{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T11:01:39Z","timestamp":1783076499350,"version":"3.54.6"},"reference-count":25,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1109\/ipdps.2010.5470413","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":85,"title":["Dynamic load balancing on single- and multi-GPU systems"],"prefix":"10.1109","author":[{"given":"Long","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oreste","family":"Villa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sriram","family":"Krishnamoorthy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guang R.","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1071866.1071869"},{"key":"ref11","author":"frenkel","year":"1996","journal-title":"Understanding Molecular Simulation From Algorithms to Applications"},{"key":"ref12","article-title":"Enabling task parallelism in the cuda scheduler","author":"guevara","year":"2009","journal-title":"PEMA 2009"},{"key":"ref13","first-page":"197","article-title":"Accelerating large graph algorithms on the gpu using cuda","author":"harish","year":"2007","journal-title":"HiPC"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/114005.102808"},{"key":"ref15","year":"0","journal-title":"Khronos OpenCL"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1145\/1353536.1346318","article-title":"Merge: a programming model for heterogeneous multi-core systems","volume":"43","author":"linderman","year":"2008","journal-title":"SIG-PLAN Not"},{"key":"ref17","author":"murray","year":"2009","journal-title":"Personal communication"},{"key":"ref18","first-page":"406","article-title":"Adaptive load balancing for raycasting of non-uniformly bricked volumes. Parallel Computing","volume":"33","author":"mller","year":"2007","journal-title":"Parallel Graphics and Visualization"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1365490.1365500"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5160984"},{"key":"ref3","author":"bird","year":"1995","journal-title":"Molecular gas dynamics and the direct simulation of gas flows GA Bird Oxford engineering science series 42"},{"key":"ref6","first-page":"57","article-title":"On Dynamic Load Balancing on Graphics Processors","author":"cederman","year":"2008","journal-title":"GH 2008"},{"key":"ref5","first-page":"16","article-title":"Parallelization of Charmm for MIMD Machines","volume":"7","author":"brooks","year":"1992","journal-title":"Chemical Design Automation News"},{"key":"ref8","first-page":"338","article-title":"Parallel Molecular Dynamics","author":"clark","year":"1991","journal-title":"SIAM PP’91"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/215399.215423"},{"key":"ref2","first-page":"863","article-title":"StarPU: A Unified Platform for Task Scheduling on Heterogeneous Multicore Architectures","author":"augonnet","year":"2009","journal-title":"Euro-Par 2009"},{"key":"ref9","author":"cormen","year":"2001","journal-title":"Introduction to Algorithms"},{"key":"ref1","year":"0","journal-title":"AMD ATI Stream"},{"key":"ref20","year":"0","journal-title":"NVidia CUDA"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISPA.2008.40"},{"key":"ref21","article-title":"Nvidia","year":"2009","journal-title":"NVIDIA CUDA Programming Guide 2 3"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/0010-4655(91)90097-5"},{"key":"ref23","first-page":"73","article-title":"Optimization principles and application performance evaluation of a multithreaded gpu using cuda","author":"ryoo","year":"2008","journal-title":"PPoPP’08"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5214359"}],"event":{"name":"2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS)","location":"Atlanta, GA, USA","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\/05470413.pdf?arnumber=5470413","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,19]],"date-time":"2017-06-19T04:58:37Z","timestamp":1497848317000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5470413\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/ipdps.2010.5470413","relation":{},"subject":[],"published":{"date-parts":[[2010]]}}}