{"id":"https://openalex.org/W4386709682","doi":"https://doi.org/10.1145/3605573.3605642","title":"Improving the Scaling of an Asynchronous Many-Task Runtime with a Lightweight Communication Engine","display_name":"Improving the Scaling of an Asynchronous Many-Task Runtime with a Lightweight Communication Engine","publication_year":2023,"publication_date":"2023-08-07","ids":{"openalex":"https://openalex.org/W4386709682","doi":"https://doi.org/10.1145/3605573.3605642"},"language":"en","primary_location":{"id":"doi:10.1145/3605573.3605642","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3605573.3605642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd International Conference on Parallel Processing","raw_type":"proceedings-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/A5092863049","display_name":"Omri Mor","orcid":"https://orcid.org/0009-0002-0969-3897"},"institutions":[{"id":"https://openalex.org/I2801919071","display_name":"University of Illinois System","ror":"https://ror.org/05e94g991","country_code":"US","type":"education","lineage":["https://openalex.org/I2801919071"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Omri Mor","raw_affiliation_strings":["University of Illinois, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois, USA","institution_ids":["https://openalex.org/I2801919071"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010055736","display_name":"George Bosilca","orcid":"https://orcid.org/0000-0003-2411-8495"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Bosilca","raw_affiliation_strings":["Innovative Computing Laboratory, University of Tennessee, USA"],"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041731995","display_name":"Marc Snir","orcid":"https://orcid.org/0000-0002-3504-2468"},"institutions":[{"id":"https://openalex.org/I2801919071","display_name":"University of Illinois System","ror":"https://ror.org/05e94g991","country_code":"US","type":"education","lineage":["https://openalex.org/I2801919071"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marc Snir","raw_affiliation_strings":["University of Illinois, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois, USA","institution_ids":["https://openalex.org/I2801919071"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5092863049"],"corresponding_institution_ids":["https://openalex.org/I2801919071"],"apc_list":null,"apc_paid":null,"fwci":3.3996,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.93184673,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"153","last_page":"162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","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/T10829","display_name":"Interconnection Networks and Systems","score":0.9987999796867371,"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/asynchronous-communication","display_name":"Asynchronous communication","score":0.8827059268951416},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8591561913490295},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5111785531044006},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5086389780044556},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5072471499443054},{"id":"https://openalex.org/keywords/execution-model","display_name":"Execution model","score":0.5005528926849365},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.48156240582466125},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4786292612552643},{"id":"https://openalex.org/keywords/infiniband","display_name":"InfiniBand","score":0.4693516194820404},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4639520049095154},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42496001720428467},{"id":"https://openalex.org/keywords/remote-direct-memory-access","display_name":"Remote direct memory access","score":0.4223445653915405},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.32435303926467896},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1654624044895172},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08069497346878052}],"concepts":[{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.8827059268951416},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8591561913490295},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5111785531044006},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5086389780044556},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5072471499443054},{"id":"https://openalex.org/C2776834041","wikidata":"https://www.wikidata.org/wiki/Q25346349","display_name":"Execution model","level":2,"score":0.5005528926849365},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.48156240582466125},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4786292612552643},{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.4693516194820404},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4639520049095154},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42496001720428467},{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.4223445653915405},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32435303926467896},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1654624044895172},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08069497346878052},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3605573.3605642","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3605573.3605642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5600000023841858}],"awards":[{"id":"https://openalex.org/G5321991598","display_name":null,"funder_award_id":"1908144, 1909015","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1825216778","https://openalex.org/W1929619420","https://openalex.org/W1962931680","https://openalex.org/W2063377848","https://openalex.org/W2079577430","https://openalex.org/W2087440962","https://openalex.org/W2112769850","https://openalex.org/W2122747952","https://openalex.org/W2133250609","https://openalex.org/W2159826908","https://openalex.org/W2168612748","https://openalex.org/W2534929279","https://openalex.org/W2747147038","https://openalex.org/W2765106570","https://openalex.org/W2798525482","https://openalex.org/W2885289883","https://openalex.org/W2896801938","https://openalex.org/W2898627297","https://openalex.org/W2983608561","https://openalex.org/W2986726791","https://openalex.org/W3036007422","https://openalex.org/W3082389863","https://openalex.org/W3097443356","https://openalex.org/W3161950341","https://openalex.org/W3173970356","https://openalex.org/W4242589337","https://openalex.org/W4248722156","https://openalex.org/W4286858025","https://openalex.org/W4321636543"],"related_works":["https://openalex.org/W1978254186","https://openalex.org/W4245217724","https://openalex.org/W4390917331","https://openalex.org/W1984788566","https://openalex.org/W4253931064","https://openalex.org/W3166154920","https://openalex.org/W2154082760","https://openalex.org/W1964981582","https://openalex.org/W4282599985","https://openalex.org/W2139382794"],"abstract_inverted_index":{"There":[0],"is":[1,66,82],"a":[2,61,83,93,104],"growing":[3],"interest":[4],"in":[5,89,102],"Asynchronous":[6],"Many-Task":[7],"(AMT)":[8],"runtimes":[9],"as":[10,50,72],"an":[11],"efficient":[12],"way":[13],"to":[14,53,100],"map":[15],"irregular":[16],"and":[17,41,92],"dynamic":[18],"parallel":[19],"applications":[20],"onto":[21],"heterogeneous":[22],"computing":[23],"resources.":[24],"In":[25],"this":[26],"work,":[27],"we":[28],"show":[29],"that":[30,42,65],"AMTs":[31],"nonetheless":[32],"struggle":[33],"with":[34,59],"communication":[35,47,74,90],"bottlenecks":[36],"when":[37],"scaling":[38],"computations":[39],"strongly":[40],"the":[43,73,77],"design":[44],"of":[45,86,95],"commonly-used":[46],"libraries":[48],"such":[49],"MPI":[51,58],"contribute":[52],"these":[54],"bottlenecks.":[55],"We":[56],"replace":[57],"LCI,":[60],"Lightweight":[62],"Communication":[63],"Interface":[64],"designed":[67],"for":[68,76],"dynamic,":[69],"asynchronous":[70],"frameworks,":[71],"layer":[75],"PaRSEC":[78],"runtime.":[79],"The":[80],"result":[81],"significant":[84],"reduction":[85,94],"end-to-end":[87],"latency":[88],"microbenchmarks":[91],"overall":[96],"time-to-solution":[97],"by":[98],"up":[99],"12%":[101],"HiCMA,":[103],"tile-based":[105],"low-rank":[106],"Cholesky":[107],"factorization":[108],"package.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
