{"id":"https://openalex.org/W2003264742","doi":"https://doi.org/10.1137/120883153","title":"Stencil-Aware GPU Optimization of Iterative Solvers","display_name":"Stencil-Aware GPU Optimization of Iterative Solvers","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2003264742","doi":"https://doi.org/10.1137/120883153","mag":"2003264742"},"language":"en","primary_location":{"id":"doi:10.1137/120883153","is_oa":false,"landing_page_url":"https://doi.org/10.1137/120883153","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Scientific Computing","raw_type":"journal-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/A5022915639","display_name":"Daniel Lowell","orcid":"https://orcid.org/0000-0002-8929-7837"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel Lowell","raw_affiliation_strings":["Ohio State University"],"affiliations":[{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013102275","display_name":"Jeswin Godwin","orcid":null},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeswin Godwin","raw_affiliation_strings":["argonne national laboratory"],"affiliations":[{"raw_affiliation_string":"argonne national laboratory","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047990794","display_name":"Justin Holewinski","orcid":null},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Holewinski","raw_affiliation_strings":["argonne national laboratory"],"affiliations":[{"raw_affiliation_string":"argonne national laboratory","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057224950","display_name":"Deepan Karthik","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deepan Karthik","raw_affiliation_strings":["Ohio State University"],"affiliations":[{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046644369","display_name":"Chekuri Choudary","orcid":null},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chekuri Choudary","raw_affiliation_strings":["argonne national laboratory"],"affiliations":[{"raw_affiliation_string":"argonne national laboratory","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074668365","display_name":"Azamat Mametjanov","orcid":"https://orcid.org/0000-0001-7316-4231"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Azamat Mametjanov","raw_affiliation_strings":["Ohio State University"],"affiliations":[{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079346036","display_name":"Boyana Norris","orcid":"https://orcid.org/0000-0001-5811-9731"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boyana Norris","raw_affiliation_strings":["Ohio State University"],"affiliations":[{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082770727","display_name":"Gerald Sabin","orcid":"https://orcid.org/0000-0002-8672-4071"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerald Sabin","raw_affiliation_strings":["Ohio State University"],"affiliations":[{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027517817","display_name":"P. Sadayappan","orcid":"https://orcid.org/0000-0002-4737-2034"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"P. Sadayappan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5028477249","display_name":"J. Sarich","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jason Sarich","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5022915639"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":3.2629,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.91766338,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"35","issue":"5","first_page":"S209","last_page":"S228"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9997000098228455,"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":0.9997000098228455,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991000294685364,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9825999736785889,"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/stencil","display_name":"Stencil","score":0.9468705654144287},{"id":"https://openalex.org/keywords/krylov-subspace","display_name":"Krylov subspace","score":0.6692839860916138},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6620475053787231},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6267347931861877},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6114900708198547},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.5913633108139038},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.516707181930542},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.5034889578819275},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.4993007183074951},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.4975002110004425},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.49045369029045105},{"id":"https://openalex.org/keywords/matrix-free-methods","display_name":"Matrix-free methods","score":0.44544094800949097},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4428040385246277},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38948214054107666},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32465097308158875},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.31429344415664673}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.9468705654144287},{"id":"https://openalex.org/C147060835","wikidata":"https://www.wikidata.org/wiki/Q1757151","display_name":"Krylov subspace","level":3,"score":0.6692839860916138},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6620475053787231},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6267347931861877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6114900708198547},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.5913633108139038},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.516707181930542},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.5034889578819275},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.4993007183074951},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.4975002110004425},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.49045369029045105},{"id":"https://openalex.org/C54219892","wikidata":"https://www.wikidata.org/wiki/Q4080929","display_name":"Matrix-free methods","level":4,"score":0.44544094800949097},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4428040385246277},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38948214054107666},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32465097308158875},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.31429344415664673},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1137/120883153","is_oa":false,"landing_page_url":"https://doi.org/10.1137/120883153","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Scientific Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W90568776","https://openalex.org/W1480928214","https://openalex.org/W1480958225","https://openalex.org/W1515687962","https://openalex.org/W1569090332","https://openalex.org/W1876394617","https://openalex.org/W1997614470","https://openalex.org/W2016888570","https://openalex.org/W2020215844","https://openalex.org/W2091908315","https://openalex.org/W2099021415","https://openalex.org/W2103877122","https://openalex.org/W2120768584","https://openalex.org/W2124007994","https://openalex.org/W2141331848","https://openalex.org/W2148643483","https://openalex.org/W2154786353","https://openalex.org/W2156560068","https://openalex.org/W2162322364","https://openalex.org/W2585550685","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2375913285","https://openalex.org/W4225411471","https://openalex.org/W1599640686","https://openalex.org/W2155596814","https://openalex.org/W4285409149","https://openalex.org/W810196809","https://openalex.org/W2084578046","https://openalex.org/W1835670156","https://openalex.org/W4381050447","https://openalex.org/W582364689"],"abstract_inverted_index":{"Numerical":[0],"solutions":[1],"of":[2,19,30,41,77,90,97],"nonlinear":[3],"partial":[4],"differential":[5],"equations":[6],"frequently":[7],"rely":[8],"on":[9,43,94],"iterative":[10,58,81],"Newton--Krylov":[11],"methods,":[12],"which":[13],"linearize":[14],"a":[15,20,23],"finite-difference":[16],"stencil-based":[17,99],"discretization":[18],"problem,":[21],"producing":[22],"sparse":[24,69],"matrix":[25,70,100],"with":[26],"regular":[27],"structure.":[28],"Knowledge":[29],"this":[31,62],"structure":[32,72],"can":[33],"be":[34],"used":[35,57],"to":[36,68],"exploit":[37],"parallelism":[38],"and":[39,47,74,101],"locality":[40],"reference":[42],"modern":[44],"cache-based":[45],"multi":[46],"manycore":[48],"architectures,":[49],"achieving":[50],"high":[51],"performance":[52],"for":[53],"computations":[54],"underlying":[55,80],"commonly":[56],"linear":[59,82],"solvers.":[60],"In":[61],"paper":[63],"we":[64],"describe":[65,88],"our":[66,75],"approach":[67],"data":[71],"design":[73],"implementation":[76],"the":[78,98],"kernels":[79],"solvers":[83],"in":[84],"PETSc.":[85],"We":[86],"also":[87],"autotuning":[89],"CUDA":[91],"implementations":[92],"based":[93],"high-level":[95],"descriptions":[96],"vector":[102],"operations.":[103]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
