{"id":"https://openalex.org/W2489171034","doi":null,"title":"Array syntax compilation and performance tuning","display_name":"Array syntax compilation and performance tuning","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2489171034","mag":"2489171034"},"language":"en","primary_location":{"id":"mag:2489171034","doi":null,"is_oa":false,"landing_page_url":"https://scholarship.rice.edu/handle/1911/20676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"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/A5084197997","display_name":"Ken Kennedy","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ken Kennedy","raw_affiliation_strings":["Rice Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rice Univ","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070714615","display_name":"Yuan Fang Zhao","orcid":"https://orcid.org/0000-0003-1980-6277","observed_orcids":["https://orcid.org/0000-0003-1980-6277"]},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Zhao","raw_affiliation_strings":["Rice Univ"],"raw_orcid":"https://orcid.org/0000-0003-1980-6277","affiliations":[{"raw_affiliation_string":"Rice Univ","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74775410"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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/T10126","display_name":"Logic, programming, and type systems","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":9.999999747378752e-05,"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/compiler-optimization","display_name":"compiler optimization","score":0.722000002861023},{"id":"https://openalex.org/keywords/loop-fusion","display_name":"loop fusion","score":0.8460000157356262},{"id":"https://openalex.org/keywords/performance-tuning","display_name":"performance tuning","score":0.7369999885559082},{"id":"https://openalex.org/keywords/vector-processors","display_name":"vector processors","score":0.8790000081062317},{"id":"https://openalex.org/keywords/cell-processor","display_name":"Cell processor","score":0.6439999938011169},{"id":"https://openalex.org/keywords/data-alignment","display_name":"data alignment","score":0.625},{"id":"https://openalex.org/keywords/data-movement","display_name":"data movement","score":0.781000018119812},{"id":"https://openalex.org/keywords/source-to-source-compiler","display_name":"source-to-source compiler","score":0.7170000076293945},{"id":"https://openalex.org/keywords/multi-core-processors","display_name":"multi-core processors","score":0.7120000123977661},{"id":"https://openalex.org/keywords/data-reuse","display_name":"data reuse","score":0.5640000104904175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8191306591033936},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7082115411758423},{"id":"https://openalex.org/C29331672","wikidata":"https://www.wikidata.org/wiki/Q3354468","display_name":"Loop optimization","level":4,"score":0.5095489025115967},{"id":"https://openalex.org/C82653869","wikidata":"https://www.wikidata.org/wiki/Q6675821","display_name":"Loop fusion","level":3,"score":0.49333348870277405},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.47240036725997925},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.46623656153678894},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.46079546213150024},{"id":"https://openalex.org/C11799548","wikidata":"https://www.wikidata.org/wiki/Q6675847","display_name":"Loop tiling","level":3,"score":0.43666872382164},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.4233022630214691},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.41046085953712463},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.3843785524368286},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.32762524485588074},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3255006670951843},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17682427167892456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11338910460472107},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2489171034","doi":null,"is_oa":false,"landing_page_url":"https://scholarship.rice.edu/handle/1911/20676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W243738321","https://openalex.org/W592740088","https://openalex.org/W1414648890","https://openalex.org/W1495550651","https://openalex.org/W1500117749","https://openalex.org/W1507805857","https://openalex.org/W1531339993","https://openalex.org/W1536051636","https://openalex.org/W1559275050","https://openalex.org/W1560132800","https://openalex.org/W1569709052","https://openalex.org/W1589300154","https://openalex.org/W1604802992","https://openalex.org/W1964031104","https://openalex.org/W2001571623","https://openalex.org/W2007451249","https://openalex.org/W2008946650","https://openalex.org/W2014832488","https://openalex.org/W2038481157","https://openalex.org/W2040522199","https://openalex.org/W2055761985","https://openalex.org/W2059564324","https://openalex.org/W2067107081","https://openalex.org/W2073866852","https://openalex.org/W2074830943","https://openalex.org/W2076346710","https://openalex.org/W2077790567","https://openalex.org/W2078113878","https://openalex.org/W2085118703","https://openalex.org/W2093126960","https://openalex.org/W2098220211","https://openalex.org/W2099404643","https://openalex.org/W2111394443","https://openalex.org/W2125955291","https://openalex.org/W2127324789","https://openalex.org/W2144643978","https://openalex.org/W2151994818","https://openalex.org/W2159309967","https://openalex.org/W2164890169","https://openalex.org/W2168767470","https://openalex.org/W2172062522","https://openalex.org/W2295099251"],"related_works":["https://openalex.org/W1523176115","https://openalex.org/W2109880579","https://openalex.org/W7097258814","https://openalex.org/W7095180233","https://openalex.org/W1761879359","https://openalex.org/W2183105482","https://openalex.org/W7099855162","https://openalex.org/W2055761985","https://openalex.org/W2507434877","https://openalex.org/W7096877437"],"abstract_inverted_index":{"Array":[0],"syntax":[1,307],"adds":[2],"expressive":[3],"power":[4],"to":[5,14,21,32,37,64,71,77,139,205,232,282],"a":[6,87,107,226,313],"language":[7,89],"by":[8,47,96,166,260],"providing":[9],"operations":[10],"on":[11,122,145,179],"and":[12,24,119,129,153,155,170,192,221,237,276],"assignments":[13],"array":[15,35,73,84,218,243,306],"sections.":[16],"Thus":[17],"it":[18],"allows":[19],"programmers":[20],"write":[22],"clear":[23],"concise":[25],"code.":[26],"However,":[27],"state-of-the-art":[28,310],"vendor":[29,261],"compilers":[30],"fail":[31],"efficiently":[33],"map":[34],"statements":[36,244],"underlying":[38],"architectures":[39,147],"for":[40,189,212,273],"high":[41],"performance.":[42],"The":[43],"inefficiency":[44],"is":[45,80],"caused":[46],"ineffectively":[48],"solving":[49],"the":[50,56,65,100,112,136,141,194,197,284,300,318],"following":[51],"three":[52],"technical":[53],"problems:":[54],"(1)\u00a0reducing":[55],"size":[57],"of":[58,175,196,199,209,265,302,315],"allocated":[59,113],"temporary":[60,114],"array;":[61],"(2)\u00a0extending":[62],"solutions":[63,76],"evolving":[66,146],"architectures;":[67],"(3)\u00a0applying":[68],"loop":[69,117,120,187,202,210,266],"fusion":[70,188,203,211,267],"multiple":[72,217],"statements.":[74],"Finding":[75],"these":[78,180],"problems":[79],"important":[81,178],"because":[82],"otherwise":[83],"syntax,":[85],"though":[86],"high-level":[88],"feature,":[90],"may":[91],"not":[92],"be":[93],"widely":[94],"used":[95],"application":[97],"developers.\r\nTo":[98],"address":[99],"above":[101],"problems,":[102],"this":[103,184,290],"research":[104,228],"first":[105],"develops":[106],"novel":[108],"strategy":[109,138,248],"that":[110,148,242,293],"minimizes":[111],"arrays":[115],"using":[116],"alignment":[118,169],"skewing":[121],"scalar":[123],"processors,":[124],"thereby":[125],"reducing":[126],"memory":[127],"traffic":[128],"improving":[130,167],"cache":[131],"utilization.":[132],"It":[133],"then":[134],"extends":[135],"minimization":[137],"exploit":[140],"increasing":[142,213],"on-chip":[143],"parallelism":[144],"offer":[149],"vector":[150,235,323],"(e.g.,":[151,157],"SSE":[152],"AltiVec)":[154],"multi-core":[156,320],"CELL)":[158],"capabilities.":[159,324],"In":[160],"addition,":[161],"new":[162,181],"techniques":[163,296],"boost":[164],"performance":[165,190,207,285,301],"data":[168,172,214],"managing":[171],"movement,":[173],"both":[174],"which":[176,279],"are":[177,223,280],"architectures.":[182],"Last,":[183],"dissertation":[185,291],"parameterizes":[186],"tuning":[191,208,286],"explores":[193],"properties":[195],"space":[198,269,277],"all":[200],"possible":[201],"configurations,":[204],"expedite":[206],"reuse":[215],"across":[216,312],"statements.\r\nThese":[219],"transformations":[220],"optimizations":[222],"implemented":[224],"in":[225,305],"source-to-source":[227],"compiler":[229],"with":[230,246,322],"extensions":[231],"target":[233],"short":[234],"processors":[236,321],"CELL":[238],"processor.":[239],"Experiments":[240],"show":[241],"compiled":[245,258],"our":[247],"run":[249],"as":[250,252],"much":[251],"two":[253],"times":[254],"faster":[255],"than":[256],"those":[257],"directly":[259],"compilers.":[262],"Our":[263],"exploration":[264],"parameter":[268],"identifies":[270],"good":[271],"candidates":[272],"heuristic":[274],"searching":[275],"pruning,":[278],"essential":[281],"make":[283],"process":[287],"practical.\r\nIn":[288],"summary,":[289],"demonstrates":[292],"advanced":[294],"compilation":[295],"can":[297],"significantly":[298],"improve":[299],"programs":[303],"written":[304],"upon":[308],"current":[309],"implementation":[311],"variety":[314],"architectures,":[316],"including":[317],"latest":[319]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-08-23T00:00:00"}
