{"id":"https://openalex.org/W2041757713","doi":"https://doi.org/10.1145/2247684.2247701","title":"Defensive loop tiling for multi-core processor","display_name":"Defensive loop tiling for multi-core processor","publication_year":2012,"publication_date":"2012-06-11","ids":{"openalex":"https://openalex.org/W2041757713","doi":"https://doi.org/10.1145/2247684.2247701","mag":"2041757713"},"language":"en","primary_location":{"id":"doi:10.1145/2247684.2247701","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2247684.2247701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2012 ACM SIGPLAN Workshop on Memory Systems Performance and Correctness","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/A5085623373","display_name":"Bin Bao","orcid":"https://orcid.org/0000-0002-0533-462X"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Bao","raw_affiliation_strings":["University of Rochester, Rochester, NY","University of Rochester; Rochester, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester, Rochester, NY","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"University of Rochester; Rochester, NY","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048605475","display_name":"Xiaoya Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoya Xiang","raw_affiliation_strings":["University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11113121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"76","last_page":"77"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10363","display_name":"Low-power high-performance VLSI design","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8199360370635986},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.788375735282898},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.7767140865325928},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.6870778799057007},{"id":"https://openalex.org/keywords/loop-tiling","display_name":"Loop tiling","score":0.635158121585846},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6108906269073486},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.4959128797054291},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.4800904393196106},{"id":"https://openalex.org/keywords/cache-oblivious-algorithm","display_name":"Cache-oblivious algorithm","score":0.47661009430885315},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.44255557656288147},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4143033027648926},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.40792590379714966},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.27329227328300476},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16492390632629395}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8199360370635986},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.788375735282898},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.7767140865325928},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.6870778799057007},{"id":"https://openalex.org/C11799548","wikidata":"https://www.wikidata.org/wiki/Q6675847","display_name":"Loop tiling","level":3,"score":0.635158121585846},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6108906269073486},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.4959128797054291},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.4800904393196106},{"id":"https://openalex.org/C59687516","wikidata":"https://www.wikidata.org/wiki/Q5015938","display_name":"Cache-oblivious algorithm","level":5,"score":0.47661009430885315},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.44255557656288147},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4143033027648926},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.40792590379714966},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.27329227328300476},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16492390632629395},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2247684.2247701","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2247684.2247701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2012 ACM SIGPLAN Workshop on Memory Systems Performance and Correctness","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2034761517","https://openalex.org/W2100741459"],"related_works":["https://openalex.org/W2001324285","https://openalex.org/W2046128376","https://openalex.org/W4388717692","https://openalex.org/W2475955799","https://openalex.org/W2147122795","https://openalex.org/W2038423975","https://openalex.org/W2527471267","https://openalex.org/W2115237803","https://openalex.org/W2792468622","https://openalex.org/W2167303720"],"abstract_inverted_index":{"Loop":[0],"tiling":[1,46,90],"is":[2,32,91],"a":[3,15,62],"compiler":[4],"transformation":[5],"that":[6,39,65],"tailors":[7],"an":[8,106],"application's":[9],"working":[10],"set":[11],"to":[12,97],"fit":[13],"in":[14,93,100],"cache":[16,30,40],"hierarchy.":[17],"On":[18],"today's":[19],"multicore":[20,108],"processors,":[21],"part":[22],"of":[23,45,88],"the":[24,27,49,54,57,68,72,86],"hierarchy,":[25],"especially":[26],"last":[28],"level":[29],"(LLC)":[31],"shared.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37],"show":[38],"sharing":[41],"requires":[42],"special":[43],"types":[44],"depending":[47],"on":[48,105],"co-run":[50],"programs.":[51],"We":[52],"analyze":[53],"reasons":[55],"for":[56,83],"performance":[58,87],"difference":[59],"and":[60],"give":[61],"defensive":[63,89],"strategy":[64],"performs":[66],"consistently":[67],"best":[69],"or":[70],"near":[71],"best.":[73],"For":[74],"example,":[75],"when":[76,103],"compared":[77],"with":[78],"conservative":[79],"tiling,":[80],"which":[81],"tiles":[82],"private":[84],"cache,":[85],"similar":[92],"solo-runs":[94],"but":[95],"up":[96],"20%":[98],"higher":[99],"program":[101],"co-runs,":[102],"tested":[104],"Intel":[107],"processor.":[109]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}