{"id":"https://openalex.org/W4315588752","doi":"https://doi.org/10.1145/3572848.3577496","title":"Improving Energy Saving of One-Sided Matrix Decompositions on CPU-GPU Heterogeneous Systems","display_name":"Improving Energy Saving of One-Sided Matrix Decompositions on CPU-GPU Heterogeneous Systems","publication_year":2023,"publication_date":"2023-02-21","ids":{"openalex":"https://openalex.org/W4315588752","doi":"https://doi.org/10.1145/3572848.3577496"},"language":"en","primary_location":{"id":"doi:10.1145/3572848.3577496","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3572848.3577496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2301.03166","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063649910","display_name":"Jieyang Chen","orcid":"https://orcid.org/0000-0002-1905-9171"},"institutions":[{"id":"https://openalex.org/I32389192","display_name":"University of Alabama at Birmingham","ror":"https://ror.org/008s83205","country_code":"US","type":"education","lineage":["https://openalex.org/I32389192"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jieyang Chen","raw_affiliation_strings":["University of Alabama at Birmingham, Birmingham, Alabama, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alabama at Birmingham, Birmingham, Alabama, USA","institution_ids":["https://openalex.org/I32389192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057011942","display_name":"Xin Liang","orcid":"https://orcid.org/0000-0002-7219-1809"},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Liang","raw_affiliation_strings":["University of Kentucky, Lexington, Kentucky, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Kentucky, Lexington, Kentucky, USA","institution_ids":["https://openalex.org/I143302722"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643410","display_name":"Kai Zhao","orcid":"https://orcid.org/0000-0001-5328-3962"},"institutions":[{"id":"https://openalex.org/I32389192","display_name":"University of Alabama at Birmingham","ror":"https://ror.org/008s83205","country_code":"US","type":"education","lineage":["https://openalex.org/I32389192"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Zhao","raw_affiliation_strings":["University of Alabama at Birmingham, Birmingham, Alabama, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alabama at Birmingham, Birmingham, Alabama, USA","institution_ids":["https://openalex.org/I32389192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010378286","display_name":"Hadi Zamani Sabzi","orcid":null},"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":"Hadi Zamani Sabzi","raw_affiliation_strings":["University of California, Riverside, Riverside, California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, California, 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, Riverside, California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, California, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"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, Riverside, California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, California, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"274","last_page":"287"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9987999796867371,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9968000054359436,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7877312898635864},{"id":"https://openalex.org/keywords/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.6283524036407471},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5338847041130066},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5337294936180115},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5275775194168091},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.4981417655944824},{"id":"https://openalex.org/keywords/qr-decomposition","display_name":"QR decomposition","score":0.4557967782020569},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.44723135232925415},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.43209075927734375},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4177362620830536},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.41516998410224915},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3954234719276428},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3403087258338928},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11732903122901917},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08443465828895569}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7877312898635864},{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.6283524036407471},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5338847041130066},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5337294936180115},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5275775194168091},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.4981417655944824},{"id":"https://openalex.org/C188060507","wikidata":"https://www.wikidata.org/wiki/Q653242","display_name":"QR decomposition","level":3,"score":0.4557967782020569},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.44723135232925415},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.43209075927734375},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4177362620830536},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.41516998410224915},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3954234719276428},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3403087258338928},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11732903122901917},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08443465828895569},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3572848.3577496","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3572848.3577496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2301.03166","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.03166","pdf_url":"https://arxiv.org/pdf/2301.03166","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2301.03166","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.03166","pdf_url":"https://arxiv.org/pdf/2301.03166","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8999999761581421,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G4549299513","display_name":"SHF: Small: Locality Aware Scheduling in Multi-GPU Systems","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":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4315588752.pdf"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W36826159","https://openalex.org/W57243869","https://openalex.org/W1585237817","https://openalex.org/W1963651058","https://openalex.org/W1974081606","https://openalex.org/W1981493666","https://openalex.org/W1982864753","https://openalex.org/W1983303752","https://openalex.org/W1995746640","https://openalex.org/W2011024076","https://openalex.org/W2014812733","https://openalex.org/W2030806070","https://openalex.org/W2031533321","https://openalex.org/W2052455844","https://openalex.org/W2058898331","https://openalex.org/W2065360261","https://openalex.org/W2077221978","https://openalex.org/W2103798727","https://openalex.org/W2108434125","https://openalex.org/W2112286143","https://openalex.org/W2132951989","https://openalex.org/W2152212524","https://openalex.org/W2152546515","https://openalex.org/W2156514327","https://openalex.org/W2162322364","https://openalex.org/W2169150754","https://openalex.org/W2235375535","https://openalex.org/W2346404725","https://openalex.org/W2412349256","https://openalex.org/W2418331349","https://openalex.org/W2480662436","https://openalex.org/W2485331474","https://openalex.org/W2515526980","https://openalex.org/W2580243656","https://openalex.org/W2624767357","https://openalex.org/W2767694495","https://openalex.org/W2798289565","https://openalex.org/W2903901007","https://openalex.org/W2924040443","https://openalex.org/W2926767350","https://openalex.org/W2949981335","https://openalex.org/W2971433136","https://openalex.org/W2986161099","https://openalex.org/W3044796228","https://openalex.org/W3048352534","https://openalex.org/W3101708369","https://openalex.org/W3105862567","https://openalex.org/W3106011734","https://openalex.org/W3173669904","https://openalex.org/W3176053424","https://openalex.org/W4233447799","https://openalex.org/W4234833047","https://openalex.org/W4239514724","https://openalex.org/W4244112648","https://openalex.org/W4253492127","https://openalex.org/W4297965929","https://openalex.org/W4302296459"],"related_works":["https://openalex.org/W2982181895","https://openalex.org/W2739115385","https://openalex.org/W2035803264","https://openalex.org/W2039527536","https://openalex.org/W3035209767","https://openalex.org/W3007862902","https://openalex.org/W1965763148","https://openalex.org/W4306891336","https://openalex.org/W1966820346","https://openalex.org/W2967794374"],"abstract_inverted_index":{"One-sided":[0],"dense":[1],"matrix":[2,46,61,87,95],"decompositions":[3,62],"(e.g.,":[4],"Cholesky,":[5],"LU,":[6],"and":[7,111,117,120,148],"QR)":[8],"are":[9,42],"the":[10,56,106,137,157],"key":[11,86],"components":[12],"in":[13,16,48],"scientific":[14],"computing":[15],"many":[17],"different":[18],"fields.":[19],"Although":[20],"their":[21],"design":[22,92],"has":[23],"been":[24],"highly":[25],"optimized":[26],"for":[27,45,85],"modern":[28],"processors,":[29],"they":[30],"still":[31],"consume":[32],"a":[33],"considerable":[34],"amount":[35],"of":[36,59],"energy.":[37,175],"As":[38],"CPU-GPU":[39,64],"heterogeneous":[40,65],"systems":[41],"commonly":[43],"used":[44],"decompositions,":[47],"this":[49],"work,":[50],"we":[51,91],"aim":[52],"to":[53,78,81,113,128,131,150,165,168],"further":[54],"improve":[55],"energy":[57,115,134,140],"saving":[58,116,141],"onesided":[60],"on":[63],"systems.":[66],"We":[67],"first":[68],"build":[69],"an":[70,93],"Algorithm-Based":[71],"Fault":[72],"Tolerance":[73],"protected":[74],"overclocking":[75,84],"technique":[76],"(ABFT-OC)":[77],"enable":[79],"us":[80],"exploit":[82],"reliable":[83],"decomposition":[88,96],"operations.":[89],"Then,":[90],"energy-saving":[94],"framework,":[97],"Bi-directional":[98],"Slack":[99],"Reclamation":[100],"(BSR),":[101],"that":[102,124],"can":[103],"intelligently":[104],"combine":[105],"capability":[107],"provided":[108],"by":[109],"ABFT-OC":[110],"DVFS":[112],"maximize":[114],"maintain":[118],"performance":[119,146,170],"reliability.":[121],"Experiments":[122],"show":[123],"BSR":[125,155],"is":[126,163],"able":[127,164],"save":[129],"up":[130,149,167],"11.7%":[132],"more":[133],"compared":[135],"with":[136,144],"current":[138],"best":[139],"optimization":[142],"approach":[143],"no":[145],"degradation":[147],"14.1%":[151],"Energy\u00d7Delay2":[152],"reduction.":[153],"Also,":[154],"enables":[156],"Pareto":[158],"efficient":[159],"performance-energy":[160],"trade-off,":[161],"which":[162],"provide":[166],"1.43\u00d7":[169],"improvement":[171],"without":[172],"costing":[173],"extra":[174]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2023-01-11T00:00:00"}