{"id":"https://openalex.org/W2619922765","doi":"https://doi.org/10.1109/tpds.2017.2709748","title":"A Code Generator for Energy-Efficient Wavefront Parallelization of Uniform Dependence Computations","display_name":"A Code Generator for Energy-Efficient Wavefront Parallelization of Uniform Dependence Computations","publication_year":2017,"publication_date":"2017-05-30","ids":{"openalex":"https://openalex.org/W2619922765","doi":"https://doi.org/10.1109/tpds.2017.2709748","mag":"2619922765"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2017.2709748","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2017.2709748","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/A5058138487","display_name":"Yun Zou","orcid":"https://orcid.org/0000-0001-8408-4114"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yun Zou","raw_affiliation_strings":["Computer Science Department, State University, Fort Collins, CO"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, State University, Fort Collins, CO","institution_ids":["https://openalex.org/I92446798"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047953886","display_name":"Sanjay Rajopadhye","orcid":"https://orcid.org/0000-0002-4246-6066"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjay Rajopadhye","raw_affiliation_strings":["Computer Science Department, State University, Fort Collins, CO"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, State University, Fort Collins, CO","institution_ids":["https://openalex.org/I92446798"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5058138487"],"corresponding_institution_ids":["https://openalex.org/I92446798"],"apc_list":null,"apc_paid":null,"fwci":0.2253,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.47136564,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"29","issue":"9","first_page":"1923","last_page":"1936"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9955999851226807,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8044188022613525},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7923778295516968},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6241666674613953},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6070170402526855},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5341998934745789},{"id":"https://openalex.org/keywords/wavefront","display_name":"Wavefront","score":0.5014078617095947},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4457125961780548},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.41913336515426636},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.41872638463974},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3008904457092285},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.16757142543792725},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.15177372097969055},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.14566361904144287},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11249351501464844},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0912889838218689},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.08427736163139343}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8044188022613525},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7923778295516968},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6241666674613953},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6070170402526855},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5341998934745789},{"id":"https://openalex.org/C165699331","wikidata":"https://www.wikidata.org/wiki/Q461533","display_name":"Wavefront","level":2,"score":0.5014078617095947},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4457125961780548},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.41913336515426636},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.41872638463974},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3008904457092285},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.16757142543792725},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.15177372097969055},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.14566361904144287},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11249351501464844},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0912889838218689},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.08427736163139343},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2017.2709748","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2017.2709748","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":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.9100000262260437}],"awards":[{"id":"https://openalex.org/G3090373930","display_name":null,"funder_award_id":"FA9550-13-1-0064","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W336684904","https://openalex.org/W1503700136","https://openalex.org/W1506424797","https://openalex.org/W1561247983","https://openalex.org/W1825294837","https://openalex.org/W1908022351","https://openalex.org/W1968013322","https://openalex.org/W1973271197","https://openalex.org/W1973532523","https://openalex.org/W1979457157","https://openalex.org/W2002252837","https://openalex.org/W2035701183","https://openalex.org/W2044977944","https://openalex.org/W2054388411","https://openalex.org/W2056971515","https://openalex.org/W2068383308","https://openalex.org/W2070961300","https://openalex.org/W2095875205","https://openalex.org/W2097757554","https://openalex.org/W2112391112","https://openalex.org/W2119609467","https://openalex.org/W2121082877","https://openalex.org/W2121297016","https://openalex.org/W2123286830","https://openalex.org/W2124931755","https://openalex.org/W2126464777","https://openalex.org/W2135682468","https://openalex.org/W2158958889","https://openalex.org/W2172191698","https://openalex.org/W2205893513","https://openalex.org/W2278224729","https://openalex.org/W2281158700","https://openalex.org/W2296218291","https://openalex.org/W2475955799","https://openalex.org/W3099448935","https://openalex.org/W3203568064","https://openalex.org/W4235662649","https://openalex.org/W4255560897","https://openalex.org/W4294628664","https://openalex.org/W6611421933","https://openalex.org/W6630360801","https://openalex.org/W6688061036","https://openalex.org/W6842480490","https://openalex.org/W6980329530","https://openalex.org/W6995680990"],"related_works":["https://openalex.org/W2108497790","https://openalex.org/W2047489700","https://openalex.org/W2053110192","https://openalex.org/W2012708622","https://openalex.org/W2624844140","https://openalex.org/W2609368280","https://openalex.org/W3122369893","https://openalex.org/W2387634031","https://openalex.org/W2048831961","https://openalex.org/W1606349578"],"abstract_inverted_index":{"Energy":[0],"is":[1,75,118],"now":[2],"critical":[3],"in":[4,203],"all":[5],"aspects":[6],"of":[7,13,24,51,73,108,128,155,176,207],"computing.":[8],"We":[9,20,131,143],"address":[10,21],"a":[11,133,145,153,165,201],"class":[12],"programs":[14],"that":[15,82],"includes":[16],"so-called":[17],"\u201cstencil":[18],"computations.\u201d":[19],"energy":[22,34,44,129,151,180,206],"optimization":[23],"such":[25,115],"programs.":[26],"Since":[27],"optimizing":[28],"for":[29,35,150],"speed":[30],"alone":[31],"already":[32],"minimizes":[33],"most":[36],"components,":[37],"we":[38,64],"seek":[39],"to":[40,87,200,212],"further":[41],"improve":[42],"the":[43,48,67,80,84,88,109,126,177,204,208],"consumption":[45,181],"by":[46,95,106,167,210],"reducing":[47],"total":[49,205],"number":[50],"off-chip":[52],"memory":[53,179],"accesses":[54],"without":[55],"sacrificing":[56],"execution":[57],"time.":[58],"Our":[59,158],"strategy":[60],"uses":[61],"two-level":[62],"tiling:":[63],"first":[65],"partition":[66],"iteration":[68],"space":[69],"into":[70],"\u201cpasses,\u201d":[71],"each":[72],"which":[74],"tiled":[76,91,135],"and":[77,123,173,193],"parallelized.":[78],"Here,":[79],"schedules":[81,104],"map":[83],"original":[85],"program":[86,209],"multi-pass,":[89],"parametrically":[90],"code":[92,136],"are":[93,98],"specified":[94],"polynomials.":[96],"They":[97],"more":[99],"general":[100],"than":[101],"affine":[102],"multidimensional":[103],"used":[105],"state":[107],"art":[110],"polyhedral":[111],"compilers,":[112],"so":[113],"generating":[114],"codes":[116],"automatically":[117],"an":[119,183],"important":[120],"open":[121],"problem,":[122],"goes":[124],"beyond":[125],"motivation":[127],"efficiency.":[130],"develop":[132],"parametric":[134],"generator":[137],"supporting":[138],"our":[139],"energy-efficient":[140],"parallelization":[141],"strategy.":[142],"give":[144],"simple":[146],"linear":[147],"regression":[148],"model":[149],"as":[152],"function":[154],"performance":[156],"counters.":[157],"experimental":[159],"validation":[160],"on":[161,182],"three":[162],"platforms":[163],"shows":[164],"reduction":[166,202],"about":[168],"74":[169],"percent":[170],"(resp.":[171,188],"75":[172],"67":[174],"percent)":[175],"dynamic":[178],"8-core":[184],"Xeon":[185,190,195],"E5-2650":[186],"v2":[187,192],"6-core":[189,194],"E5-2620":[191],"E52602":[196],"v3).":[197],"This":[198],"leads":[199],"2":[211],"14":[213],"percent.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
