{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T12:13:36Z","timestamp":1763468016980,"version":"3.37.3"},"reference-count":13,"publisher":"CRC Press","isbn-type":[{"type":"print","value":"9781439825365"},{"type":"electronic","value":"9781439825372"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,12,7]]},"DOI":"10.1201\/b10376-8","type":"book-chapter","created":{"date-parts":[[2011,1,28]],"date-time":"2011-01-28T09:37:12Z","timestamp":1296207432000},"page":"83-109","source":"Crossref","is-referenced-by-count":17,"title":["Sparse Matrix-Vector Multiplication on Multicore and Accelerators"],"prefix":"10.1201","author":[{"given":"Samuel","family":"Williams","sequence":"first","affiliation":[]},{"given":"Nathan","family":"Bell","sequence":"additional","affiliation":[]},{"given":"Jee","family":"Whan Choi","sequence":"additional","affiliation":[]},{"given":"Michael","family":"Garland","sequence":"additional","affiliation":[]},{"given":"Leonid","family":"Oliker","sequence":"additional","affiliation":[]},{"given":"Richard","family":"Vu","sequence":"additional","affiliation":[]}],"member":"301","published-online":{"date-parts":[[2011,1,28]]},"reference":[{"volume-title":"Issue 6: POSIX Threads (pthread.h)","year":"2004","author":"The Open Group Base Specifications","key":"p_1"},{"volume-title":"Version 2.1. http:\/\/developer.download.nvidia.com\/ compute\/cuda\/2_1\/toolkit\/docs\/NVIDIA_CUDA_Programming_Guide_ 2.1.pdf","year":"2008","author":"Compute Unified Device NVIDIA CUDA","key":"p_2"},{"volume-title":"May","year":"2008","key":"p_3"},{"key":"p_5","doi-asserted-by":"crossref","unstructured":"Nathan Bell and Michael Garland. Implementing a sparse matrix-vector multiplication on throughput-oriented processors. InProc. ACM\/IEEE Conf. Supercomputing (SC), Portland, OR, USA, November 2009.","DOI":"10.1145\/1654059.1654078"},{"key":"p_7","doi-asserted-by":"crossref","unstructured":"Jee Whan Choi, Amik Singh, and Richard W. Vuduc. Model-driven autotuning of sparse matrix-vector multiply on GPUs. InProc. ACM SIGPLAN Symp. Principles and Practice of Parallel Programming (PPoPP), Bangalore, India, January 2010.","DOI":"10.1145\/1693453.1693471"},{"volume-title":"February","year":"2004","author":"Im Eun-Jin","key":"p_8"},{"volume-title":"September","year":"2009","author":"NVIDIA.","key":"p_9"},{"volume-title":"Boisvert","year":"1984","author":"Rice John R.","key":"p_10"},{"key":"p_11","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718003"},{"key":"p_12","unstructured":"Shubhabrata Sengupta, Mark Harris, Yao Zhang, and John D. Owens. Scan primitives for GPU computing. InProc. ACM SIGGRAPH\/EUROGRAPHICS Symp. Graphics Hardware, San Diego, CA, USA, 2007."},{"key":"p_14","doi-asserted-by":"crossref","unstructured":"Sam Williams, Leonid Oliker, Richard Vuduc, John Shalf, Katherine Yelick, and James Demmel. Optimization of sparse matrix-vector multiplication on emerging multicore platforms. InProc. ACM\/IEEE Conf. Supercomputing (SC), 2007.","DOI":"10.1145\/1362622.1362674"},{"key":"p_15","doi-asserted-by":"crossref","unstructured":"Sam Williams, Richard Vuduc, Leonid Oliker, John Shalf, Katherine Yelick, and James Demmel. Optimizing sparse matrix-vector multiply on emerging multicore platforms. Parallel Computing (ParCo), 35(3):178-194, March 2009. Extends conference version: http:\/\/dx.doi.org\/10. 1145\/1362622.1362674.","DOI":"10.1016\/j.parco.2008.12.006"},{"volume-title":"Auto-tuning performance on multicore computers. UCB\/EECS-2008-164","year":"2008","author":"Williams Samuel Webb","key":"p_16"}],"container-title":["Chapman & Hall\/CRC Computational Science","Scientific Computing with Multicore and Accelerators"],"original-title":[],"language":"en","deposited":{"date-parts":[[2019,6,8]],"date-time":"2019-06-08T01:42:56Z","timestamp":1559958176000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.crcnetbase.com\/doi\/abs\/10.1201\/b10376-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,12,7]]},"ISBN":["9781439825365","9781439825372"],"references-count":13,"alternative-id":["10.1201\/b10376-8","10.1201\/CHCOMPUTSCI","10.1201\/b10376"],"URL":"https:\/\/doi.org\/10.1201\/b10376-8","relation":{},"ISSN":["2154-4492"],"issn-type":[{"type":"print","value":"2154-4492"}],"subject":[],"published":{"date-parts":[[2010,12,7]]}}}