{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T05:54:20Z","timestamp":1791352460123,"version":"4.3.1"},"reference-count":31,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,4]]},"DOI":"10.1109\/ipdps.2010.5470477","type":"proceedings-article","created":{"date-parts":[[2010,6,2]],"date-time":"2010-06-02T16:25:07Z","timestamp":1275495907000},"page":"1-12","source":"Crossref","is-referenced-by-count":76,"title":["Inter-block GPU communication via fast barrier synchronization"],"prefix":"10.1109","author":[{"family":"Shucai Xiao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"family":"Wu-chun Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2009.110"},{"key":"ref30","first-page":"25","article-title":"Fitting FFT onto the G80 Architecture","author":"volkov","year":"2006"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/PDP.2007.10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013153020460"},{"key":"ref12","first-page":"47","article-title":"All-Pairs Shortest-Paths for Large Graphs on the GPU","author":"katz","year":"2008","journal-title":"Proc of the ACM SIGGRAPH Symp on Graphics Hardware"},{"key":"ref13","article-title":"Bitonic Sort","author":"lang","year":"1997"},{"key":"ref14","article-title":"Bio-Sequence Database Scanning on a GPU","author":"liu","year":"2006","journal-title":"IPDPS"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1007\/11758549_29","article-title":"GPU Accelerated Smith-Waterman","volume":"3994","author":"liu","year":"2006","journal-title":"Proc of the International Conference on Computational Science Lectures Notes in Computer Science"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970999"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/BF01407956"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-9-S2-S10"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/BIBE.2008.4696721"},{"key":"ref28","article-title":"A Tutorial on Dynamic Programming","author":"trick","year":"1997"},{"key":"ref4","first-page":"307","article-title":"Sorting Networks and their Applications","author":"batcher","year":"1968","journal-title":"Proc AFIPS Joint Comput Conf"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161065"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/165231.165265"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5213922"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5214359"},{"key":"ref5","first-page":"57","article-title":"On Dynamic Load Balancing on Graphics Processors","author":"cederman","year":"2008","journal-title":"Proc of the ACM SIGGRAPH Symp on Graphics Hardware"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/BF01407897"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2006.1639284"},{"key":"ref2","article-title":"AMD\/ATI. Stream Computing User Guide","year":"2009"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77220-0_21"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/135419.135446"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5213210"},{"key":"ref22","article-title":"NVIDIA CUDA Programming Guide-2.2","year":"2009"},{"key":"ref21","article-title":"CUDA SDK 2.2.1","year":"2009"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1345206.1345220"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1145\/1366230.1366277","article-title":"GPU Acceleration of Cutoff Pair Potentials for Molecular Modeling Applications","author":"rodrigues","year":"2008","journal-title":"Proc of the Conference on Computing Frontiers"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161066"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/0022-2836(81)90087-5"}],"event":{"name":"Distributed Processing (IPDPS)","location":"Atlanta, GA","start":{"date-parts":[[2010,4,19]]},"end":{"date-parts":[[2010,4,23]]}},"container-title":["2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5465899\/5470342\/05470477.pdf?arnumber=5470477","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,28]],"date-time":"2021-10-28T16:37:35Z","timestamp":1635439055000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5470477\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,4]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/ipdps.2010.5470477","relation":{},"subject":[],"published":{"date-parts":[[2010,4]]}}}