{"id":"https://openalex.org/W4399304221","doi":"https://doi.org/10.1145/3650200.3656614","title":"Matrix-free SBP-SAT finite difference methods and the multigrid preconditioner on GPUs","display_name":"Matrix-free SBP-SAT finite difference methods and the multigrid preconditioner on GPUs","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399304221","doi":"https://doi.org/10.1145/3650200.3656614"},"language":"en","primary_location":{"id":"doi:10.1145/3650200.3656614","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650200.3656614","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650200.3656614","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th ACM International Conference on Supercomputing","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/10.1145/3650200.3656614","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004377601","display_name":"Alexandre Chen","orcid":"https://orcid.org/0000-0003-1927-2965"},"institutions":[{"id":"https://openalex.org/I181233156","display_name":"University of Oregon","ror":"https://ror.org/0293rh119","country_code":"US","type":"education","lineage":["https://openalex.org/I181233156"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alexandre Chen","raw_affiliation_strings":["Department of Computer Science, University of Oregon, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Oregon, United States","institution_ids":["https://openalex.org/I181233156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001204161","display_name":"Brittany A. Erickson","orcid":"https://orcid.org/0000-0001-9457-8572"},"institutions":[{"id":"https://openalex.org/I181233156","display_name":"University of Oregon","ror":"https://ror.org/0293rh119","country_code":"US","type":"education","lineage":["https://openalex.org/I181233156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brittany A. Erickson","raw_affiliation_strings":["Department of Computer Science &amp; Department of Earth Sciences, University of Oregon, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science &amp; Department of Earth Sciences, University of Oregon, USA","institution_ids":["https://openalex.org/I181233156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056180795","display_name":"Jeremy E. Kozdon","orcid":"https://orcid.org/0000-0002-2493-4292"},"institutions":[{"id":"https://openalex.org/I35364215","display_name":"Naval Postgraduate School","ror":"https://ror.org/033yfkj90","country_code":"US","type":"education","lineage":["https://openalex.org/I1330347796","https://openalex.org/I3130687028","https://openalex.org/I35364215"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeremy E. Kozdon","raw_affiliation_strings":["Department of Applied Mathematics, Naval Postgraduate School, USA"],"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, Naval Postgraduate School, USA","institution_ids":["https://openalex.org/I35364215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090972683","display_name":"Jee Choi","orcid":"https://orcid.org/0000-0002-6938-8221"},"institutions":[{"id":"https://openalex.org/I181233156","display_name":"University of Oregon","ror":"https://ror.org/0293rh119","country_code":"US","type":"education","lineage":["https://openalex.org/I181233156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jee Choi","raw_affiliation_strings":["Department of Computer Science, University of Oregon, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Oregon, United States","institution_ids":["https://openalex.org/I181233156"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5004377601"],"corresponding_institution_ids":["https://openalex.org/I181233156"],"apc_list":null,"apc_paid":null,"fwci":0.3954,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53445314,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"400","last_page":"412"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9941999912261963,"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":0.9936000108718872,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/preconditioner","display_name":"Preconditioner","score":0.9278385639190674},{"id":"https://openalex.org/keywords/multigrid-method","display_name":"Multigrid method","score":0.8376811742782593},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6539043188095093},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.6269667744636536},{"id":"https://openalex.org/keywords/conjugate-gradient-method","display_name":"Conjugate gradient method","score":0.5762760639190674},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.5688249468803406},{"id":"https://openalex.org/keywords/finite-difference","display_name":"Finite difference","score":0.4967527985572815},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.47816023230552673},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.462878942489624},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.45297354459762573},{"id":"https://openalex.org/keywords/coefficient-matrix","display_name":"Coefficient matrix","score":0.43158185482025146},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.43112149834632874},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4187094569206238},{"id":"https://openalex.org/keywords/partial-differential-equation","display_name":"Partial differential equation","score":0.3874843418598175},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.333702951669693},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3263213038444519},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28026461601257324},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.09067171812057495},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.07975783944129944}],"concepts":[{"id":"https://openalex.org/C167431342","wikidata":"https://www.wikidata.org/wiki/Q1754327","display_name":"Preconditioner","level":3,"score":0.9278385639190674},{"id":"https://openalex.org/C137119250","wikidata":"https://www.wikidata.org/wiki/Q1413101","display_name":"Multigrid method","level":3,"score":0.8376811742782593},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6539043188095093},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6269667744636536},{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.5762760639190674},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.5688249468803406},{"id":"https://openalex.org/C181330731","wikidata":"https://www.wikidata.org/wiki/Q2068418","display_name":"Finite difference","level":2,"score":0.4967527985572815},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.47816023230552673},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.462878942489624},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.45297354459762573},{"id":"https://openalex.org/C60866291","wikidata":"https://www.wikidata.org/wiki/Q5140577","display_name":"Coefficient matrix","level":3,"score":0.43158185482025146},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.43112149834632874},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4187094569206238},{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.3874843418598175},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.333702951669693},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3263213038444519},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28026461601257324},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.09067171812057495},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.07975783944129944},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3650200.3656614","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650200.3656614","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650200.3656614","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3650200.3656614","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650200.3656614","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650200.3656614","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399304221.pdf"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W96454744","https://openalex.org/W610778723","https://openalex.org/W1525132831","https://openalex.org/W1770498610","https://openalex.org/W1965855805","https://openalex.org/W1972161707","https://openalex.org/W1972670182","https://openalex.org/W1979962898","https://openalex.org/W1985876447","https://openalex.org/W1995649289","https://openalex.org/W1997542937","https://openalex.org/W2029553973","https://openalex.org/W2039789965","https://openalex.org/W2046273006","https://openalex.org/W2049991352","https://openalex.org/W2051465806","https://openalex.org/W2065978762","https://openalex.org/W2072132691","https://openalex.org/W2072625243","https://openalex.org/W2078794610","https://openalex.org/W2083887298","https://openalex.org/W2120575449","https://openalex.org/W2120920736","https://openalex.org/W2128539477","https://openalex.org/W2128679183","https://openalex.org/W2128853364","https://openalex.org/W2130320670","https://openalex.org/W2162283062","https://openalex.org/W2162447272","https://openalex.org/W2305968769","https://openalex.org/W2335317371","https://openalex.org/W2622491854","https://openalex.org/W2725337818","https://openalex.org/W2774096293","https://openalex.org/W2891818448","https://openalex.org/W2950920252","https://openalex.org/W2996372729","https://openalex.org/W2996807164","https://openalex.org/W3003365364","https://openalex.org/W3004059730","https://openalex.org/W3015498000","https://openalex.org/W3033540019","https://openalex.org/W3093098265","https://openalex.org/W3122602094","https://openalex.org/W3134033554","https://openalex.org/W3138530731","https://openalex.org/W3157991109","https://openalex.org/W4238630733","https://openalex.org/W4253172477","https://openalex.org/W4293567396","https://openalex.org/W4294959428","https://openalex.org/W4318704660","https://openalex.org/W6949034314"],"related_works":["https://openalex.org/W4389317411","https://openalex.org/W1492522302","https://openalex.org/W2120298265","https://openalex.org/W2096454229","https://openalex.org/W2159515580","https://openalex.org/W2042199958","https://openalex.org/W2103149966","https://openalex.org/W2081820376","https://openalex.org/W2177482563","https://openalex.org/W2740546554"],"abstract_inverted_index":{"Summation-by-parts":[0],"(SBP)":[1],"finite":[2],"difference":[3],"methods":[4,109,142],"are":[5],"widely":[6],"used":[7],"in":[8,79,193,205,214],"scientific":[9],"applications":[10],"alongside":[11],"a":[12,91,115,158],"special":[13],"treatment":[14],"of":[15,28,52,160,166,186],"boundary":[16],"conditions":[17],"through":[18],"the":[19,25,65,84,175,179,194,224],"simultaneous-approximate-term":[20],"(SAT)":[21],"technique":[22],"which":[23],"enables":[24],"valuable":[26],"proof":[27],"numerical":[29,66,99],"stability.":[30],"Our":[31],"work":[32,216],"is":[33,90],"motivated":[34],"by":[35,41],"multi-scale":[36],"earthquake":[37],"cycle":[38],"simulations":[39,222],"described":[40],"partial":[42],"differential":[43],"equations":[44,53],"(PDEs)":[45],"whose":[46,138],"discretizations":[47],"lead":[48],"to":[49,63,190],"huge":[50],"systems":[51],"and":[54,60,198,208],"often":[55],"rely":[56],"on":[57,110],"iterative":[58],"schemes":[59],"parallel":[61],"implementations":[62],"make":[64,143],"solutions":[67],"tractable.":[68],"In":[69],"this":[70,144,215],"study,":[71],"we":[72],"consider":[73],"2D,":[74],"variable":[75],"coefficient":[76],"elliptic":[77],"PDEs":[78],"complex":[80],"geometries":[81],"discretized":[82],"with":[83],"SBP-SAT":[85,108,225],"method.":[86,226],"The":[87,162,211],"multigrid":[88],"method":[89,121,169,212],"well-known,":[92],"efficient":[93],"solver":[94,220],"or":[95],"preconditioner":[96],"for":[97,107,135,178,221],"traditional":[98,141],"discretizations,":[100],"but":[101,147],"they":[102],"have":[103],"not":[104],"been":[105],"well-developed":[106],"HPC":[111],"platforms.":[112],"We":[113,126],"propose":[114],"custom":[116],"geometric-multigrid":[117],"preconditioned":[118],"conjugate-gradient":[119],"(MGCG)":[120],"that":[122,148],"applies":[123],"SBP-preserving":[124],"interpolations.":[125],"then":[127],"present":[128],"novel,":[129],"matrix-free":[130,163],"GPU":[131,164],"kernels":[132],"designed":[133],"specifically":[134],"SBP":[136],"operators":[137],"differences":[139],"from":[140],"task":[145],"nontrivial":[146],"perform":[149],"3":[150],"\u00d7":[151,172],"faster":[152,173],"than":[153,174],"SpMV":[154,176],"while":[155],"requiring":[156],"only":[157],"fraction":[159],"memory.":[161],"implementation":[165,201],"our":[167,200],"MGCG":[168],"performs":[170],"5":[171],"counterpart":[177],"largest":[180],"problems":[181],"considered":[182],"(67":[183],"million":[184],"degrees":[185],"freedom).":[187],"When":[188],"compared":[189],"off-the-shelf":[191],"solvers":[192],"state-of-the-art":[195],"libraries":[196],"PETSc":[197],"AmgX,":[199],"achieves":[202],"superior":[203],"performance":[204],"both":[206],"iterations":[207],"overall":[209],"runtime.":[210],"presented":[213],"offers":[217],"an":[218],"attractive":[219],"using":[223]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
