{"id":"https://openalex.org/W2044183128","doi":"https://doi.org/10.1145/1065895.1065897","title":"Instruction combining for coalescing memory accesses using global code motion","display_name":"Instruction combining for coalescing memory accesses using global code motion","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2044183128","doi":"https://doi.org/10.1145/1065895.1065897","mag":"2044183128"},"language":"en","primary_location":{"id":"doi:10.1145/1065895.1065897","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1065895.1065897","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 workshop on Memory system performance  - MSP '04","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/A5084728520","display_name":"Motohiro Kawahito","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Motohiro Kawahito","raw_affiliation_strings":["IBM Tokyo Research Laboratory, Shimotsuruma, Yamato, Kanagawa, Japan","IBM Tokyo Research Laboratory, Shimotsuruma, Yamato, Kanagawa, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Tokyo Research Laboratory, Shimotsuruma, Yamato, Kanagawa, Japan","institution_ids":["https://openalex.org/I4210145865"]},{"raw_affiliation_string":"IBM Tokyo Research Laboratory, Shimotsuruma, Yamato, Kanagawa, Japan#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109033933","display_name":"Hideaki Komatsu","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Hideaki Komatsu","raw_affiliation_strings":["IBM Tokyo Research Laboratory, Shimotsuruma, Yamato, Kanagawa, Japan","IBM Tokyo Research Laboratory, Shimotsuruma, Yamato, Kanagawa, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Tokyo Research Laboratory, Shimotsuruma, Yamato, Kanagawa, Japan","institution_ids":["https://openalex.org/I4210145865"]},{"raw_affiliation_string":"IBM Tokyo Research Laboratory, Shimotsuruma, Yamato, Kanagawa, Japan#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006642369","display_name":"Toshio Nakatani","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Toshio Nakatani","raw_affiliation_strings":["IBM Tokyo Research Laboratory, Shimotsuruma, Yamato, Kanagawa, Japan","IBM Tokyo Research Laboratory, Shimotsuruma, Yamato, Kanagawa, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Tokyo Research Laboratory, Shimotsuruma, Yamato, Kanagawa, Japan","institution_ids":["https://openalex.org/I4210145865"]},{"raw_affiliation_string":"IBM Tokyo Research Laboratory, Shimotsuruma, Yamato, Kanagawa, Japan#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.13031265,"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":"2","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9904000163078308,"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":0.8856737613677979},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6882703900337219},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6462249755859375},{"id":"https://openalex.org/keywords/memory-model","display_name":"Memory model","score":0.5373825430870056},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.5144691467285156},{"id":"https://openalex.org/keywords/just-in-time-compilation","display_name":"Just-in-time compilation","score":0.49948620796203613},{"id":"https://openalex.org/keywords/uniform-memory-access","display_name":"Uniform memory access","score":0.4423831105232239},{"id":"https://openalex.org/keywords/memory-address","display_name":"Memory address","score":0.44031861424446106},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.42699766159057617},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.3395134210586548},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.3091624081134796},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.28807950019836426},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.09096944332122803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8856737613677979},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6882703900337219},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6462249755859375},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.5373825430870056},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5144691467285156},{"id":"https://openalex.org/C76782552","wikidata":"https://www.wikidata.org/wiki/Q110546","display_name":"Just-in-time compilation","level":3,"score":0.49948620796203613},{"id":"https://openalex.org/C51290061","wikidata":"https://www.wikidata.org/wiki/Q1936765","display_name":"Uniform memory access","level":4,"score":0.4423831105232239},{"id":"https://openalex.org/C153247305","wikidata":"https://www.wikidata.org/wiki/Q835713","display_name":"Memory address","level":3,"score":0.44031861424446106},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.42699766159057617},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.3395134210586548},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.3091624081134796},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.28807950019836426},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.09096944332122803},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1065895.1065897","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1065895.1065897","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 workshop on Memory system performance  - MSP '04","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.90.7861","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.90.7861","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://192.5.53.208/~cding/Archive/MSP04Proceedings/p2_kawahito.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1559984336","https://openalex.org/W1644882639","https://openalex.org/W1912722244","https://openalex.org/W1986644367","https://openalex.org/W2015918966","https://openalex.org/W2018127156","https://openalex.org/W2026202743","https://openalex.org/W2031621974","https://openalex.org/W2042264308","https://openalex.org/W2058360616","https://openalex.org/W2074672347","https://openalex.org/W2111394443","https://openalex.org/W2111566595","https://openalex.org/W2111984394","https://openalex.org/W2114067856","https://openalex.org/W2116938429","https://openalex.org/W2118263004","https://openalex.org/W2123160336","https://openalex.org/W2130652793","https://openalex.org/W2137857636","https://openalex.org/W2143602127","https://openalex.org/W2156800521","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4317827391","https://openalex.org/W1839004754","https://openalex.org/W2186451538","https://openalex.org/W40577698","https://openalex.org/W2182797201","https://openalex.org/W2107163823","https://openalex.org/W4233212676","https://openalex.org/W2124489231","https://openalex.org/W2078898826","https://openalex.org/W1496676675"],"abstract_inverted_index":{"Instruction":[0],"combining":[1,40,130,158,166],"is":[2],"an":[3,217],"optimization":[4],"to":[5,79,109,136,243,249],"replace":[6,211],"a":[7,12,21,48,55,125,244],"sequence":[8],"of":[9,54,139,145,214,246],"instructions":[10,107],"with":[11,44,202,220],"more":[13,146],"efficient":[14],"instruction":[15,129],"yielding":[16],"the":[17,36,70,82,86,140,164,175,187,197,225,230,234],"same":[18],"result":[19],"in":[20,143,174,233],"fewer":[22],"machine":[23],"cycles.":[24],"When":[25],"we":[26,33,123,194,210,222],"use":[27],"it":[28],"for":[29,51,64,74,98,128,153,180,216,229],"coalescing":[30,101,154],"memory":[31,37,42,59,93,99,155],"accesses,":[32,156],"can":[34,61,195,223,240],"reduce":[35],"traffic":[38],"by":[39,68,84,90,131,185,200,227],"narrow":[41],"references":[43],"contiguous":[45],"addresses":[46],"into":[47],"wider":[49,137],"reference":[50],"taking":[52],"advantage":[53],"wide-bus":[56],"architecture.":[57],"Coalescing":[58],"accesses":[60],"improve":[62,196,224],"performance":[63,199,226],"two":[65,151,159,167],"reasons:":[66],"one":[67,157],"reducing":[69,85],"additional":[71,204],"cycles":[72,88],"required":[73],"moving":[75],"data":[76],"from":[77],"caches":[78],"registers":[80],"and":[81,113,163,182,248],"other":[83,118,165],"stall":[87],"caused":[89],"multiple":[91],"outstanding":[92],"access":[94,100,106],"requests.":[95],"Previous":[96],"approaches":[97],"focus":[102],"only":[103],"on":[104],"array":[105],"related":[108],"loop":[110],"induction":[111],"variables,":[112],"thus":[114],"they":[115],"miss":[116],"many":[117],"opportunities.":[119],"In":[120,191],"this":[121],"paper,":[122],"propose":[124],"new":[126],"algorithm":[127,173],"applying":[132],"global":[133],"code":[134],"motion":[135],"regions":[138],"given":[141],"program":[142],"search":[144],"potential":[147],"candidates.":[148],"We":[149],"implemented":[150],"optimizations":[152],"32-bit":[160],"integer":[161],"loads":[162],"single-precision":[168],"floating-point":[169],"loads,":[170],"using":[171],"our":[172,192],"IBM":[176],"Java\u2122":[177],"JIT":[178],"compiler":[179],"IA-64,":[181],"evaluated":[183],"them":[184],"measuring":[186],"SPECjvm98":[188],"benchmark":[189,232,236],"suite.":[190,237],"experiment,":[193],"maximum":[198],"5.5%":[201],"little":[203],"compilation":[205],"time":[206],"overhead.":[207],"Moreover,":[208],"when":[209],"every":[212],"declaration":[213],"double":[215],"instance":[218],"variable":[219],"float,":[221],"7.3%":[228],"MolDyn":[231],"JavaGrande":[235],"Our":[238],"approach":[239],"be":[241],"applied":[242],"variety":[245],"architectures":[247],"programming":[250],"languages":[251],"besides":[252],"Java.":[253]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}