{"id":"https://openalex.org/W2789351849","doi":"https://doi.org/10.1109/tpds.2018.2817207","title":"Unifying Fixed Code Mapping, Communication, Synchronization and Scheduling Algorithms for Efficient and Scalable Loop Pipelining","display_name":"Unifying Fixed Code Mapping, Communication, Synchronization and Scheduling Algorithms for Efficient and Scalable Loop Pipelining","publication_year":2018,"publication_date":"2018-03-19","ids":{"openalex":"https://openalex.org/W2789351849","doi":"https://doi.org/10.1109/tpds.2018.2817207","mag":"2789351849"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2018.2817207","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2817207","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5028216967","display_name":"Aristeidis Mastoras","orcid":"https://orcid.org/0000-0002-5235-8499"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Aristeidis Mastoras","raw_affiliation_strings":["Department of Computer Science, ETH Zurich, Z\u00fcrich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, ETH Zurich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101575762","display_name":"Thomas R. Gross","orcid":"https://orcid.org/0000-0002-2038-2902"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Thomas R. Gross","raw_affiliation_strings":["Department of Computer Science, ETH Zurich, Z\u00fcrich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, ETH Zurich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028216967"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":1.0099,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73038377,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"29","issue":"9","first_page":"2136","last_page":"2149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9998000264167786,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9991000294685364,"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":0.8823195099830627},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7230868339538574},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6227374076843262},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5824699401855469},{"id":"https://openalex.org/keywords/processor-scheduling","display_name":"Processor scheduling","score":0.5572383403778076},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5257951617240906},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.4852752387523651},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.47302794456481934},{"id":"https://openalex.org/keywords/software-pipelining","display_name":"Software pipelining","score":0.4464890658855438},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4148615896701813},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.159486323595047},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.09040170907974243},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08399415016174316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8823195099830627},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7230868339538574},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6227374076843262},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5824699401855469},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.5572383403778076},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5257951617240906},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.4852752387523651},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.47302794456481934},{"id":"https://openalex.org/C188854837","wikidata":"https://www.wikidata.org/wiki/Q268469","display_name":"Software pipelining","level":3,"score":0.4464890658855438},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4148615896701813},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.159486323595047},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.09040170907974243},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08399415016174316},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"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/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"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/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2018.2817207","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2817207","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W35708471","https://openalex.org/W79448102","https://openalex.org/W1964960933","https://openalex.org/W1969240521","https://openalex.org/W1976397984","https://openalex.org/W1982812416","https://openalex.org/W1986804682","https://openalex.org/W1990199656","https://openalex.org/W2006059438","https://openalex.org/W2009964586","https://openalex.org/W2011737674","https://openalex.org/W2016559894","https://openalex.org/W2034209740","https://openalex.org/W2040523061","https://openalex.org/W2042326586","https://openalex.org/W2046188666","https://openalex.org/W2061153463","https://openalex.org/W2072725684","https://openalex.org/W2073983509","https://openalex.org/W2082056472","https://openalex.org/W2086779607","https://openalex.org/W2090408221","https://openalex.org/W2094020960","https://openalex.org/W2109639089","https://openalex.org/W2113563476","https://openalex.org/W2122698306","https://openalex.org/W2128294826","https://openalex.org/W2143592587","https://openalex.org/W2143746374","https://openalex.org/W2145406052","https://openalex.org/W2147536281","https://openalex.org/W2155312437","https://openalex.org/W2165100134","https://openalex.org/W2166263713","https://openalex.org/W2167089275","https://openalex.org/W2169875292","https://openalex.org/W2171546589","https://openalex.org/W2176686728","https://openalex.org/W2508028078","https://openalex.org/W2793755249","https://openalex.org/W3149553891","https://openalex.org/W4230609379","https://openalex.org/W4239580808","https://openalex.org/W4252176599","https://openalex.org/W6603274625","https://openalex.org/W6641437221","https://openalex.org/W6681818463"],"related_works":["https://openalex.org/W1511601046","https://openalex.org/W1775076859","https://openalex.org/W2166265062","https://openalex.org/W2068350864","https://openalex.org/W1991112231","https://openalex.org/W2359150115","https://openalex.org/W2149265258","https://openalex.org/W1540273122","https://openalex.org/W2530146034","https://openalex.org/W2534949186"],"abstract_inverted_index":{"Pipelining":[0,49],"allows":[1],"the":[2,16,25,32,124,130,142,163,203],"execution":[3],"of":[4,126,133,144,162,173,195],"loop":[5,17],"iterations":[6],"with":[7,89,105,129],"cross-iteration":[8],"dependences":[9,27],"to":[10,70,122,206],"overlap":[11],"in":[12],"time,":[13],"provided":[14],"that":[15,24,51,65,92,118,140,157,184,198],"body":[18],"is":[19,44,120,180,199],"partitioned":[20],"into":[21],"stages":[22,33,43],"such":[23],"data":[26,108,147],"are":[28,34,68],"not":[29],"violated.":[30],"Then,":[31],"mapped":[35],"onto":[36],"threads":[37],"and":[38,40,72,102,110,153],"communication":[39,101],"synchronization":[41,103],"between":[42],"typically":[45],"achieved":[46],"using":[47,136],"queues.":[48],"techniques":[50],"rely":[52],"on":[53,151],"static":[54,127,168],"scheduling":[55,128,188],"perform":[56],"poorly":[57,200],"for":[58,76,170,189],"load-imbalanced":[59],"loops.":[60,78],"Moreover,":[61],"previous":[62],"research":[63],"efforts":[64],"achieve":[66],"load-balancing":[67],"restricted":[69],"work-stealing":[71,134],"imply":[73],"high":[74,207],"overhead":[75],"fine-grained":[77,190],"In":[79],"this":[80],"article,":[81],"we":[82],"present":[83],"URTS,":[84],"a":[85,94,106,137,145,167,171,181,193],"unified":[86,138],"runtime":[87],"system":[88],"compiler":[90],"support":[91],"provides":[93],"lightweight":[95],"dynamic":[96,187],"scheduler":[97],"by":[98,135,202],"combining":[99],"mapping,":[100],"algorithms":[104],"suitable":[107],"structure":[109],"an":[111],"efficient":[112,186],"ticket":[113],"mechanism.":[114],"Particularly,":[115],"URTS":[116,158,179],"shows":[117,156],"it":[119],"possible":[121],"combine":[123],"efficiency":[125],"load-imbalance":[131],"tolerance":[132],"design":[139],"exploits":[141],"properties":[143],"novel":[146],"structure.":[148],"The":[149],"evaluation":[150],"8-":[152],"32-core":[154],"machines":[155],"implies":[159],"low":[160],"overhead,":[161],"same":[164],"order":[165],"as":[166],"scheduler,":[169],"set":[172],"benchmarks":[174],"chosen":[175],"from":[176],"widely-used":[177],"collections.":[178],"scalable":[182],"solution":[183],"performs":[185],"loops,":[191],"i.e.,":[192],"class":[194],"interesting":[196],"loops":[197],"handled":[201],"state-of-the-art":[204],"due":[205],"overhead.":[208]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}