{"id":"https://openalex.org/W2124273985","doi":"https://doi.org/10.1145/2150976.2151014","title":"SIMD defragmenter","display_name":"SIMD defragmenter","publication_year":2012,"publication_date":"2012-03-03","ids":{"openalex":"https://openalex.org/W2124273985","doi":"https://doi.org/10.1145/2150976.2151014","mag":"2124273985"},"language":"en","primary_location":{"id":"doi:10.1145/2150976.2151014","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2150976.2151014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the seventeenth international conference on Architectural Support for Programming Languages and Operating Systems","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/A5086980677","display_name":"Yongjun Park","orcid":"https://orcid.org/0000-0003-3725-0380"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yongjun Park","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083141649","display_name":"Sangwon Seo","orcid":"https://orcid.org/0000-0003-2281-9167"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sangwon Seo","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012994918","display_name":"Hyunchul Park","orcid":"https://orcid.org/0000-0002-4025-6153"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyunchul Park","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000303565","display_name":"Hyoun Kyu Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyoun Kyu Cho","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002075773","display_name":"Scott Mahlke","orcid":"https://orcid.org/0000-0002-0438-0616"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Mahlke","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5086980677"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":3.4807,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.92926738,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"363","last_page":"374"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9998000264167786,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9983999729156494,"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/simd","display_name":"SIMD","score":0.9537700414657593},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8652589321136475},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8062936067581177},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.7541729211807251},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6413677334785461},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5554741024971008},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.4857771694660187},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.4275757372379303},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09714564681053162}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.9537700414657593},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8652589321136475},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8062936067581177},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.7541729211807251},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6413677334785461},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5554741024971008},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.4857771694660187},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.4275757372379303},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09714564681053162}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2150976.2151014","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2150976.2151014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the seventeenth international conference on Architectural Support for Programming Languages and Operating Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1494930385","https://openalex.org/W1515793664","https://openalex.org/W1982008951","https://openalex.org/W2012252449","https://openalex.org/W2023433806","https://openalex.org/W2034971312","https://openalex.org/W2058997312","https://openalex.org/W2099206054","https://openalex.org/W2099731629","https://openalex.org/W2100484677","https://openalex.org/W2104378884","https://openalex.org/W2111394443","https://openalex.org/W2112324761","https://openalex.org/W2113558024","https://openalex.org/W2113622688","https://openalex.org/W2115184416","https://openalex.org/W2117285153","https://openalex.org/W2118031182","https://openalex.org/W2121176848","https://openalex.org/W2122171990","https://openalex.org/W2122553095","https://openalex.org/W2131783928","https://openalex.org/W2132000191","https://openalex.org/W2137249790","https://openalex.org/W2137857636","https://openalex.org/W2140169558","https://openalex.org/W2149959321","https://openalex.org/W2155509874","https://openalex.org/W2158899676","https://openalex.org/W2544732887","https://openalex.org/W2548047505","https://openalex.org/W3141847830","https://openalex.org/W4241736131","https://openalex.org/W4247115961","https://openalex.org/W4250370106","https://openalex.org/W6995434384"],"related_works":["https://openalex.org/W2566637483","https://openalex.org/W2127324789","https://openalex.org/W2778498407","https://openalex.org/W3024308452","https://openalex.org/W2099629705","https://openalex.org/W4244894488","https://openalex.org/W4285390450","https://openalex.org/W2979513934","https://openalex.org/W2366442643","https://openalex.org/W2766828645"],"abstract_inverted_index":{"Single-instruction":[0],"multiple-data":[1],"(SIMD)":[2],"accelerators":[3],"provide":[4],"an":[5],"energy-efficient":[6],"platform":[7],"to":[8,64,84,101,201],"scale":[9],"the":[10,24,28,108,111,121,129,155,163],"performance":[11],"of":[12,27,49,113,144],"mobile":[13],"systems":[14],"while":[15],"still":[16],"retaining":[17],"post-programmability.":[18],"The":[19,117,135],"central":[20],"challenge":[21],"is":[22,55,119,168],"translating":[23],"parallel":[25,153],"resources":[26],"SIMD":[29,79,99,133,136,156,173,179],"hardware":[30],"into":[31],"real":[32],"application":[33],"performance.":[34],"In":[35],"scientific":[36],"applications,":[37],"automatic":[38],"vectorization":[39,54,96,189],"techniques":[40],"have":[41],"proven":[42],"quite":[43],"effective":[44,59],"at":[45,162],"extracting":[46],"large":[47],"levels":[48],"data-level":[50],"parallelism":[51,115],"(DLP).":[52],"However,":[53],"often":[56],"much":[57],"less":[58],"for":[60,198],"media":[61],"applications":[62],"due":[63,83],"low":[65],"trip":[66],"count":[67],"loops,":[68],"complex":[69],"control":[70],"flow,":[71],"and":[72,190],"non-uniform":[73],"execution":[74],"behavior.":[75],"As":[76],"a":[77,94,171,182,191],"result,":[78],"lanes":[80],"remain":[81],"idle":[82],"insufficient":[85],"DLP.":[86,202],"To":[87],"attack":[88],"this":[89,91,139],"problem,":[90],"paper":[92],"proposes":[93],"new":[95],"pass":[97],"called":[98],"Defragmenter":[100],"uncover":[102],"hidden":[103],"DLP":[104],"that":[105,125,148,178],"lurks":[106],"below":[107],"surface":[109],"in":[110,152,160],"form":[112],"instruction-level":[114],"(ILP).":[116],"difficulty":[118],"managing":[120],"data":[122],"packing/unpacking":[123,166],"overhead":[124,167],"can":[126,149],"easily":[127],"exceed":[128],"benefits":[130],"gained":[131],"through":[132],"execution.":[134],"degragmenter":[137],"overcomes":[138],"problem":[140],"by":[141],"identifying":[142],"groups":[143],"compatible":[145],"instructions":[146],"(subgraphs)":[147],"be":[150],"executed":[151],"across":[154],"lanes.":[157],"By":[158],"SIMDizing":[159],"bulk":[161],"subgraph":[164],"level,":[165],"minimized.":[169],"On":[170],"16-lane":[172],"processor,":[174],"experimental":[175],"results":[176],"show":[177],"defragmentation":[180],"achieves":[181],"mean":[183],"1.6x":[184],"speedup":[185],"over":[186,194],"traditional":[187],"loop":[188],"31%":[192],"gain":[193],"prior":[195],"research":[196],"approaches":[197],"converting":[199],"ILP":[200]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}