{"id":"https://openalex.org/W4416004303","doi":"https://doi.org/10.1145/3731599.3767501","title":"KDRSolvers: Scalable, Flexible, Task-Oriented Krylov Solvers","display_name":"KDRSolvers: Scalable, Flexible, Task-Oriented Krylov Solvers","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416004303","doi":"https://doi.org/10.1145/3731599.3767501"},"language":null,"primary_location":{"id":"doi:10.1145/3731599.3767501","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731599.3767501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","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/A5025358309","display_name":"David K. Zhang","orcid":"https://orcid.org/0000-0003-3379-4890"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Kai Zhang","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3379-4890","affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047980263","display_name":"Rohan Yadav","orcid":"https://orcid.org/0000-0003-0746-066X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohan Yadav","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0746-066X","affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087402475","display_name":"Alex Aiken","orcid":"https://orcid.org/0000-0002-3723-9555"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Aiken","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3723-9555","affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041886781","display_name":"Fredrik Kj\u00f8lstad","orcid":"https://orcid.org/0000-0002-2267-903X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fredrik Kjolstad","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2267-903X","affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005774998","display_name":"Sean Treichler","orcid":"https://orcid.org/0000-0003-2189-4026"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sean Treichler","raw_affiliation_strings":["NVIDIA Corporation, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2189-4026","affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.34638315,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1351","last_page":"1365"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.7475000023841858,"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":0.7475000023841858,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.07750000059604645,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.049400001764297485,"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/krylov-subspace","display_name":"Krylov subspace","score":0.7470999956130981},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5680000185966492},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5613999962806702},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.5572999715805054},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5371000170707703},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.515500009059906},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.48100000619888306},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4666000008583069}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7470999956130981},{"id":"https://openalex.org/C147060835","wikidata":"https://www.wikidata.org/wiki/Q1757151","display_name":"Krylov subspace","level":3,"score":0.7470999956130981},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5680000185966492},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5613999962806702},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.5572999715805054},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5371000170707703},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.515500009059906},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.49380001425743103},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.48100000619888306},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4666000008583069},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4593000113964081},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4465999901294708},{"id":"https://openalex.org/C2777168461","wikidata":"https://www.wikidata.org/wiki/Q42196253","display_name":"Set operations","level":3,"score":0.42739999294281006},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40070000290870667},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.3416999876499176},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.3368000090122223},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.265500009059906},{"id":"https://openalex.org/C147358964","wikidata":"https://www.wikidata.org/wiki/Q1200992","display_name":"Abstraction layer","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731599.3767501","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731599.3767501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","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":16,"referenced_works":["https://openalex.org/W1525132831","https://openalex.org/W1990090459","https://openalex.org/W2008940670","https://openalex.org/W2018850201","https://openalex.org/W2103607061","https://openalex.org/W2121893797","https://openalex.org/W2140153041","https://openalex.org/W2155216327","https://openalex.org/W2316564661","https://openalex.org/W2536203406","https://openalex.org/W3000323728","https://openalex.org/W3209526830","https://openalex.org/W4231715478","https://openalex.org/W4248722156","https://openalex.org/W4289464760","https://openalex.org/W4327911434"],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"KDRSolvers,":[2,104],"a":[3,35,137],"novel":[4],"framework":[5],"for":[6,53],"representing":[7],"sparse":[8,27],"linear":[9],"systems":[10,82],"and":[11,39,55,86,92,113,119],"implementing":[12],"Krylov":[13],"subspace":[14],"methods":[15],"on":[16,128],"modern":[17],"heterogeneous":[18],"supercomputers.":[19],"KDRSolvers":[20,47,78],"uses":[21],"dependent":[22],"partitioning":[23,66],"to":[24,48,68,117,125,136],"uniformly":[25],"represent":[26],"matrix":[28,85],"storage":[29,60],"formats":[30],"as":[31],"abstract":[32],"maps":[33],"between":[34],"matrix\u2019s":[36],"domain,":[37],"range,":[38],"set":[40],"of":[41,58,103],"nonzero":[42],"entries.":[43],"This":[44],"abstraction":[45],"enables":[46],"define":[49],"universal":[50],"co-partitioning":[51],"operators":[52],"matrices":[54],"vectors":[56],"independent":[57],"underlying":[59],"formats,":[61],"allowing":[62],"changes":[63],"in":[64,83,94,140],"data":[65,88,99],"strategies":[67],"automatically":[69],"propagate":[70],"through":[71],"an":[72],"application":[73],"with":[74,123],"no":[75],"code":[76],"modification.":[77],"also":[79],"introduces":[80],"multi-operator":[81],"which":[84],"vector":[87],"can":[89],"be":[90],"ingested":[91],"processed":[93],"multiple":[95],"non-contiguous":[96],"pieces":[97],"without":[98],"movement.":[100],"Our":[101],"implementation":[102,133],"targeting":[105],"the":[106,129],"Legion":[107],"runtime":[108],"system,":[109],"achieves":[110,134],"greater":[111],"flexibility":[112],"competitive":[114],"performance":[115],"compared":[116],"PETSc":[118],"Trilinos.":[120],"In":[121],"experiments":[122],"up":[124,135],"1,024":[126],"GPUs":[127],"Lassen":[130],"supercomputer,":[131],"our":[132],"9.6%":[138],"reduction":[139],"execution":[141],"time":[142],"per":[143],"iteration.":[144]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-07T00:00:00"}