{"id":"https://openalex.org/W4367147522","doi":"https://doi.org/10.1109/hipc56025.2022.00030","title":"A Portable Sparse Solver Framework for Large Matrices on Heterogeneous Architectures","display_name":"A Portable Sparse Solver Framework for Large Matrices on Heterogeneous Architectures","publication_year":2022,"publication_date":"2022-12-01","ids":{"openalex":"https://openalex.org/W4367147522","doi":"https://doi.org/10.1109/hipc56025.2022.00030"},"language":"en","primary_location":{"id":"doi:10.1109/hipc56025.2022.00030","doi":"https://doi.org/10.1109/hipc56025.2022.00030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc56025.2022.00030","pdf_url":null,"source":{"id":"https://openalex.org/S4306418683","display_name":"IEEE International Conference on High Performance Computing, Data, and Analytics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 29th International Conference on High Performance Computing, Data, and Analytics (HiPC)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5057965288","display_name":"Fazlay Rabbi","orcid":null,"observed_orcids":[]},"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,Computer Science & Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University,Computer Science & Engineering","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039454582","display_name":"Christopher S. Daley","orcid":"https://orcid.org/0000-0003-3105-0804","observed_orcids":["https://orcid.org/0000-0003-3105-0804"]},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher S. Daley","raw_affiliation_strings":["Lawrence Berkeley National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026046737","display_name":"\u00dcmit V. \u00c7ataly\u00fcrek","orcid":"https://orcid.org/0000-0002-5625-3758","observed_orcids":["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":"\u00dcmit V. \u00c7ataly\u00fcrek","raw_affiliation_strings":["Georgia Institute of Technology,Amazon Web Services\u00a7 and School of Computational Science & Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Amazon Web Services\u00a7 and School of Computational Science & Engineering","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","observed_orcids":["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,Computer Science & Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University,Computer Science & Engineering","institution_ids":["https://openalex.org/I87216513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"145","last_page":"155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9945999979972839,"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":0.9945999979972839,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.004399999976158142,"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"}},{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/gpu-memory-management","display_name":"GPU memory management","score":0.6330000162124634},{"id":"https://openalex.org/keywords/heterogeneous-computing","display_name":"heterogeneous computing","score":0.5270000100135803},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"task parallelism","score":0.5139999985694885},{"id":"https://openalex.org/keywords/tiling","display_name":"tiling","score":0.628000020980835},{"id":"https://openalex.org/keywords/directed-acyclic-graphs","display_name":"directed acyclic graphs","score":0.8849999904632568},{"id":"https://openalex.org/keywords/large-sparse-matrices","display_name":"large sparse matrices","score":0.6790000200271606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.880593478679657},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7461146116256714},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.70125412940979},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.6876830458641052},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.643316388130188},{"id":"https://openalex.org/C50954386","wikidata":"https://www.wikidata.org/wiki/Q656083","display_name":"Paging","level":2,"score":0.4755775034427643},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4723323881626129},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.4708634912967682},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.32527393102645874},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.25306862592697144},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1290741264820099},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hipc56025.2022.00030","doi":"https://doi.org/10.1109/hipc56025.2022.00030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc56025.2022.00030","pdf_url":null,"source":{"id":"https://openalex.org/S4306418683","display_name":"IEEE International Conference on High Performance Computing, Data, and Analytics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 29th International Conference on High Performance Computing, Data, and Analytics (HiPC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1480928214","https://openalex.org/W1735172278","https://openalex.org/W1967993405","https://openalex.org/W1985312666","https://openalex.org/W1988425770","https://openalex.org/W2001148043","https://openalex.org/W2040404421","https://openalex.org/W2051142108","https://openalex.org/W2053107666","https://openalex.org/W2095836023","https://openalex.org/W2128131218","https://openalex.org/W2128853364","https://openalex.org/W2259950804","https://openalex.org/W2330672121","https://openalex.org/W2740117223","https://openalex.org/W2808128431","https://openalex.org/W2885571639","https://openalex.org/W2964337156","https://openalex.org/W2969925465","https://openalex.org/W3006573990","https://openalex.org/W3017891227","https://openalex.org/W3019218318","https://openalex.org/W3081656884","https://openalex.org/W3093969206","https://openalex.org/W4214826206","https://openalex.org/W4243261006"],"related_works":["https://openalex.org/W3006573990","https://openalex.org/W3202517391","https://openalex.org/W3176486103","https://openalex.org/W2280361371","https://openalex.org/W2983162098","https://openalex.org/W4385623280","https://openalex.org/W2964337156","https://openalex.org/W4408029514","https://openalex.org/W3185393231","https://openalex.org/W2168931017"],"abstract_inverted_index":{"Programming":[0],"applications":[1,35],"on":[2,99,157],"heterogeneous":[3],"systems":[4],"with":[5],"hardware":[6],"accelerators":[7],"is":[8],"challenging":[9],"due":[10],"to":[11,50,95,140,177,192,197,204],"the":[12,17,21,30,40,67,74,78,106,123,155,208],"disjoint":[13],"address":[14],"spaces":[15],"between":[16,105,165],"host":[18,107,191,198],"(CPU)":[19],"and":[20,63,108,121,134,159,161,195],"device":[22,26,42,75,193,196],"(GPU).":[23],"The":[24],"limited":[25,41],"memory":[27,76,137],"further":[28],"exacerbates":[29],"challenges":[31],"as":[32,126,167],"most":[33],"data-intensive":[34],"will":[36],"not":[37,146],"fit":[38,147],"in":[39,117,174],"memory.":[43,150],"CUDA":[44],"Unified":[45],"Memory":[46],"(UM)":[47],"was":[48],"introduced":[49],"mitigate":[51],"such":[52],"challenges.":[53],"UM":[54],"improves":[55],"GPU":[56,149],"programmability":[57],"by":[58,101],"supporting":[59],"oversubscription,":[60],"on-demand":[61],"paging,":[62],"migration.":[64],"However,":[65],"when":[66],"working":[68],"set":[69],"of":[70,154],"an":[71],"application":[72],"exceeds":[73],"capacity,":[77],"resulting":[79],"data":[80,103,156,164],"movement":[81,104],"can":[82],"cause":[83],"significant":[84],"performance":[85],"losses.":[86],"We":[87,132,169],"propose":[88],"a":[89,118,127,136],"tiling-based":[90],"task-parallel":[91],"framework,":[92],"named":[93],"DeepSparseGPU,":[94],"accelerate":[96],"sparse":[97,119],"eigensolvers":[98],"GPUs":[100],"minimizing":[102],"device.":[109],"To":[110],"this":[111],"end,":[112],"we":[113],"tile":[114],"all":[115],"operations":[116],"solver":[120],"express":[122],"entire":[124],"computation":[125],"directed":[128],"acyclic":[129],"graph":[130],"(DAG).":[131],"design":[133],"develop":[135],"manager":[138],"(MM)":[139],"execute":[141],"larger":[142],"inputs":[143],"that":[144,186],"do":[145],"into":[148],"MM":[151],"keeps":[152],"track":[153],"CPU":[158],"GPU,":[160],"automatically":[162],"moves":[163],"them":[166],"needed.":[168],"use":[170],"OpenMP":[171],"target":[172],"offload":[173],"our":[175],"implementation":[176],"achieve":[178],"portability":[179],"beyond":[180],"NVIDIA":[181],"hardware.":[182],"Performance":[183],"evaluations":[184],"show":[185],"DeepSparseGPU":[187],"transfers":[188],"1.39x-2.18x":[189],"less":[190],"(H2D)":[194],"(D2H)":[199],"data,":[200],"while":[201],"executing":[202],"up":[203],"2.93x":[205],"faster":[206],"than":[207],"UM-based":[209],"baseline":[210],"version.":[211]},"counts_by_year":[],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-04-28T00:00:00"}