{"id":"https://openalex.org/W2996522450","doi":"https://doi.org/10.1145/3371275","title":"Data-driven Mixed Precision Sparse Matrix Vector Multiplication for GPUs","display_name":"Data-driven Mixed Precision Sparse Matrix Vector Multiplication for GPUs","publication_year":2019,"publication_date":"2019-12-17","ids":{"openalex":"https://openalex.org/W2996522450","doi":"https://doi.org/10.1145/3371275","mag":"2996522450"},"language":"en","primary_location":{"id":"doi:10.1145/3371275","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3371275","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3371275","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3371275","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029449217","display_name":"Khalid Ahmad","orcid":"https://orcid.org/0000-0002-5966-5774"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Khalid Ahmad","raw_affiliation_strings":["University of Utah, Salt Lake City, UT"],"affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, UT","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051806400","display_name":"Hari Sundar","orcid":"https://orcid.org/0000-0001-9001-5107"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hari Sundar","raw_affiliation_strings":["University of Utah, Salt Lake City, UT"],"affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, UT","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030152493","display_name":"Mary Hall","orcid":"https://orcid.org/0000-0002-3058-7573"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mary Hall","raw_affiliation_strings":["University of Utah, Salt Lake City, UT"],"affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, UT","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5029449217"],"corresponding_institution_ids":["https://openalex.org/I223532165"],"apc_list":null,"apc_paid":null,"fwci":3.8523,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":{"value":0.94221237,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"16","issue":"4","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991000294685364,"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":0.9991000294685364,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12303","display_name":"Tensor decomposition and applications","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.9082356691360474},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7993786931037903},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.7283729910850525},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6722300052642822},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.665092408657074},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5913715958595276},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5856010913848877},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.5561385154724121},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5031096339225769},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.48706915974617004},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3807348906993866},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14779284596443176},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07633662223815918}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.9082356691360474},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7993786931037903},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.7283729910850525},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6722300052642822},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.665092408657074},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5913715958595276},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5856010913848877},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.5561385154724121},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5031096339225769},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.48706915974617004},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3807348906993866},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14779284596443176},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07633662223815918},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3371275","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3371275","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3371275","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3371275","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3371275","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3371275","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1159014390","display_name":null,"funder_award_id":"1704715","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2996522450.pdf","grobid_xml":"https://content.openalex.org/works/W2996522450.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1970009422","https://openalex.org/W2022219663","https://openalex.org/W2035080386","https://openalex.org/W2060429332","https://openalex.org/W2081368694","https://openalex.org/W2094281253","https://openalex.org/W2104281151","https://openalex.org/W2106191211","https://openalex.org/W2111593426","https://openalex.org/W2114239896","https://openalex.org/W2117752372","https://openalex.org/W2165558283","https://openalex.org/W2480388112","https://openalex.org/W2500846120","https://openalex.org/W2553043960","https://openalex.org/W2557039832","https://openalex.org/W2743322459","https://openalex.org/W2765439756","https://openalex.org/W2766659420","https://openalex.org/W2801035805","https://openalex.org/W2889447872","https://openalex.org/W4237974662"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W2995605830","https://openalex.org/W4206811032","https://openalex.org/W2086123442","https://openalex.org/W2596457687","https://openalex.org/W3212757063","https://openalex.org/W2093666864"],"abstract_inverted_index":{"We":[0],"optimize":[1],"Sparse":[2,76],"Matrix":[3,77],"Vector":[4],"multiplication":[5],"(SpMV)":[6],"using":[7],"a":[8,81],"mixed":[9],"precision":[10,56],"strategy":[11],"(MpSpMV)":[12],"for":[13,47],"Nvidia":[14],"V100":[15],"GPUs.":[16],"The":[17],"approach":[18],"has":[19],"three":[20],"benefits:":[21],"(1)":[22],"It":[23],"reduces":[24,29,38],"computation":[25],"time,":[26],"(2)":[27],"it":[28,43],"the":[30,33,67,75],"size":[31],"of":[32,66,84,89],"input":[34],"matrix":[35],"and":[36,41,86],"therefore":[37],"data":[39,58],"movement,":[40],"(3)":[42],"provides":[44],"an":[45],"opportunity":[46],"increased":[48],"parallelism.":[49],"MpSpMV\u2019s":[50],"decision":[51],"to":[52,54,99],"lower":[53],"single":[55,100],"is":[57],"driven":[59],",":[60],"based":[61],"on":[62],"individual":[63],"nonzero":[64],"values":[65],"sparse":[68],"matrix.":[69],"On":[70],"all":[71],"real-valued":[72],"matrices":[73],"from":[74],"Collection,":[78],"we":[79],"obtain":[80],"maximum":[82],"speedup":[83,88],"2.61\u00d7":[85],"average":[87],"1.06\u00d7":[90],"over":[91],"double":[92],"precision,":[93],"while":[94],"maintaining":[95],"higher":[96],"accuracy":[97],"compared":[98],"precision.":[101]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}