{"id":"https://openalex.org/W2117228145","doi":"https://doi.org/10.1145/1375527.1375572","title":"Efficient computation of sum-products on GPUs through software-managed cache","display_name":"Efficient computation of sum-products on GPUs through software-managed cache","publication_year":2008,"publication_date":"2008-06-07","ids":{"openalex":"https://openalex.org/W2117228145","doi":"https://doi.org/10.1145/1375527.1375572","mag":"2117228145"},"language":"en","primary_location":{"id":"doi:10.1145/1375527.1375572","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1375527.1375572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd annual international conference on Supercomputing","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/A5022593894","display_name":"Mark Silberstein","orcid":"https://orcid.org/0000-0001-9659-068X"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Mark Silberstein","raw_affiliation_strings":["Technion - Israel Institute of Technology, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion - Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090998564","display_name":"Assaf Schuster","orcid":"https://orcid.org/0000-0002-3311-6937"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Assaf Schuster","raw_affiliation_strings":["Technion - Israel Institute of Technology, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion - Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000414827","display_name":"Dan Geiger","orcid":"https://orcid.org/0000-0001-9988-0199"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Dan Geiger","raw_affiliation_strings":["Technion - Israel Institute of Technology, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion - Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027283935","display_name":"Anjul Patney","orcid":"https://orcid.org/0000-0002-4911-2674"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anjul Patney","raw_affiliation_strings":["University of California, Davis, CA, USA","[University of California, Davis, CA~, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"[University of California, Davis, CA~, USA]","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028662746","display_name":"John D. Owens","orcid":"https://orcid.org/0000-0001-6582-8237"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John D. Owens","raw_affiliation_strings":["University of California, Davis, CA, USA","[University of California, Davis, CA~, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"[University of California, Davis, CA~, USA]","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5022593894"],"corresponding_institution_ids":["https://openalex.org/I174306211"],"apc_list":null,"apc_paid":null,"fwci":17.264,"has_fulltext":false,"cited_by_count":100,"citation_normalized_percentile":{"value":0.99357812,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"309","last_page":"318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9990000128746033,"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":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.8707595467567444},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7449106574058533},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6894158720970154},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.6316816806793213},{"id":"https://openalex.org/keywords/cache-pollution","display_name":"Cache pollution","score":0.5620182752609253},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.5594924092292786},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5512161254882812},{"id":"https://openalex.org/keywords/cache-oblivious-algorithm","display_name":"Cache-oblivious algorithm","score":0.5361573100090027},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5140360593795776},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.49033284187316895},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.4799107015132904},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4623813033103943},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3976937532424927},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.26576268672943115},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18389782309532166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8707595467567444},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7449106574058533},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6894158720970154},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.6316816806793213},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.5620182752609253},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.5594924092292786},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5512161254882812},{"id":"https://openalex.org/C59687516","wikidata":"https://www.wikidata.org/wiki/Q5015938","display_name":"Cache-oblivious algorithm","level":5,"score":0.5361573100090027},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5140360593795776},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.49033284187316895},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.4799107015132904},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4623813033103943},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3976937532424927},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.26576268672943115},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18389782309532166},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1145/1375527.1375572","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1375527.1375572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd annual international conference on Supercomputing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.298.6820","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.298.6820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.technion.ac.il/~dang/conf_papers/SilbersteinSGPO08.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.362.7294","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.362.7294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.idav.ucdavis.edu/func/return_pdf?pub_id=940","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.422.9334","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.422.9334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ics.uci.edu/~dechter/courses/ics-295/spring-2008/SumProductPaper.pdf","raw_type":"text"},{"id":"pmh:oai:escholarship.org/ark:/13030/qt8js4v3f7","is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/8js4v3f7","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"pmh:qt8js4v3f7","is_oa":false,"landing_page_url":"http://www.escholarship.org/uc/item/8js4v3f7","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Silberstein, Mark; Schuster, Assaf; Geiger, Dan; Patney, Anjul; &amp; Owens, John D.(2008). Efficient Computation of Sum-products on GPUs Through Software-Managed Cache. UC Davis: Institute for Data Analysis and Visualization. Retrieved from: http://www.escholarship.org/uc/item/8js4v3f7","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/12","score":0.44999998807907104,"display_name":"Responsible consumption and production"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1605419350","https://openalex.org/W1865141138","https://openalex.org/W1964031104","https://openalex.org/W2085118703","https://openalex.org/W2097922255","https://openalex.org/W2108157916","https://openalex.org/W2108792719","https://openalex.org/W2113520225","https://openalex.org/W2129471558","https://openalex.org/W2139774022","https://openalex.org/W2144643978","https://openalex.org/W2165952534","https://openalex.org/W2168028787","https://openalex.org/W2541107968","https://openalex.org/W2728600909"],"related_works":["https://openalex.org/W2098406302","https://openalex.org/W2121191383","https://openalex.org/W2538519144","https://openalex.org/W1584415117","https://openalex.org/W2546991807","https://openalex.org/W2167303720","https://openalex.org/W1496086148","https://openalex.org/W2146079099","https://openalex.org/W1860107648","https://openalex.org/W57688818"],"abstract_inverted_index":{"We":[0,40],"present":[1,42],"a":[2,37],"technique":[3],"for":[4,46],"designing":[5],"memory-bound":[6],"algorithms":[7],"with":[8,18],"high":[9],"data":[10],"reuse":[11],"on":[12,26],"Graphics":[13],"Processing":[14],"Units":[15],"(GPUs)":[16],"equipped":[17],"close-to-ALU":[19],"software-managed":[20,38],"memory.":[21],"The":[22],"approach":[23],"is":[24],"based":[25],"the":[27,34],"efficient":[28],"use":[29],"of":[30,36,49],"this":[31],"memory":[32],"through":[33],"implementation":[35],"cache.":[39],"also":[41],"an":[43],"analytical":[44],"model":[45],"performance":[47],"analysis":[48],"such":[50],"algorithms.":[51]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":13}],"updated_date":"2026-05-08T15:41:06.802602","created_date":"2025-10-10T00:00:00"}
