{"id":"https://openalex.org/W3048132182","doi":"https://doi.org/10.1145/3404397.3404416","title":"Parallel Shift-Invert Spectrum Slicing on Distributed Architectures with GPU Accelerators","display_name":"Parallel Shift-Invert Spectrum Slicing on Distributed Architectures with GPU Accelerators","publication_year":2020,"publication_date":"2020-08-09","ids":{"openalex":"https://openalex.org/W3048132182","doi":"https://doi.org/10.1145/3404397.3404416","mag":"3048132182"},"language":"en","primary_location":{"id":"doi:10.1145/3404397.3404416","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3404397.3404416","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3404397.3404416","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"49th International Conference on Parallel Processing - ICPP","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/10.1145/3404397.3404416","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007317870","display_name":"David B. Williams\u2010Young","orcid":"https://orcid.org/0000-0003-2735-3706"},"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":"David B. Williams-Young","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077547409","display_name":"Chao Yang","orcid":"https://orcid.org/0000-0001-7172-7539"},"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":"Chao Yang","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, USA","institution_ids":["https://openalex.org/I148283060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148283060"],"apc_list":null,"apc_paid":null,"fwci":0.944,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73147365,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9961000084877014,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computer-science","display_name":"Computer science","score":0.8368737697601318},{"id":"https://openalex.org/keywords/slicing","display_name":"Slicing","score":0.7550194263458252},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.709739089012146},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.686382532119751},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6747053265571594},{"id":"https://openalex.org/keywords/concurrency","display_name":"Concurrency","score":0.6100819110870361},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5723612308502197},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.43508023023605347},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.42641279101371765},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.32481637597084045},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.12633204460144043},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11657586693763733},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08695104718208313}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8368737697601318},{"id":"https://openalex.org/C2776190703","wikidata":"https://www.wikidata.org/wiki/Q488148","display_name":"Slicing","level":2,"score":0.7550194263458252},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.709739089012146},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.686382532119751},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6747053265571594},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.6100819110870361},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5723612308502197},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.43508023023605347},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.42641279101371765},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32481637597084045},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.12633204460144043},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11657586693763733},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08695104718208313},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3404397.3404416","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3404397.3404416","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3404397.3404416","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"49th International Conference on Parallel Processing - ICPP","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3404397.3404416","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3404397.3404416","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3404397.3404416","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"49th International Conference on Parallel Processing - ICPP","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5899999737739563}],"awards":[{"id":"https://openalex.org/G3232922872","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G6859237865","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8052219770","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320337506","funder_display_name":"Advanced Scientific Computing Research"},{"id":"https://openalex.org/G8253304997","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320317220","display_name":"National Energy Research Scientific Computing Center","ror":"https://ror.org/05v3mvq14"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3048132182.pdf","grobid_xml":"https://content.openalex.org/works/W3048132182.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W625657276","https://openalex.org/W753054573","https://openalex.org/W995198334","https://openalex.org/W1491884104","https://openalex.org/W1506690472","https://openalex.org/W1974507967","https://openalex.org/W1975818677","https://openalex.org/W1990238127","https://openalex.org/W2013424510","https://openalex.org/W2021231414","https://openalex.org/W2035080386","https://openalex.org/W2037502605","https://openalex.org/W2044489142","https://openalex.org/W2051142108","https://openalex.org/W2051297414","https://openalex.org/W2053266474","https://openalex.org/W2053999255","https://openalex.org/W2059076129","https://openalex.org/W2086160340","https://openalex.org/W2137541800","https://openalex.org/W2139774022","https://openalex.org/W2141331848","https://openalex.org/W2148678374","https://openalex.org/W2175127010","https://openalex.org/W2275630370","https://openalex.org/W2314709240","https://openalex.org/W2523376728","https://openalex.org/W2564758025","https://openalex.org/W2610012734","https://openalex.org/W2752576738","https://openalex.org/W2774512715","https://openalex.org/W2782740643","https://openalex.org/W2887674375","https://openalex.org/W2887777878","https://openalex.org/W2888754879","https://openalex.org/W2951691564","https://openalex.org/W2954782233","https://openalex.org/W2962939379","https://openalex.org/W2967701142","https://openalex.org/W2973084438","https://openalex.org/W2983126917","https://openalex.org/W3098493705","https://openalex.org/W3104616705","https://openalex.org/W4229666556","https://openalex.org/W4230094279","https://openalex.org/W4231150350"],"related_works":["https://openalex.org/W112744582","https://openalex.org/W2361361118","https://openalex.org/W2516240846","https://openalex.org/W1597592026","https://openalex.org/W94000989","https://openalex.org/W647346242","https://openalex.org/W2000058275","https://openalex.org/W2590733122","https://openalex.org/W3179800311","https://openalex.org/W2007500630"],"abstract_inverted_index":{"The":[0,144],"solution":[1],"of":[2,62,72,83,97,115,140,167,189],"large":[3,39,178],"scale":[4],"eigenvalue":[5],"problems":[6],"(EVP)":[7],"is":[8,146],"often":[9],"the":[10,70,81,95,110,123,141,165,187],"computational":[11],"bottleneck":[12],"for":[13,80,126,164],"many":[14,127],"scientific":[15],"and":[16,26,45,112],"engineering":[17],"applications.":[18],"Traditional":[19],"eigensolvers,":[20,157],"such":[21,74],"as":[22,75],"direct":[23],"(e.g.":[24,29],"ScaLAPACK)":[25],"Krylov":[27],"subspace":[28],"Lanczos)":[30],"methods,":[31],"have":[32],"struggled":[33],"in":[34,51,58,103,159,175],"achieving":[35],"high":[36],"scalability":[37],"on":[38,69,100,177,194],"computing":[40,179],"resources":[41],"due":[42],"to":[43,65,108,135,171],"communication":[44,111],"synchronization":[46,113],"bottlenecks":[47,114],"which":[48,67,131,149,162],"are":[49],"inherent":[50],"their":[52,84],"implementation.":[53],"This":[54],"includes":[55],"a":[56,147,160],"difficulty":[57],"developing":[59],"well-performing":[60],"ports":[61],"these":[63],"algorithms":[64],"architectures":[66],"rely":[68],"use":[71],"accelerators,":[73],"graphics":[76],"processing":[77],"units":[78],"(GPU),":[79],"majority":[82],"floating":[85,152],"point":[86,153],"operations.":[87],"Recently,":[88],"there":[89],"has":[90],"been":[91],"significant":[92],"research":[93],"into":[94],"development":[96],"eigensolvers":[98],"based":[99],"spectrum":[101,106,120,192],"slicing,":[102,107],"particular":[104],"shift-invert":[105,191],"alleviate":[109],"traditional":[116,156],"eigensolvers.":[117],"In":[118,181],"general,":[119],"slicing":[121,193],"trades":[122],"global":[124],"EVP":[125],"smaller,":[128],"independent":[129],"EVPs":[130],"may":[132],"be":[133],"combined":[134],"assemble":[136],"some":[137],"desired":[138],"subset":[139],"entire":[142],"eigenspectrum.":[143],"result":[145],"method":[148],"utilizes":[150],"more":[151],"operations":[154],"than":[155],"but":[158],"way":[161],"allows":[163],"expression":[166],"massive":[168],"concurrency":[169],"leading":[170],"an":[172],"overall":[173],"improvement":[174],"time-to-solution":[176],"resources.":[180],"this":[182],"work,":[183],"we":[184],"will":[185],"examine":[186],"performance":[188],"parallel":[190],"modern":[195],"GPU":[196],"clusters":[197],"using":[198],"state-of-the-art":[199],"linear":[200],"algebra":[201],"software.":[202]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-28T08:01:55.173337","created_date":"2025-10-10T00:00:00"}
