{"id":"https://openalex.org/W2129654573","doi":"https://doi.org/10.1109/hpcsim.2014.6903669","title":"Run-time mechanisms for fine-grained parallelism on network processors: The TILEPro64 experience","display_name":"Run-time mechanisms for fine-grained parallelism on network processors: The TILEPro64 experience","publication_year":2014,"publication_date":"2014-07-01","ids":{"openalex":"https://openalex.org/W2129654573","doi":"https://doi.org/10.1109/hpcsim.2014.6903669","mag":"2129654573"},"language":"en","primary_location":{"id":"doi:10.1109/hpcsim.2014.6903669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2014.6903669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on High Performance Computing & Simulation (HPCS)","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/A5019212161","display_name":"Daniele Buono","orcid":"https://orcid.org/0009-0002-1433-9104"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Daniele Buono","raw_affiliation_strings":["Department of Computer Science, University of Pisa, Pisa, Italy","Department of Computer Science, University of Pisa, Largo B. Pontecorvo, 3, I-56127, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Pisa, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]},{"raw_affiliation_string":"Department of Computer Science, University of Pisa, Largo B. Pontecorvo, 3, I-56127, Italy","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047226405","display_name":"Gabriele Mencagli","orcid":"https://orcid.org/0000-0002-6263-7723"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Gabriele Mencagli","raw_affiliation_strings":["Department of Computer Science, University of Pisa, Pisa, Italy","Department of Computer Science, University of Pisa, Largo B. Pontecorvo, 3, I-56127, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Pisa, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]},{"raw_affiliation_string":"Department of Computer Science, University of Pisa, Largo B. Pontecorvo, 3, I-56127, Italy","institution_ids":["https://openalex.org/I108290504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I108290504"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"41","issue":null,"first_page":"55","last_page":"64"},"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/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":0.8979550004005432},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7056352496147156},{"id":"https://openalex.org/keywords/cache-coherence","display_name":"Cache coherence","score":0.6875894069671631},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6619337201118469},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6166078448295593},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5329094529151917},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.5173699259757996},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.512959897518158},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4957224130630493},{"id":"https://openalex.org/keywords/interconnection","display_name":"Interconnection","score":0.44671839475631714},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.44620272517204285},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.4422786831855774},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.42438775300979614},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.41116997599601746},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.34253889322280884},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.3355677127838135},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.1675674021244049},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.12948688864707947},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09129199385643005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8979550004005432},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7056352496147156},{"id":"https://openalex.org/C141917322","wikidata":"https://www.wikidata.org/wiki/Q1025017","display_name":"Cache coherence","level":5,"score":0.6875894069671631},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6619337201118469},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6166078448295593},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5329094529151917},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.5173699259757996},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.512959897518158},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4957224130630493},{"id":"https://openalex.org/C123745756","wikidata":"https://www.wikidata.org/wiki/Q1665949","display_name":"Interconnection","level":2,"score":0.44671839475631714},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.44620272517204285},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.4422786831855774},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.42438775300979614},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.41116997599601746},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.34253889322280884},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.3355677127838135},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.1675674021244049},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.12948688864707947},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09129199385643005},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hpcsim.2014.6903669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2014.6903669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on High Performance Computing & Simulation (HPCS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arpi.unipi.it:11568/666269","is_oa":false,"landing_page_url":"http://hdl.handle.net/11568/666269","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W55245903","https://openalex.org/W1931014159","https://openalex.org/W1969137635","https://openalex.org/W2029601347","https://openalex.org/W2052540119","https://openalex.org/W2128294826","https://openalex.org/W2150905424","https://openalex.org/W2162544437","https://openalex.org/W2226245130","https://openalex.org/W2256063247","https://openalex.org/W3140062895","https://openalex.org/W4237609491","https://openalex.org/W6602259208","https://openalex.org/W6640314448","https://openalex.org/W6642384903","https://openalex.org/W6691964987"],"related_works":["https://openalex.org/W2950520577","https://openalex.org/W74409296","https://openalex.org/W2003935582","https://openalex.org/W1554644772","https://openalex.org/W305742777","https://openalex.org/W2940653809","https://openalex.org/W2567390125","https://openalex.org/W2124295435","https://openalex.org/W2121547511","https://openalex.org/W2468095077"],"abstract_inverted_index":{"The":[0,127],"efficient":[1,72,121],"parallelization":[2],"of":[3,42,50,95,112,124],"very":[4],"fine-grained":[5,125],"computations":[6],"is":[7,84],"an":[8,133],"old":[9],"problem":[10],"still":[11],"challenging":[12],"also":[13],"on":[14,40,76],"modern":[15],"shared":[16],"memory":[17],"architectures.":[18,44],"Scalable":[19],"parallelizations":[20],"are":[21,35,111],"possible":[22],"if":[23],"the":[24,29,51,55,60,77,89],"base":[25],"mechanisms":[26,75,119],"provided":[27],"by":[28,59],"run-time":[30,143],"support":[31],"(for":[32],"inter-thread/inter-process":[33],"synchronization/communication)":[34],"carefully":[36],"designed":[37],"and":[38,54,106,132],"developed":[39],"top":[41],"parallel":[43,87,122],"This":[45],"requires":[46],"a":[47,85,92],"deep":[48],"knowledge":[49],"hardware":[52],"behavior":[53],"interaction":[56,74],"patterns":[57],"used":[58],"parallelism":[61],"paradigms.":[62],"In":[63],"this":[64],"paper":[65,128],"we":[66],"present":[67],"our":[68,130,138],"experience":[69],"in":[70],"developing":[71],"inter-thread":[73],"Tilera":[78],"TILEPro64":[79,90],"network":[80],"processor.":[81],"Although":[82],"it":[83],"domain-specific":[86],"architecture,":[88],"represents":[91],"notable":[93],"example":[94],"how":[96],"advanced":[97],"architectural":[98],"structures,":[99],"such":[100],"as":[101],"user-accessible":[102],"on-chip":[103],"interconnection":[104],"networks":[105],"configurable":[107],"cache":[108],"coherence":[109],"protocols,":[110],"great":[113],"importance":[114],"to":[115],"design":[116],"lightweight":[117],"cooperation":[118],"enabling":[120],"implementations":[123],"problems.":[126],"presents":[129],"ideas":[131],"experimental":[134],"evaluation":[135],"that":[136],"compares":[137],"proposals":[139],"with":[140],"other":[141],"existing":[142],"supports.":[144]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}