{"id":"https://openalex.org/W2106349908","doi":"https://doi.org/10.1109/ccgrid.2010.81","title":"From Sparse Matrix to Optimal GPU CUDA Sparse Matrix Vector Product Implementation","display_name":"From Sparse Matrix to Optimal GPU CUDA Sparse Matrix Vector Product Implementation","publication_year":2010,"publication_date":"2010-05-01","ids":{"openalex":"https://openalex.org/W2106349908","doi":"https://doi.org/10.1109/ccgrid.2010.81","mag":"2106349908"},"language":"en","primary_location":{"id":"doi:10.1109/ccgrid.2010.81","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccgrid.2010.81","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 10th IEEE/ACM International Conference on Cluster, Cloud and Grid Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026223367","display_name":"Ahmed H. El Zein","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Ahmed H El Zein","raw_affiliation_strings":["ANU Supercomputing Facility, Australian National University, Canberra, ACT, Australia","ANU Supercomput. Facility, Australian Nat. Univ., Canberra, ACT, Australia"],"affiliations":[{"raw_affiliation_string":"ANU Supercomputing Facility, Australian National University, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"ANU Supercomput. Facility, Australian Nat. Univ., Canberra, ACT, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084423147","display_name":"Alistair P. Rendell","orcid":"https://orcid.org/0000-0002-9445-0146"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Alistair P Rendell","raw_affiliation_strings":["School of Computer Science, Australian National University, Canberra, ACT, Australia","Sch. of Comput. Sci., Australian Nat. Univ., Canberra, ACT, Australia"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Australian National University, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"Sch. of Comput. Sci., Australian Nat. Univ., Canberra, ACT, Australia","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5026223367"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":1.5161,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.83973584,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"92","issue":null,"first_page":"808","last_page":"813"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.9102574586868286},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.7222885489463806},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7216995358467102},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.7173035740852356},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7041919231414795},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5612711906433105},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.49452587962150574},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.48080721497535706},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.45299032330513},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4137935936450958},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.41351646184921265},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33254384994506836},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1446739137172699},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13756132125854492}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.9102574586868286},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.7222885489463806},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7216995358467102},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.7173035740852356},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7041919231414795},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5612711906433105},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.49452587962150574},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.48080721497535706},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.45299032330513},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4137935936450958},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.41351646184921265},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33254384994506836},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1446739137172699},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13756132125854492},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ccgrid.2010.81","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccgrid.2010.81","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 10th IEEE/ACM International Conference on Cluster, Cloud and Grid Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/55420","is_oa":false,"landing_page_url":"http://hdl.handle.net/1885/55420","pdf_url":null,"source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings 10th IEEE/ACM International Conference on Cluster, Cloud and Grid Computing (CCGRID 2010)","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G359018525","display_name":"Parallel and Distributed Machine Learning - Smart Data Analysis in the Multicore Era","funder_award_id":"DP0987773","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1990832096","https://openalex.org/W2035080386","https://openalex.org/W2099625934","https://openalex.org/W2100452915","https://openalex.org/W2103877122","https://openalex.org/W2119547137","https://openalex.org/W2128853364","https://openalex.org/W2130289795","https://openalex.org/W2141374519","https://openalex.org/W4285719527","https://openalex.org/W6659374036","https://openalex.org/W6678107477"],"related_works":["https://openalex.org/W1537323515","https://openalex.org/W2052993554","https://openalex.org/W2091883426","https://openalex.org/W2046125858","https://openalex.org/W2174948646","https://openalex.org/W3173235360","https://openalex.org/W2293771254","https://openalex.org/W2024017047","https://openalex.org/W4318256793","https://openalex.org/W4221142455"],"abstract_inverted_index":{"The":[0,76],"CUDA":[1,85],"model":[2],"for":[3,62,78],"GPUs":[4],"presents":[5],"the":[6,42,49,67],"programmer":[7],"with":[8],"a":[9,36,52],"plethora":[10],"of":[11,44,51,69],"different":[12,17,20,25,46],"programming":[13],"options.":[14],"These":[15],"includes":[16],"memory":[18,21],"types,":[19],"access":[22],"methods,":[23],"and":[24,33,65],"data":[26],"types.":[27],"Identifying":[28],"which":[29],"options":[30,47],"to":[31,83],"use":[32],"when":[34],"is":[35,74,91],"non-trivial":[37],"exercise.":[38],"This":[39],"paper":[40],"explores":[41],"effect":[43],"these":[45],"on":[48],"performance":[50,64],"routine":[53],"that":[54,71],"evaluates":[55],"sparse":[56,80,86],"matrix":[57,81,87],"vector":[58,88],"products.":[59],"A":[60],"process":[61],"analysing":[63],"selecting":[66],"subset":[68],"implementations":[70],"perform":[72],"best":[73],"proposed.":[75],"potential":[77],"mapping":[79],"attributes":[82],"optimal":[84],"product":[89],"implementation":[90],"discussed.":[92]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2016-06-24T00:00:00"}