts":[[2015,6]]}}}