{"id":"https://openalex.org/W2127462303","doi":"https://doi.org/10.1109/ipdps.2009.5160859","title":"Many-core parallel computing - Can compilers and tools do the heavy lifting?","display_name":"Many-core parallel computing - Can compilers and tools do the heavy lifting?","publication_year":2009,"publication_date":"2009-05-01","ids":{"openalex":"https://openalex.org/W2127462303","doi":"https://doi.org/10.1109/ipdps.2009.5160859","mag":"2127462303"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2009.5160859","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2009.5160859","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Parallel & Distributed 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/A5040404999","display_name":"Wen\u2010mei Hwu","orcid":"https://orcid.org/0000-0003-2532-5349"},"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":true,"raw_author_name":"Wen-mei W. Hwu","raw_affiliation_strings":["University of Illinois, Urbana-Champaign, USA","University of Illinois, Urbana-Champaign , USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois, Urbana-Champaign , USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5040404999"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":1.4806,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.88812066,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9983000159263611,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8819644451141357},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8632516264915466},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8225144147872925},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.709649920463562},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.642309308052063},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6134670376777649},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.47480833530426025},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.25237181782722473},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19987261295318604}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8819644451141357},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8632516264915466},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8225144147872925},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.709649920463562},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.642309308052063},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6134670376777649},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.47480833530426025},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.25237181782722473},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19987261295318604}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdps.2009.5160859","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2009.5160859","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Parallel & Distributed Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5899999737739563,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2778498407","https://openalex.org/W3012895752","https://openalex.org/W3023876411","https://openalex.org/W123152114"],"abstract_inverted_index":{"Modern":[0],"GPUs":[1],"such":[2],"as":[3],"the":[4,12,40,57,60,91,140,153,173],"NVIDIA":[5],"GeForce":[6],"GTX280,":[7],"ATI":[8],"Radeon":[9],"4860,":[10],"and":[11,70,103,148,158],"upcoming":[13],"Intel":[14],"Larrabee":[15],"are":[16,28],"massively":[17],"parallel,":[18],"many-core":[19,26,116],"processors.":[20,117],"Today,":[21,84],"application":[22,86,106,136],"developers":[23,79],"for":[24],"these":[25,44],"chips":[27],"reporting":[29],"10X-100X":[30],"speedup":[31,52],"over":[32,50,53,152],"sequential":[33,71],"code":[34],"on":[35,115,124],"traditional":[36],"microprocessors.":[37],"According":[38],"to":[39,49,80,89,110],"semiconductor":[41],"industry":[42],"roadmap,":[43],"processors":[45],"could":[46],"scale":[47],"up":[48,123],"1,000X":[51],"single":[54],"cores":[55],"by":[56,132],"end":[58],"of":[59,78,146],"year":[61],"2016.":[62],"Such":[63],"a":[64,143],"dramatic":[65],"performance":[66,101,113],"difference":[67],"between":[68],"parallel":[69,93,160],"execution":[72],"will":[73,128,163,169],"motivate":[74],"an":[75,85],"increasing":[76],"number":[77],"parallelize":[81],"their":[82,105,112],"applications.":[83,161],"programmer":[87],"has":[88],"understand":[90],"desirable":[92],"programming":[94],"idioms,":[95],"manually":[96],"work":[97],"around":[98],"potential":[99],"hardware":[100],"pitfalls,":[102],"restructure":[104],"design":[107,137],"in":[108,156],"order":[109],"achieve":[111],"objectives":[114],"Although":[118],"many":[119],"researchers":[120],"have":[121],"given":[122],"parallelizing":[125],"compilers,":[126],"I":[127,162],"show":[129],"evidence":[130],"that":[131],"systematically":[133],"incorporating":[134],"high-level":[135],"knowledge":[138],"into":[139],"source":[141],"code,":[142],"new":[144],"generation":[145],"compilers":[147],"tools":[149],"can":[150],"take":[151],"heavy":[154],"lifting":[155],"developing":[157],"tuning":[159],"also":[164],"discuss":[165],"roadblocks":[166],"whose":[167],"removal":[168],"require":[170],"innovations":[171],"from":[172],"entire":[174],"research":[175],"community.":[176]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}