{"id":"https://openalex.org/W4388581238","doi":"https://doi.org/10.1145/3624062.3624248","title":"Task-Based Polar Decomposition Using SLATE on Massively Parallel Systems with Hardware Accelerators","display_name":"Task-Based Polar Decomposition Using SLATE on Massively Parallel Systems with Hardware Accelerators","publication_year":2023,"publication_date":"2023-11-10","ids":{"openalex":"https://openalex.org/W4388581238","doi":"https://doi.org/10.1145/3624062.3624248"},"language":"en","primary_location":{"id":"doi:10.1145/3624062.3624248","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3624062.3624248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","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/A5064027099","display_name":"Dalal Sukkari","orcid":"https://orcid.org/0000-0002-4228-4211"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dalal Sukkari","raw_affiliation_strings":["ICL/UTK, United States"],"affiliations":[{"raw_affiliation_string":"ICL/UTK, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104910026","display_name":"Mark Gates","orcid":"https://orcid.org/0000-0003-2996-1641"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Gates","raw_affiliation_strings":["ICL/UTK, USA"],"affiliations":[{"raw_affiliation_string":"ICL/UTK, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045148446","display_name":"Mohammed Al Farhan","orcid":"https://orcid.org/0000-0002-4988-4674"},"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":"Mohammed Al Farhan","raw_affiliation_strings":["King Abdullah University of Science & Technology, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science & Technology, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012133869","display_name":"Hartwig Anzt","orcid":"https://orcid.org/0000-0003-2177-952X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hartwig Anzt","raw_affiliation_strings":["ICL/UTK, USA"],"affiliations":[{"raw_affiliation_string":"ICL/UTK, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075517045","display_name":"Jack Dongarra","orcid":"https://orcid.org/0000-0003-3247-1782"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["ICL/UTK, USA"],"affiliations":[{"raw_affiliation_string":"ICL/UTK, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5064027099"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17201166,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1680","last_page":"1687"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9980000257492065,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9976999759674072,"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/software-portability","display_name":"Software portability","score":0.8508067727088928},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8230685591697693},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7350373268127441},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.6786966323852539},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.4906562864780426},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.4658896028995514},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.44032660126686096},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4292669892311096},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4107537567615509},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.39688533544540405},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.26870018243789673},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09354069828987122}],"concepts":[{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.8508067727088928},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8230685591697693},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7350373268127441},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.6786966323852539},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.4906562864780426},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.4658896028995514},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.44032660126686096},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4292669892311096},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4107537567615509},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.39688533544540405},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.26870018243789673},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09354069828987122},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3624062.3624248","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3624062.3624248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W995198334","https://openalex.org/W1624763321","https://openalex.org/W2016279572","https://openalex.org/W2016358047","https://openalex.org/W2016606481","https://openalex.org/W2020054862","https://openalex.org/W2022846189","https://openalex.org/W2040557342","https://openalex.org/W2057069782","https://openalex.org/W2059076129","https://openalex.org/W2087843362","https://openalex.org/W2093529653","https://openalex.org/W2112033694","https://openalex.org/W2121893797","https://openalex.org/W2128362857","https://openalex.org/W2326297968","https://openalex.org/W2758813627","https://openalex.org/W2774052225","https://openalex.org/W2774512715","https://openalex.org/W2809263166","https://openalex.org/W2900234561","https://openalex.org/W2943231329","https://openalex.org/W2944649521","https://openalex.org/W2983126917","https://openalex.org/W4241548534","https://openalex.org/W4248806677","https://openalex.org/W4318602967"],"related_works":["https://openalex.org/W2109126387","https://openalex.org/W2152666498","https://openalex.org/W4225552076","https://openalex.org/W4290725151","https://openalex.org/W2161750975","https://openalex.org/W3043805228","https://openalex.org/W1998492046","https://openalex.org/W2021525945","https://openalex.org/W3095040987","https://openalex.org/W1589630408"],"abstract_inverted_index":{"We":[0,20],"investigate":[1],"a":[2],"new":[3],"task-based":[4],"implementation":[5],"of":[6,34,42],"the":[7,22,72],"polar":[8,69],"decomposition":[9,70],"on":[10,47],"massively":[11],"parallel":[12,97],"systems":[13],"augmented":[14],"with":[15],"multiple":[16],"GPUs":[17],"using":[18],"SLATE.":[19],"implement":[21,66],"iterative":[23],"QR":[24],"Dynamically-Weighted":[25],"Halley":[26],"(QDWH)":[27],"algorithm,":[28],"whose":[29],"building":[30],"blocks":[31],"mainly":[32],"consist":[33],"compute-bound":[35],"matrix":[36],"operations,":[37],"allowing":[38],"for":[39],"high":[40],"levels":[41],"parallelism":[43],"to":[44,111],"be":[45],"exploited":[46],"various":[48],"hardware":[49],"architectures,":[50],"such":[51,83,100],"as":[52,84,93,95,101],"NVIDIA,":[53],"AMD,":[54],"and":[55,63,90,104,107],"Intel":[56],"GPU-based":[57],"systems.":[58],"To":[59],"achieve":[60],"both":[61],"performance":[62],"portability,":[64],"we":[65],"our":[67],"QDWH-based":[68],"in":[71,79],"SLATE":[73],"library,":[74],"which":[75],"uses":[76,108],"efficient":[77],"techniques":[78],"dense":[80],"linear":[81],"algebra,":[82],"2D":[85],"block":[86],"cyclic":[87],"data":[88,113],"distribution":[89],"communication-avoiding":[91],"algorithms,":[92],"well":[94],"modern":[96],"programming":[98],"approaches,":[99],"dynamic":[102],"scheduling":[103],"communication":[105],"overlapping,":[106],"OpenMP":[109],"tasks":[110],"track":[112],"dependencies.":[114]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}