{"id":"https://openalex.org/W4388096455","doi":"https://doi.org/10.1145/3581784.3607109","title":"High-Performance SVD Partial Spectrum Computation","display_name":"High-Performance SVD Partial Spectrum Computation","publication_year":2023,"publication_date":"2023-10-30","ids":{"openalex":"https://openalex.org/W4388096455","doi":"https://doi.org/10.1145/3581784.3607109"},"language":"en","primary_location":{"id":"doi:10.1145/3581784.3607109","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581784.3607109","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3581784.3607109","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021283893","display_name":"David E. Keyes","orcid":"https://orcid.org/0000-0002-4052-7224"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"David Keyes","raw_affiliation_strings":["King Abdullah University of Science & Technology, Thuwal, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-4052-7224","affiliations":[{"raw_affiliation_string":"King Abdullah University of Science & Technology, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017526753","display_name":"Hatem Ltaief","orcid":"https://orcid.org/0000-0002-6897-1095"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Hatem Ltaief","raw_affiliation_strings":["King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-6897-1095","affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008129578","display_name":"Yuji Nakatsukasa","orcid":"https://orcid.org/0000-0001-7911-1501"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuji Nakatsukasa","raw_affiliation_strings":["Mathematical Institute University of Oxford, Oxford, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-7911-1501","affiliations":[{"raw_affiliation_string":"Mathematical Institute University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064027099","display_name":"Dalal Sukkari","orcid":"https://orcid.org/0000-0002-4228-4211"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dalal Sukkari","raw_affiliation_strings":["Innovative Computing Laboratory University of Tennessee, Knoxville, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-4228-4211","affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory University of Tennessee, Knoxville, United States of America","institution_ids":["https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T12303","display_name":"Tensor decomposition and applications","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6155591607093811},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6098266839981079},{"id":"https://openalex.org/keywords/singular-value-decomposition","display_name":"Singular value decomposition","score":0.5971629023551941},{"id":"https://openalex.org/keywords/spectrum","display_name":"Spectrum (functional analysis)","score":0.5117287635803223},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3750428259372711},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.15073490142822266}],"concepts":[{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6155591607093811},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6098266839981079},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.5971629023551941},{"id":"https://openalex.org/C156778621","wikidata":"https://www.wikidata.org/wiki/Q1365748","display_name":"Spectrum (functional analysis)","level":2,"score":0.5117287635803223},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3750428259372711},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15073490142822266},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581784.3607109","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581784.3607109","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581784.3607109","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581784.3607109","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W995198334","https://openalex.org/W1580960713","https://openalex.org/W1581582143","https://openalex.org/W1987255606","https://openalex.org/W1991973947","https://openalex.org/W1995406764","https://openalex.org/W2016606481","https://openalex.org/W2032503266","https://openalex.org/W2039599184","https://openalex.org/W2052799831","https://openalex.org/W2057204994","https://openalex.org/W2059076129","https://openalex.org/W2078841894","https://openalex.org/W2083246623","https://openalex.org/W2102181290","https://openalex.org/W2117756735","https://openalex.org/W2119233169","https://openalex.org/W2119522963","https://openalex.org/W2160774872","https://openalex.org/W2275630370","https://openalex.org/W2397480569","https://openalex.org/W2740048653","https://openalex.org/W2744399788","https://openalex.org/W2758813627","https://openalex.org/W2774052225","https://openalex.org/W2774512715","https://openalex.org/W2809263166","https://openalex.org/W2943231329","https://openalex.org/W2963513094","https://openalex.org/W3013334287","https://openalex.org/W3026465517","https://openalex.org/W3098608845","https://openalex.org/W3154152825"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2390279801","https://openalex.org/W3121932492","https://openalex.org/W4232638561","https://openalex.org/W2358668433","https://openalex.org/W1997544008","https://openalex.org/W2376932109"],"abstract_inverted_index":{"We":[0,56,73,130,164],"introduce":[1],"a":[2,47,58,75,115,138],"new":[3],"singular":[4,54],"value":[5],"decomposition":[6],"(SVD)":[7],"solver":[8],"based":[9,122],"on":[10,64,114,123],"the":[11,20,28,32,35,39,42,52,81,170],"QR-based":[12],"Dynamically":[13],"Weighted":[14],"Halley":[15],"(QDWH)":[16],"algorithm":[17,44],"for":[18,100,169],"computing":[19],"partial":[21],"spectrum":[22,40],"SVD":[23],"(QDWHpartial-SVD)":[24],"problems.":[25],"By":[26],"optimizing":[27],"rational":[29],"function":[30],"underlying":[31],"algorithms":[33,172],"in":[34,181],"desired":[36],"part":[37],"of":[38,51,61,141],"only,":[41],"QDWHpartial-SVD":[43,62,101,134,176],"efficiently":[45],"computes":[46],"fraction":[48],"(say":[49],"1--20%)":[50],"leading":[53],"values/vectors.":[55],"develop":[57],"high-performance":[59],"implementation":[60],"1":[63],"distributed-memory":[65],"manycore":[66],"systems":[67],"and":[68,105,112,151,173],"demonstrate":[69,174],"its":[70],"numerical":[71,83],"robustness.":[72],"perform":[74],"benchmarking":[76],"campaign":[77],"against":[78,107],"counterparts":[79],"from":[80,110,162],"state-of-the-art":[82],"libraries":[84],"across":[85],"various":[86],"matrix":[87],"sizes":[88],"using":[89,119],"up":[90,102,155],"to":[91,103,137,156,159],"36K":[92],"MPI":[93],"processes.":[94],"Experimental":[95],"results":[96],"show":[97],"performance":[98,153],"speedups":[99],"6X":[104],"2X":[106],"vendor-optimized":[108,160],"PDGESVD":[109,161,180],"ScaLAPACK":[111],"KSVD":[113],"Cray":[116],"XC40":[117],"system":[118,139],"1152":[120],"nodes":[121,143],"two-socket":[124,145],"16-core":[125],"Intel":[126],"Haswell":[127],"CPU,":[128],"respectively.":[129],"also":[131,165],"port":[132],"our":[133],"software":[135],"library":[136],"composed":[140],"256":[142],"with":[144],"64-Core":[146],"AMD":[147],"EPYC":[148],"Milan":[149],"CPU":[150],"achieve":[152],"speedup":[154],"4X":[157],"compared":[158],"ScaLAPACK.":[163],"compare":[166],"energy":[167],"consumption":[168],"two":[171],"how":[175],"can":[177],"further":[178],"outperform":[179],"that":[182],"regard":[183],"by":[184],"performing":[185],"fewer":[186],"memory-bound":[187],"operations.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}