{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T17:47:10Z","timestamp":1729619230258,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/padsw.2014.7097819","type":"proceedings-article","created":{"date-parts":[[2015,5,1]],"date-time":"2015-05-01T10:35:19Z","timestamp":1430476519000},"page":"281-288","source":"Crossref","is-referenced-by-count":12,"title":["Cache-aware sparse matrix formats for Kepler GPU"],"prefix":"10.1109","author":[{"given":"Yusuke","family":"Nagasaka","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akira","family":"Nukada","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoshi","family":"Matsuoka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"26","author":"tang","year":"2013","journal-title":"Proceedings of SC13 International Conference for High Performance Computing Networking Storage and Analysis"},{"key":"ref11","article-title":"Performance evaluation of sparse matrix multiplication kernels on Intel Xeon Phi","author":"saule","year":"2013","journal-title":"arXiv preprint arXiv 1302 1078"},{"key":"ref12","article-title":"Optimizing sparse matrix-vector multiplication on GPUs using compile-time and run-time strategies","author":"baskaran","year":"2008","journal-title":"IBM Reserach Report RC24704 (W0812–047)"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"893","DOI":"10.1007\/978-3-642-01970-8_90","article-title":"Fast conjugate gradients with multiple GPUs","author":"cevahir","year":"2009","journal-title":"Computational Science-ICCS 2009"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1007\/s00450-010-0112-6","article-title":"High performance conjugate gradient solver on multi-GPU clusters using hypergraph partitioning","volume":"25","year":"2010","journal-title":"Computer Science-Research and Development"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1007\/978-3-642-11515-8_10","article-title":"Automatically tuning sparse matrix-vector multiplication for GPU architectures","author":"monakov","year":"2010","journal-title":"High Performance Embedded Architectures and Compilers"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.1658"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2464996.2465013"},{"key":"ref18","article-title":"A unified sparse matrix data format for modern processors with wide SIMD units","volume":"abs 1307 6209","author":"kreutzer","year":"2013","journal-title":"CoRR"},{"key":"ref19","first-page":"18","author":"bell","year":"2009","journal-title":"Proceedings of the Conference on High Performance Computing Networking Storage and Analysis"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718003"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2008.12.006"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s00200-007-0038-9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2009.21"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2004.1327917"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/PDP.2012.78"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2013.58"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1007\/978-3-642-03138-0_32","article-title":"Implementing blocked sparse matrix-vector multiplication on NVIDIA GPUs","author":"monakov","year":"2009","journal-title":"Embedded Computer Systems Architectures Modeling and Simulation"},{"key":"ref20","article-title":"Hardware Technology of the SX-9 (1)","volume":"3","author":"nakazato","year":"0","journal-title":"NEC TECHNICAL JOURNAL Special Issue Supercomputer SX-9"},{"key":"ref22","first-page":"231","author":"xu","year":"2012","journal-title":"13th ACIS International Conference on Software Engineering Artificial Intelligence Networking and Parallel & Distributed Computing (SNPD) 2012"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/1094342004041296"}],"event":{"name":"2014 20th IEEE International Conference on Parallel and Distributed Systems (ICPADS)","start":{"date-parts":[[2014,12,16]]},"location":"Hsinchu, Taiwan","end":{"date-parts":[[2014,12,19]]}},"container-title":["2014 20th IEEE International Conference on Parallel and Distributed Systems (ICPADS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7092978\/7097773\/07097819.pdf?arnumber=7097819","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,23]],"date-time":"2017-06-23T06:43:42Z","timestamp":1498200222000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7097819\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/padsw.2014.7097819","relation":{},"subject":[],"published":{"date-parts":[[2014,12]]}}}