{"id":"https://openalex.org/W4308090470","doi":"https://doi.org/10.1109/hpec55821.2022.9926410","title":"A Hierarchical Jacobi Iteration for Structured Matrices on GPUs using Shared Memory","display_name":"A Hierarchical Jacobi Iteration for Structured Matrices on GPUs using Shared Memory","publication_year":2022,"publication_date":"2022-09-19","ids":{"openalex":"https://openalex.org/W4308090470","doi":"https://doi.org/10.1109/hpec55821.2022.9926410"},"language":"en","primary_location":{"id":"doi:10.1109/hpec55821.2022.9926410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec55821.2022.9926410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5043088569","display_name":"Mohammad Shafaet Islam","orcid":null},"institutions":[{"id":"https://openalex.org/I46020346","display_name":"American Institute of Aeronautics and Astronautics","ror":"https://ror.org/00a1rzv11","country_code":"US","type":"other","lineage":["https://openalex.org/I46020346"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mohammad Shafaet Islam","raw_affiliation_strings":["Massachusetts Institute of Technology,Department of Aeronautics and Astronautics,Massachusetts,Cambridge,02139"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Department of Aeronautics and Astronautics,Massachusetts,Cambridge,02139","institution_ids":["https://openalex.org/I46020346","https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101519068","display_name":"Qiqi Wang","orcid":"https://orcid.org/0000-0001-9669-2563"},"institutions":[{"id":"https://openalex.org/I46020346","display_name":"American Institute of Aeronautics and Astronautics","ror":"https://ror.org/00a1rzv11","country_code":"US","type":"other","lineage":["https://openalex.org/I46020346"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiqi Wang","raw_affiliation_strings":["Massachusetts Institute of Technology,Department of Aeronautics and Astronautics,Massachusetts,Cambridge,02139"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Department of Aeronautics and Astronautics,Massachusetts,Cambridge,02139","institution_ids":["https://openalex.org/I46020346","https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043088569"],"corresponding_institution_ids":["https://openalex.org/I46020346","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15012262,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9988999962806702,"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/T11416","display_name":"Numerical methods for differential equations","score":0.9879999756813049,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9790999889373779,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8860682249069214},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8042545914649963},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7598652839660645},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.6696537137031555},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.5750793218612671},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5456247925758362},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.5340717434883118},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4397454857826233},{"id":"https://openalex.org/keywords/domain-decomposition-methods","display_name":"Domain decomposition methods","score":0.41112056374549866},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3311833143234253},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16368535161018372},{"id":"https://openalex.org/keywords/finite-element-method","display_name":"Finite element method","score":0.08648702502250671}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8860682249069214},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8042545914649963},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7598652839660645},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.6696537137031555},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.5750793218612671},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5456247925758362},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.5340717434883118},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4397454857826233},{"id":"https://openalex.org/C198880260","wikidata":"https://www.wikidata.org/wiki/Q5289813","display_name":"Domain decomposition methods","level":3,"score":0.41112056374549866},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3311833143234253},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16368535161018372},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.08648702502250671},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec55821.2022.9926410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec55821.2022.9926410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2331939936","https://openalex.org/W2026512611","https://openalex.org/W1985165680","https://openalex.org/W4245497162","https://openalex.org/W2353146130","https://openalex.org/W1990817968","https://openalex.org/W2150064838","https://openalex.org/W1933089384","https://openalex.org/W2185094550","https://openalex.org/W2088823210"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3,114],"algorithm":[4,83,95],"to":[5,53,131],"accelerate":[6],"the":[7,42,54,88,94,98,103,120],"Jacobi":[8,61,137],"iteration":[9,138],"for":[10],"solving":[11],"linear":[12,99],"systems":[13,100],"of":[14,30,57,87,105,136],"equations":[15],"arising":[16,101],"from":[17,102],"structured":[18],"problems":[19],"on":[20,97,142],"graphics":[21],"processing":[22],"units":[23],"(GPUs).":[24],"Acceleration":[25],"is":[26,45,51],"achieved":[27],"by":[28],"utilization":[29],"on-chip":[31],"GPU":[32,59,89,134],"shared":[33,55,69],"memory":[34,56,70,75,90],"via":[35],"a":[36,81,124,132],"domain":[37,44],"decomposition":[38],"procedure.":[39],"In":[40],"particular,":[41],"problem":[43,122],"partitioned":[46],"into":[47],"subdomains":[48],"whose":[49],"data":[50],"copied":[52],"each":[58,67],"block.":[60],"iterations":[62],"are":[63],"performed":[64],"internally":[65],"within":[66],"block's":[68],"while":[71],"avoiding":[72],"expensive":[73],"global":[74,143],"accesses":[76],"every":[77],"iteration,":[78],"resulting":[79],"in":[80,108,117,119,128],"hierarchical":[82],"(which":[84],"takes":[85],"advantage":[86],"hierarchy).":[91],"We":[92],"investigate":[93],"performance":[96],"discretization":[104],"Poisson's":[106],"equation":[107],"1D":[109,121],"and":[110,112,123],"2D,":[111],"observe":[113],"8x":[115],"speedup":[116,127],"convergence":[118],"nearly":[125],"6x":[126],"2D":[129],"compared":[130],"conventional":[133],"implementation":[135],"which":[139],"only":[140],"relies":[141],"memory.":[144]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}