{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T04:57:18Z","timestamp":1755838638499,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":12,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,11,12]],"date-time":"2017-11-12T00:00:00Z","timestamp":1510444800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Helmholtz-Gemeinschaft","award":["VH-NG-1241"],"award-info":[{"award-number":["VH-NG-1241"]}]},{"DOI":"10.13039\/501100003329","name":"Ministerio de Econom\u00eda y Competitividad","doi-asserted-by":"publisher","award":["TIN2014-53495-R"],"award-info":[{"award-number":["TIN2014-53495-R"]}],"id":[{"id":"10.13039\/501100003329","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-SC-0010042"],"award-info":[{"award-number":["DE-SC-0010042"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010664","name":"H2020 Future and Emerging Technologies","doi-asserted-by":"publisher","award":["732631 OPRECOMP"],"award-info":[{"award-number":["732631 OPRECOMP"]}],"id":[{"id":"10.13039\/100010664","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,11,12]]},"DOI":"10.1145\/3148226.3148230","type":"proceedings-article","created":{"date-parts":[[2017,11,3]],"date-time":"2017-11-03T12:36:10Z","timestamp":1509712570000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Flexible batched sparse matrix-vector product on GPUs"],"prefix":"10.1145","author":[{"given":"Hartwig","family":"Anzt","sequence":"first","affiliation":[{"name":"Karlsruhe Institute of Technology, Germany and University of Tennessee"}]},{"given":"Gary","family":"Collins","sequence":"additional","affiliation":[{"name":"University of Tennessee"}]},{"given":"Jack","family":"Dongarra","sequence":"additional","affiliation":[{"name":"University of Tennessee and University of Manchester, Manchester, UK"}]},{"given":"Goran","family":"Flegar","sequence":"additional","affiliation":[{"name":"Universidad Jaume I, Castellon, Spain"}]},{"given":"Enrique S.","family":"Quintana-Ort\u00ed","sequence":"additional","affiliation":[{"name":"Universidad Jaume I, Castellon, Spain"}]}],"member":"320","published-online":{"date-parts":[[2017,11,12]]},"reference":[{"volume-title":"Performance, design, and autotuning of batched GEMM for GPUs","author":"Abdelfattah Ahmad","key":"e_1_3_2_1_1_1","unstructured":"Ahmad Abdelfattah , Azzam Haidar , Stanimire Tomov , and Jack Dongarra . 2016. Performance, design, and autotuning of batched GEMM for GPUs . Springer International Publishing , Cham , 21--38. Ahmad Abdelfattah, Azzam Haidar, Stanimire Tomov, and Jack Dongarra. 2016. Performance, design, and autotuning of batched GEMM for GPUs. Springer International Publishing, Cham, 21--38."},{"key":"e_1_3_2_1_2_1","volume-title":"Technical Report 291. LAPACK Working Note.","author":"Anzt H.","year":"2016","unstructured":"H. Anzt , E. Chow , and J. Dongarra . 2016 . On block-asynchronous execution on GPUs . Technical Report 291. LAPACK Working Note. H. Anzt, E. Chow, and J. Dongarra. 2016. On block-asynchronous execution on GPUs. Technical Report 291. LAPACK Working Note."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2017.05.006"},{"key":"e_1_3_2_1_4_1","unstructured":"H. Anzt S. Tomov and J. Dongarra. 2014. Implementing a Sparse Matrix Vector Product for the SELL-C\/SELL-C-σ formats on NVIDIA GPUs. Technical Report ut-eecs-14-727. University of Tennessee.  H. Anzt S. Tomov and J. Dongarra. 2014. Implementing a Sparse Matrix Vector Product for the SELL-C\/SELL-C-σ formats on NVIDIA GPUs. Technical Report ut-eecs-14-727. University of Tennessee."},{"key":"e_1_3_2_1_5_1","volume-title":"Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods","author":"Barrett R.","unstructured":"R. Barrett , M. Berry , T. F. Chan , J. Demmel , J. Donato , J. Dongarra , V. Eijkhout , R. Pozo , C. Romine , and H. Van der Vorst . 1994. Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods , 2 nd Edition. SIAM , Philadelphia, PA . R. Barrett, M. Berry, T. F. Chan, J. Demmel, J. Donato, J. Dongarra, V. Eijkhout, R. Pozo, C. Romine, and H. Van der Vorst. 1994. Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods, 2nd Edition. SIAM, Philadelphia, PA.","edition":"2"},{"key":"e_1_3_2_1_7_1","volume-title":"CUSP: Generic Parallel Algorithms for Sparse Matrix and Graph Computations.","author":"Dalton Steven","year":"2014","unstructured":"Steven Dalton , Nathan Bell , Luke Olson , and Michael Garland . 2014 . CUSP: Generic Parallel Algorithms for Sparse Matrix and Graph Computations. (2014). http:\/\/cusplibrary.github.io\/ Version 0.5.0. Steven Dalton, Nathan Bell, Luke Olson, and Michael Garland. 2014. CUSP: Generic Parallel Algorithms for Sparse Matrix and Graph Computations. (2014). http:\/\/cusplibrary.github.io\/ Version 0.5.0."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_2_1_9_1","volume-title":"Technical Report 2016.25. The University of Manchester, ISSN 1749--9097.","author":"Dongarra J.","year":"2016","unstructured":"J. Dongarra , I. S. Duff , M. Gates , A. Haidar , S. Hammerling , J. Higham , J. Hogg , P. Valero-Lara , D. Relton , S. Tomov , and M. Zounon . 2016 . A Proposed API for Batched Basic Linear Algebra Subprograms . Technical Report 2016.25. The University of Manchester, ISSN 1749--9097. J. Dongarra, I. S. Duff, M. Gates, A. Haidar, S. Hammerling, J. Higham, J. Hogg, P. Valero-Lara, D. Relton, S. Tomov, and M. Zounon. 2016. A Proposed API for Batched Basic Linear Algebra Subprograms. Technical Report 2016.25. The University of Manchester, ISSN 1749--9097."},{"key":"e_1_3_2_1_10_1","volume-title":"EuroPar","author":"Flegar Goran","year":"2017","unstructured":"Goran Flegar and Enrique S . Quintana-Ort\u00ed. accepted. Balanced CSR Sparse Matrix-Vector Product on Graphics Processors . In EuroPar 2017 . Goran Flegar and Enrique S. Quintana-Ort\u00ed. accepted. Balanced CSR Sparse Matrix-Vector Product on Graphics Processors. In EuroPar 2017."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1137\/130930352"},{"key":"e_1_3_2_1_12_1","volume-title":"Whitepaper: NVIDIA Tesla P100. WP-08019-001_v01.1.","author":"NVIDIA.","year":"2016","unstructured":"NVIDIA. 2016 . Whitepaper: NVIDIA Tesla P100. WP-08019-001_v01.1. (2016). NVIDIA. 2016. Whitepaper: NVIDIA Tesla P100. WP-08019-001_v01.1. (2016)."},{"key":"e_1_3_2_1_13_1","unstructured":"NVIDIA. 2017. CUDA toolkit V8.0.  NVIDIA. 2017. CUDA toolkit V8.0."}],"event":{"name":"SC '17: The International Conference for High Performance Computing, Networking, Storage and Analysis","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","IEEE-CS\\DATC IEEE Computer Society"],"location":"Denver Colorado","acronym":"SC '17"},"container-title":["Proceedings of the 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3148226.3148230","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3148226.3148230","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3148226.3148230","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:11:02Z","timestamp":1750212662000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3148226.3148230"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11,12]]},"references-count":12,"alternative-id":["10.1145\/3148226.3148230","10.1145\/3148226"],"URL":"https:\/\/doi.org\/10.1145\/3148226.3148230","relation":{},"subject":[],"published":{"date-parts":[[2017,11,12]]},"assertion":[{"value":"2017-11-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}