{"id":"https://openalex.org/W4321178867","doi":"https://doi.org/10.1145/3583590","title":"GreenMD: Energy-efficient Matrix Decomposition on Heterogeneous Multi-GPU Systems","display_name":"GreenMD: Energy-efficient Matrix Decomposition on Heterogeneous Multi-GPU Systems","publication_year":2023,"publication_date":"2023-02-17","ids":{"openalex":"https://openalex.org/W4321178867","doi":"https://doi.org/10.1145/3583590"},"language":"en","primary_location":{"id":"doi:10.1145/3583590","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583590","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583590","source":{"id":"https://openalex.org/S2483380313","display_name":"ACM Transactions on Parallel Computing","issn_l":"2329-4949","issn":["2329-4949","2329-4957"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Parallel Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3583590","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042883520","display_name":"Hadi Zamani","orcid":"https://orcid.org/0000-0002-9637-6576"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hadi Zamani","raw_affiliation_strings":["University of California, Riverside, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Riverside, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048949780","display_name":"Laxmi N. Bhuyan","orcid":"https://orcid.org/0000-0002-8759-0458"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laxmi Bhuyan","raw_affiliation_strings":["University of California, Riverside, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Riverside, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063649910","display_name":"Jieyang Chen","orcid":"https://orcid.org/0000-0002-1905-9171"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jieyang Chen","raw_affiliation_strings":["Oak Ridge National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061737717","display_name":"Zizhong Chen","orcid":"https://orcid.org/0000-0003-2578-4940"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zizhong Chen","raw_affiliation_strings":["University of California, Riverside, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Riverside, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5042883520"],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":1.509,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7991466,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"10","issue":"2","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9962999820709229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7973978519439697},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6942492127418518},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.668463408946991},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.6147852540016174},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5465582609176636},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5357334613800049},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.5349351763725281},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.5108789801597595},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.47024527192115784},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.4695604145526886},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.41872870922088623},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3665662705898285},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25850731134414673},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1712195873260498}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7973978519439697},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6942492127418518},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.668463408946991},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.6147852540016174},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5465582609176636},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5357334613800049},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.5349351763725281},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.5108789801597595},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.47024527192115784},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.4695604145526886},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.41872870922088623},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3665662705898285},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25850731134414673},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1712195873260498},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3583590","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583590","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583590","source":{"id":"https://openalex.org/S2483380313","display_name":"ACM Transactions on Parallel Computing","issn_l":"2329-4949","issn":["2329-4949","2329-4957"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Parallel Computing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3583590","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583590","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583590","source":{"id":"https://openalex.org/S2483380313","display_name":"ACM Transactions on Parallel Computing","issn_l":"2329-4949","issn":["2329-4949","2329-4957"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Parallel Computing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.9100000262260437,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G4549299513","display_name":null,"funder_award_id":"1907401","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/W4321178867.pdf","grobid_xml":"https://content.openalex.org/works/W4321178867.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1268450243","https://openalex.org/W1560991867","https://openalex.org/W1973923004","https://openalex.org/W2017099699","https://openalex.org/W2033597569","https://openalex.org/W2042415312","https://openalex.org/W2102061396","https://openalex.org/W2102587899","https://openalex.org/W2130336316","https://openalex.org/W2130388542","https://openalex.org/W2138692126","https://openalex.org/W2140440478","https://openalex.org/W2142577331","https://openalex.org/W2150283124","https://openalex.org/W2161125731","https://openalex.org/W2170059648","https://openalex.org/W2233640613","https://openalex.org/W2234633824","https://openalex.org/W2235375535","https://openalex.org/W2521210839","https://openalex.org/W2556446894","https://openalex.org/W2766888159","https://openalex.org/W2790957308","https://openalex.org/W2945148926","https://openalex.org/W2945969444","https://openalex.org/W2949981335","https://openalex.org/W2950162708","https://openalex.org/W2978697470","https://openalex.org/W4230315356","https://openalex.org/W4233447799","https://openalex.org/W4234833047","https://openalex.org/W4241072847","https://openalex.org/W4244112648"],"related_works":["https://openalex.org/W2766762530","https://openalex.org/W119752240","https://openalex.org/W2602301532","https://openalex.org/W2152666498","https://openalex.org/W1988437637","https://openalex.org/W1977700955","https://openalex.org/W4225552076","https://openalex.org/W4290725151","https://openalex.org/W4388311419","https://openalex.org/W1973739845"],"abstract_inverted_index":{"The":[0],"current":[1],"trend":[2],"of":[3],"performance":[4,74,168],"growth":[5],"in":[6,15],"HPC":[7],"systems":[8,29],"is":[9,37,46,51,148],"accompanied":[10],"by":[11,58],"a":[12,38,137],"massive":[13],"increase":[14],"energy":[16,98,158],"consumption.":[17],"In":[18],"this":[19,56],"article,":[20],"we":[21,100,121],"introduce":[22],"GreenMD,":[23],"an":[24],"energy-efficient":[25],"framework":[26],"for":[27,30,79,105,131],"heterogeneous":[28],"LU":[31,35],"factorization":[32,36],"utilizing":[33,136],"multi-GPUs.":[34],"crucial":[39],"kernel":[40],"from":[41],"the":[42,70,86,123,132,153,170],"MAGMA":[43,174],"library,":[44],"which":[45],"highly":[47],"optimized.":[48],"Our":[49],"aim":[50],"to":[52,55,118,169],"apply":[53,143],"DVFS":[54,93],"application":[57],"leveraging":[59],"slacks":[60],"intelligently":[61],"on":[62,85],"both":[63,80,106],"CPUs":[64,81,107,133],"and":[65,82,89,108,134,142,156,162],"multiple":[66],"GPUs.":[67,109],"To":[68],"predict":[69],"slack":[71],"times,":[72],"accurate":[73],"models":[75],"are":[76],"developed":[77],"separately":[78],"GPUs":[83,135],"based":[84],"algorithmic":[87],"knowledge":[88],"manufacturer\u2019s":[90],"specifications.":[91],"Since":[92],"does":[94],"not":[95],"reduce":[96],"static":[97],"consumption,":[99],"also":[101],"develop":[102],"undervolting":[103],"techniques":[104],"Reducing":[110],"voltage":[111],"below":[112],"threshold":[113],"values":[114],"may":[115],"give":[116],"rise":[117],"errors;":[119],"hence,":[120],"extract":[122],"minimum":[124],"safe":[125],"voltages":[126],"(":[127],"V":[128],"safeMin":[129],")":[130],"low":[138],"overhead":[139],"profiling":[140],"phase":[141],"them":[144],"before":[145],"execution.":[146],"It":[147],"shown":[149],"that":[150],"GreenMD":[151],"improves":[152],"CPU,":[154],"GPU,":[155],"total":[157],"about":[159],"59%,":[160],"21%,":[161],"31%,":[163],"respectively,":[164],"while":[165],"delivering":[166],"similar":[167],"state-of-the-art":[171],"linear":[172],"algebra":[173],"library.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}