{"id":"https://openalex.org/W2796244266","doi":"https://doi.org/10.1142/s0129626418500044","title":"Scaling Up Parallel Computation of Tiled QR Factorizations by a Distributed Scheduling Runtime System and Analytical Modeling","display_name":"Scaling Up Parallel Computation of Tiled QR Factorizations by a Distributed Scheduling Runtime System and Analytical Modeling","publication_year":2018,"publication_date":"2018-03-01","ids":{"openalex":"https://openalex.org/W2796244266","doi":"https://doi.org/10.1142/s0129626418500044","mag":"2796244266"},"language":"en","primary_location":{"id":"doi:10.1142/s0129626418500044","is_oa":true,"landing_page_url":"https://doi.org/10.1142/s0129626418500044","pdf_url":"https://www.worldscientific.com/doi/pdf/10.1142/S0129626418500044","source":{"id":"https://openalex.org/S18360026","display_name":"Parallel Processing Letters","issn_l":"0129-6264","issn":["0129-6264","1793-642X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Parallel Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.worldscientific.com/doi/pdf/10.1142/S0129626418500044","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051499975","display_name":"Weijian Zheng","orcid":"https://orcid.org/0000-0003-2791-0031"},"institutions":[{"id":"https://openalex.org/I55769427","display_name":"Indiana University \u2013 Purdue University Indianapolis","ror":"https://ror.org/05gxnyn08","country_code":"US","type":"education","lineage":["https://openalex.org/I55769427","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weijian Zheng","raw_affiliation_strings":["Indiana University-Purdue University Indianapolis, 723 W. Michigan St, Indianapolis, Indiana 46202, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University-Purdue University Indianapolis, 723 W. Michigan St, Indianapolis, Indiana 46202, USA","institution_ids":["https://openalex.org/I55769427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032742296","display_name":"Fengguang Song","orcid":"https://orcid.org/0000-0001-7382-093X"},"institutions":[{"id":"https://openalex.org/I55769427","display_name":"Indiana University \u2013 Purdue University Indianapolis","ror":"https://ror.org/05gxnyn08","country_code":"US","type":"education","lineage":["https://openalex.org/I55769427","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fengguang Song","raw_affiliation_strings":["Indiana University-Purdue University Indianapolis, 723 W. Michigan St, Indianapolis, Indiana 46202, USA"],"raw_orcid":"https://orcid.org/0000-0001-7382-093X","affiliations":[{"raw_affiliation_string":"Indiana University-Purdue University Indianapolis, 723 W. Michigan St, Indianapolis, Indiana 46202, USA","institution_ids":["https://openalex.org/I55769427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100302765","display_name":"Lan Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I198089087","display_name":"Ball State University","ror":"https://ror.org/00k6tx165","country_code":"US","type":"education","lineage":["https://openalex.org/I198089087"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lan Lin","raw_affiliation_strings":["Ball State University, 2000 W. University Ave, Muncie, Indiana 47306, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ball State University, 2000 W. University Ave, Muncie, Indiana 47306, USA","institution_ids":["https://openalex.org/I198089087"]}]},{"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 at Riverside, 900 University Ave, Riverside, California 92521, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California at Riverside, 900 University Ave, Riverside, California 92521, 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":0.2306,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47753965,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"28","issue":"01","first_page":"1850004","last_page":"1850004"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9976000189781189,"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":0.8274327516555786},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7816988229751587},{"id":"https://openalex.org/keywords/qr-decomposition","display_name":"QR decomposition","score":0.7317641377449036},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6314696073532104},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5862547755241394},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5589893460273743},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5490472912788391},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.4841945469379425},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.48297062516212463},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.4566974937915802},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4467615485191345},{"id":"https://openalex.org/keywords/parallel-algorithm","display_name":"Parallel algorithm","score":0.4332195818424225},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3468763530254364},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32126492261886597},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.12232449650764465},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.1180858314037323},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11711499094963074}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8274327516555786},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7816988229751587},{"id":"https://openalex.org/C188060507","wikidata":"https://www.wikidata.org/wiki/Q653242","display_name":"QR decomposition","level":3,"score":0.7317641377449036},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6314696073532104},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5862547755241394},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5589893460273743},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5490472912788391},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.4841945469379425},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.48297062516212463},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.4566974937915802},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4467615485191345},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.4332195818424225},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3468763530254364},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32126492261886597},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.12232449650764465},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.1180858314037323},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11711499094963074},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0129626418500044","is_oa":true,"landing_page_url":"https://doi.org/10.1142/s0129626418500044","pdf_url":"https://www.worldscientific.com/doi/pdf/10.1142/S0129626418500044","source":{"id":"https://openalex.org/S18360026","display_name":"Parallel Processing Letters","issn_l":"0129-6264","issn":["0129-6264","1793-642X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Parallel Processing Letters","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1142/s0129626418500044","is_oa":true,"landing_page_url":"https://doi.org/10.1142/s0129626418500044","pdf_url":"https://www.worldscientific.com/doi/pdf/10.1142/S0129626418500044","source":{"id":"https://openalex.org/S18360026","display_name":"Parallel Processing Letters","issn_l":"0129-6264","issn":["0129-6264","1793-642X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Parallel Processing Letters","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309667","display_name":"Purdue Research Foundation","ror":"https://ror.org/007n03h88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W171963546","https://openalex.org/W2033130314","https://openalex.org/W2042025615","https://openalex.org/W2097273583","https://openalex.org/W2112290071","https://openalex.org/W2208990223","https://openalex.org/W4231150350","https://openalex.org/W4236558082","https://openalex.org/W4301491118","https://openalex.org/W4302564868"],"related_works":["https://openalex.org/W1485846902","https://openalex.org/W3037218165","https://openalex.org/W1970433854","https://openalex.org/W1980464854","https://openalex.org/W2982181895","https://openalex.org/W2739115385","https://openalex.org/W2023867642","https://openalex.org/W2084348954","https://openalex.org/W3007255846","https://openalex.org/W170159993"],"abstract_inverted_index":{"Implementing":[0],"parallel":[1,12,145],"software":[2,44],"for":[3,51],"QR":[4,42,61,86],"factorizations":[5],"to":[6,48,75,115,128,157,165,179],"achieve":[7],"scalable":[8],"performance":[9,32,126,196],"on":[10],"massively":[11],"manycore":[13],"systems":[14],"requires":[15,109],"a":[16,37,58,68,123,150],"comprehensive":[17],"design":[18,57],"that":[19,45,119,142],"includes":[20],"algorithm":[21,63],"redesign,":[22],"efficient":[23],"runtime":[24,73],"systems,":[25],"synchronization":[26,78],"and":[27,30,64,79,108,112,159,192],"communication":[28],"reduction,":[29],"analytical":[31,125,177],"modeling.":[33],"This":[34],"paper":[35],"presents":[36],"piece":[38],"of":[39,84,93,98,133,170,184,198],"tiled":[40,59],"communication-avoiding":[41,60,85],"factorization":[43,62,87],"is":[46,103,147,186],"able":[47],"scale":[49],"efficiently":[50],"matrices":[52],"with":[53,67,168],"general":[54],"dimensions.":[55],"We":[56],"implement":[65],"it":[66],"fully":[69],"distributed":[70],"dynamic":[71],"scheduling":[72],"system":[74],"minimize":[76],"both":[77],"communication.":[80],"The":[81,138],"whole":[82],"class":[83],"algorithms":[88],"uses":[89],"an":[90,130,181,194],"important":[91],"parameter":[92],"D":[94],"(i.e.,":[95],"the":[96,175],"number":[97,132,183],"domains),":[99],"whose":[100],"best":[101],"solution":[102],"still":[104],"unknown":[105],"so":[106],"far":[107],"manual":[110],"tuning":[111],"empirical":[113],"searching":[114],"find":[116],"it.":[117],"To":[118],"end,":[120],"we":[121],"introduce":[122],"simplified":[124],"model":[127,178],"determine":[129],"optimal":[131,182],"domains":[134,185],"D[Formula:":[135],"see":[136],"text].":[137],"experimental":[139],"results":[140],"show":[141],"our":[143],"new":[144,176],"implementation":[146],"faster":[148,160],"than":[149,161],"state-of-the-art":[151],"multicore-based":[152],"numerical":[153],"library":[154],"by":[155,163],"up":[156,164],"30%,":[158],"ScaLAPACK":[162],"30":[166],"times":[167],"thousands":[169],"CPU":[171],"cores.":[172],"Furthermore,":[173],"using":[174],"predict":[180],"as":[187,189],"competitive":[188],"exhaustive":[190],"searching,":[191],"exhibits":[193],"average":[195],"difference":[197],"1%.":[199]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}