{"id":"https://openalex.org/W2137571283","doi":"https://doi.org/10.1145/2464996.2465444","title":"G-Charm","display_name":"G-Charm","publication_year":2013,"publication_date":"2013-05-28","ids":{"openalex":"https://openalex.org/W2137571283","doi":"https://doi.org/10.1145/2464996.2465444","mag":"2137571283"},"language":"en","primary_location":{"id":"doi:10.1145/2464996.2465444","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2464996.2465444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th international ACM conference on International conference on supercomputing","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/A5001834469","display_name":"Rama K. Vasudevan","orcid":"https://orcid.org/0000-0003-4692-8579"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"R. Vasudevan","raw_affiliation_strings":["Indian Institute of Science, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078057384","display_name":"Sathish Vadhiyar","orcid":"https://orcid.org/0000-0002-5476-8328"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sathish S. Vadhiyar","raw_affiliation_strings":["Indian Institute of Science, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051465480","display_name":"Laxmikant V. Kal\u00e9","orcid":"https://orcid.org/0000-0001-9673-8445"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laxmikant V. Kal\u00e9","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA","University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5106,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.89790997,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"349","last_page":"358"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987000226974487,"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":0.8306798338890076},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7712221741676331},{"id":"https://openalex.org/keywords/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.6459146738052368},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5881687998771667},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5756989121437073},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.46046754717826843},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.43170350790023804},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07831525802612305}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8306798338890076},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7712221741676331},{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.6459146738052368},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5881687998771667},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5756989121437073},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.46046754717826843},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.43170350790023804},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07831525802612305},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2464996.2465444","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2464996.2465444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th international ACM conference on International conference on supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W57243869","https://openalex.org/W1004371317","https://openalex.org/W2015935981","https://openalex.org/W2026600854","https://openalex.org/W2050612421","https://openalex.org/W2070961300","https://openalex.org/W2087354108","https://openalex.org/W2111354435","https://openalex.org/W2121893797","https://openalex.org/W2122570236","https://openalex.org/W2141514639","https://openalex.org/W2159792012","https://openalex.org/W2162322364","https://openalex.org/W2167173222","https://openalex.org/W3145412265","https://openalex.org/W4239059712","https://openalex.org/W4255468259","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2403987929","https://openalex.org/W2039814159","https://openalex.org/W2374847384","https://openalex.org/W2063512590","https://openalex.org/W2107649022","https://openalex.org/W2356488190","https://openalex.org/W2966537581","https://openalex.org/W2079508979","https://openalex.org/W604331851","https://openalex.org/W2172051598"],"abstract_inverted_index":{"The":[0,94,109],"effective":[1,15],"use":[2,17],"of":[3,12,18,30,53,87,117,126,158,204,215],"GPUs":[4],"for":[5,67,84,106],"accelerating":[6],"applications":[7,90],"depends":[8],"on":[9,50,91,98,119,148],"a":[10,76,100,160,168,219],"number":[11],"factors":[13],"including":[14],"asynchronous":[16],"heterogeneous":[19],"resources,":[20],"reducing":[21,38],"memory":[22],"transfer":[23],"between":[24],"CPU":[25,120],"and":[26,41,57,64,104,121,137,151,163,183],"GPU,":[27],"increasing":[28],"occupancy":[29],"GPU":[31,39,122,130,135],"kernels,":[32],"overlapping":[33],"data":[34,127,132],"transfers":[35],"with":[36,79,178,218],"computations,":[37],"idling":[40],"kernel":[42],"optimizations.":[43],"Overcoming":[44],"these":[45],"challenges":[46],"require":[47],"considerable":[48],"effort":[49],"the":[51,54],"part":[52],"application":[55],"developers":[56],"most":[58],"optimization":[59],"strategies":[60],"are":[61],"often":[62],"proposed":[63],"tuned":[65],"specifically":[66],"individual":[68],"applications.":[69,108],"In":[70],"this":[71],"paper,":[72],"we":[73,193],"present":[74,128],"G-Charm,":[75],"generic":[77,191],"framework":[78,95,113,147],"an":[80,213],"adaptive":[81],"runtime":[82,105],"system":[83],"efficient":[85],"execution":[86],"message-driven":[88,101],"parallel":[89,107,164,181],"hybrid":[92],"systems.":[93],"is":[96],"based":[97],"Charm++,":[99],"programming":[102],"environment":[103],"techniques":[110],"in":[111,129,134],"our":[112,146,190],"include":[114],"dynamic":[115],"scheduling":[116],"work":[118],"cores,":[123],"maximizing":[124],"reuse":[125],"memory,":[131,136],"management":[133],"combining":[138],"multiple":[139],"kernels.":[140],"We":[141,206],"have":[142],"presented":[143],"results":[144],"using":[145,155],"Tesla":[149],"S1070":[150],"Fermi":[152],"C2070":[153],"systems":[154],"three":[156],"classes":[157],"applications:":[159],"highly":[161,184],"regular":[162,169],"2D":[165],"Jacobi":[166],"solver,":[167],"dense":[170],"matrix":[171],"Cholesky":[172,216],"factorization":[173,217],"representing":[174],"linear":[175],"algebra":[176],"computations":[177,182],"dependencies":[179],"among":[180],"irregular":[185],"molecular":[186],"dynamics":[187],"simulations.":[188],"With":[189],"framework,":[192],"obtain":[194,208],"1.5":[195],"to":[196],"15":[197],"times":[198],"improvement":[199,211],"over":[200,212],"previous":[201],"GPU-based":[202],"implementation":[203,214],"Charm++.":[205],"also":[207],"about":[209],"14\\%":[210],"static":[220],"work-distribution":[221],"scheme.":[222]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2016-06-24T00:00:00"}