{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T11:55:05Z","timestamp":1776772505101,"version":"3.51.2"},"reference-count":17,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012,7]]},"DOI":"10.1109\/hpcsim.2012.6266966","type":"proceedings-article","created":{"date-parts":[[2012,8,22]],"date-time":"2012-08-22T10:48:48Z","timestamp":1345632528000},"page":"511-519","source":"Crossref","is-referenced-by-count":23,"title":["Algorithmic strategies for optimizing the parallel reduction primitive in CUDA"],"prefix":"10.1109","author":[{"given":"Pedro J.","family":"Martin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luis F.","family":"Ayuso","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roberto","family":"Torres","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonio","family":"Gavilanes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"17","doi-asserted-by":"publisher","DOI":"10.1145\/1457515.1409079"},{"key":"15","author":"sengupta","year":"2008","journal-title":"Efficient Parallel Scan Algorithms for GPUs"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.5815\/ijmecs.2011.04.08"},{"key":"13","first-page":"26","article-title":"A work-efficient stepefficient prefix sum algorithm","author":"sengupta","year":"0","journal-title":"Proc Edge Computing Using New Commodity Architectures 2006"},{"key":"14","first-page":"97","article-title":"Scan Primitives for GPU Computing","author":"sengupta","year":"2007","journal-title":"Proc Graphics Hardware (GH 07)"},{"key":"11","first-page":"573","article-title":"Stream reduction operations for GPGPU applications","volume":"2","author":"horn","year":"2005","journal-title":"GPU Gems"},{"key":"12","first-page":"904","article-title":"CUDA Solutions for the SSSP Problem","author":"marti?n","year":"2009","journal-title":"Proc International Conference on Computational Science (ICCS 09)"},{"key":"3","author":"bell","year":"2008","journal-title":"Efficient Sparse Matrix-Vector Multiplication on CUDA"},{"key":"2","article-title":"CudaDMA: Optimizing GPU Memory Bandwidth via Warp Specialization","author":"bauer","year":"2011","journal-title":"Proc Int Conference for High Performance Computing Networking Storage and Analysis (SC '11)"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1145\/1572769.1572792"},{"key":"10","author":"harris","year":"2007","journal-title":"Optimizing Parallel Reduction in CUDA"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1145\/1375527.1375559"},{"key":"6","year":"0","journal-title":"CUDA Data Parallel Primitives Library (CUDPP)"},{"key":"5","author":"blelloch","year":"1993","journal-title":"Prefix Sums and Their Applications"},{"key":"4","author":"blelloch","year":"1990","journal-title":"Vector Models for Data-Parallel Computing"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2006.00969.x"},{"key":"8","year":"0","journal-title":"General-Purpose Computation on Graphics Hardware"}],"event":{"name":"2012 International Conference on High Performance Computing & Simulation (HPCS)","location":"Madrid, Spain","start":{"date-parts":[[2012,7,2]]},"end":{"date-parts":[[2012,7,6]]}},"container-title":["2012 International Conference on High Performance Computing & Simulation (HPCS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6260982\/6266874\/06266966.pdf?arnumber=6266966","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,21]],"date-time":"2017-03-21T21:54:58Z","timestamp":1490133298000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6266966\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,7]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/hpcsim.2012.6266966","relation":{},"subject":[],"published":{"date-parts":[[2012,7]]}}}