{"id":"https://openalex.org/W3202766834","doi":"https://doi.org/10.1145/3472456.3472476","title":"An Evaluation of Task-Parallel Frameworks for Sparse Solvers on Multicore and Manycore CPU Architectures","display_name":"An Evaluation of Task-Parallel Frameworks for Sparse Solvers on Multicore and Manycore CPU Architectures","publication_year":2021,"publication_date":"2021-08-09","ids":{"openalex":"https://openalex.org/W3202766834","doi":"https://doi.org/10.1145/3472456.3472476","mag":"3202766834"},"language":"en","primary_location":{"id":"doi:10.1145/3472456.3472476","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3472456.3472476","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3472456.3472476","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"50th International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3472456.3472476","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068365809","display_name":"Abdullah Alperen","orcid":null},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Abdullah Alperen","raw_affiliation_strings":["Michigan State University"],"affiliations":[{"raw_affiliation_string":"Michigan State University","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090150968","display_name":"Md Afibuzzaman","orcid":"https://orcid.org/0000-0001-9224-638X"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Md Afibuzzaman","raw_affiliation_strings":["Michigan State University, United States of America"],"affiliations":[{"raw_affiliation_string":"Michigan State University, United States of America","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057965288","display_name":"Fazlay Rabbi","orcid":null},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fazlay Rabbi","raw_affiliation_strings":["Michigan State University, United States of America"],"affiliations":[{"raw_affiliation_string":"Michigan State University, United States of America","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085400686","display_name":"M. Yusuf \u00d6zkaya","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Yusuf Ozkaya","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026046737","display_name":"\u00dcmit V. \u00c7ataly\u00fcrek","orcid":"https://orcid.org/0000-0002-5625-3758"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Umit Catalyurek","raw_affiliation_strings":["Georgia Institute of Technology, United States of America"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, United States of America","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072718512","display_name":"Hasan Metin Aktulga","orcid":"https://orcid.org/0000-0003-3061-6378"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hasan Metin Aktulga","raw_affiliation_strings":["Michigan State University"],"affiliations":[{"raw_affiliation_string":"Michigan State University","institution_ids":["https://openalex.org/I87216513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5068365809"],"corresponding_institution_ids":["https://openalex.org/I87216513"],"apc_list":null,"apc_paid":null,"fwci":0.7074,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68117719,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9994999766349792,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8966625928878784},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8305541276931763},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.7430459856987},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.6668494343757629},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.5547263026237488},{"id":"https://openalex.org/keywords/runtime-system","display_name":"Runtime system","score":0.5155551433563232},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.5039412379264832},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.48808443546295166},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.45824500918388367},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1191432774066925}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8966625928878784},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8305541276931763},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.7430459856987},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.6668494343757629},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.5547263026237488},{"id":"https://openalex.org/C2780870223","wikidata":"https://www.wikidata.org/wiki/Q1004415","display_name":"Runtime system","level":2,"score":0.5155551433563232},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.5039412379264832},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.48808443546295166},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.45824500918388367},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1191432774066925}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3472456.3472476","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3472456.3472476","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3472456.3472476","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"50th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3472456.3472476","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3472456.3472476","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3472456.3472476","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"50th International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3734581427","display_name":null,"funder_award_id":"NUCLEI SciDAC","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G3761866520","display_name":null,"funder_award_id":"CCF-1822932, OAC-1845208, CCF-1919021","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3887249236","display_name":"CAREER: Scalable Sparse Linear Algebra for Extreme-Scale Data Analytics and Scientific Computing","funder_award_id":"1845208","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4367178226","display_name":null,"funder_award_id":"DE-SC0018083","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6127774790","display_name":null,"funder_award_id":"1919021","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6627486083","display_name":null,"funder_award_id":"CCF-1919021","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7064412432","display_name":"SPX: A Geometry and Architecture Agnostic Scalable Framework for N-body Problems with Oscillatory Potentials","funder_award_id":"1822932","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7546856147","display_name":null,"funder_award_id":"NUCLEI SciDAC","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7827746701","display_name":null,"funder_award_id":"CCF-1822932","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8344606036","display_name":null,"funder_award_id":"SciDAC","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","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"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320310016","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320332431","display_name":"College of Engineering, Michigan State University","ror":"https://ror.org/05hs6h993"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3202766834.pdf","grobid_xml":"https://content.openalex.org/works/W3202766834.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W284224400","https://openalex.org/W1735172278","https://openalex.org/W1984689820","https://openalex.org/W1984848758","https://openalex.org/W1988425770","https://openalex.org/W2035821661","https://openalex.org/W2053999255","https://openalex.org/W2087440962","https://openalex.org/W2126004407","https://openalex.org/W2133250609","https://openalex.org/W2783190869","https://openalex.org/W2783728688","https://openalex.org/W2903247043","https://openalex.org/W2931411095","https://openalex.org/W2966129987","https://openalex.org/W3101929792","https://openalex.org/W3187688612","https://openalex.org/W4213135654","https://openalex.org/W4248722156","https://openalex.org/W4250807363","https://openalex.org/W4288086138"],"related_works":["https://openalex.org/W2026512611","https://openalex.org/W1985165680","https://openalex.org/W4245497162","https://openalex.org/W2793205098","https://openalex.org/W2353146130","https://openalex.org/W1990817968","https://openalex.org/W1996138408","https://openalex.org/W2138782497","https://openalex.org/W1935251877","https://openalex.org/W2309631221"],"abstract_inverted_index":{"Recently,":[0],"several":[1],"task-parallel":[2],"programming":[3,35],"models":[4],"have":[5],"emerged":[6],"to":[7,64,119,134,174,196],"address":[8],"the":[9,28,57,82,101,139,204],"high":[10],"synchronization":[11],"and":[12,46,61,85,93,97,110,126,160,188],"load":[13],"imbalance":[14],"issues":[15],"as":[16,18],"well":[17],"data":[19],"movement":[20],"overheads":[21,137],"in":[22,89,117,200],"modern":[23,164],"shared":[24,32,77],"memory":[25,33,66,78],"architectures.":[26,79],"OpenMP,":[27,83],"most":[29],"commonly":[30],"used":[31],"parallel":[34],"model,":[36],"has":[37],"added":[38],"task":[39],"execution":[40,59,201],"support":[41,56],"with":[42,138],"dataflow":[43,58],"dependencies.":[44],"HPX":[45,84],"Regent":[47,86],"are":[48],"two":[49,106,153],"more":[50],"recent":[51],"runtime":[52,87,124],"systems":[53,88],"that":[54,143,169],"also":[55,193],"model":[60,104],"extend":[62],"it":[63],"distributed":[65],"environments.":[67],"We":[68,80,112,147,167],"focus":[69],"on":[70,76,152],"parallelization":[71],"of":[72,91,95,141],"sparse":[73],"matrix":[74],"computations":[75],"evaluate":[81],"terms":[90],"performance":[92,133],"ease":[94],"implementation,":[96],"compare":[98],"them":[99],"against":[100],"traditional":[102],"BSP":[103,183,206],"for":[105,130],"popular":[107],"eigensolvers,":[108],"Lanczos":[109],"LOBPCG.":[111],"give":[113],"a":[114,128],"general":[115],"outline":[116],"regards":[118],"achieving":[120],"parallelism":[121,142],"using":[122],"these":[123,170],"systems,":[125],"present":[127],"heuristic":[129],"tuning":[131],"their":[132,150],"balance":[135],"tasking":[136],"degree":[140],"can":[144],"be":[145],"exposed.":[146],"then":[148],"demonstrate":[149],"merits":[151],"architectures,":[154],"Intel":[155],"Broadwell":[156],"(a":[157,163],"multicore":[158],"processor)":[159],"AMD":[161],"EPYC":[162],"manycore":[165],"processor).":[166],"observe":[168],"frameworks":[171],"achieve":[172],"up":[173,195],"13.7":[175],"\u00d7":[176,198],"fewer":[177],"cache":[178,190],"misses":[179],"over":[180,203],"an":[181],"efficient":[182],"implementation":[184],"across":[185],"L1,":[186],"L2":[187],"L3":[189],"layers.":[191],"They":[192],"obtain":[194],"9.9":[197],"improvement":[199],"time":[202],"same":[205],"implementation.":[207]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}
