{"id":"https://openalex.org/W4293024962","doi":"https://doi.org/10.1145/3489517.3530610","title":"Optimizing parallel PREM compilation over nested loop structures","display_name":"Optimizing parallel PREM compilation over nested loop structures","publication_year":2022,"publication_date":"2022-07-10","ids":{"openalex":"https://openalex.org/W4293024962","doi":"https://doi.org/10.1145/3489517.3530610"},"language":"en","primary_location":{"id":"doi:10.1145/3489517.3530610","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3489517.3530610","pdf_url":null,"source":{"id":"https://openalex.org/S4363608816","display_name":"Proceedings of the 59th ACM/IEEE Design Automation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 59th ACM/IEEE Design Automation Conference","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/A5102189754","display_name":"Zhao Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Zhao Gu","raw_affiliation_strings":["University of Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009578055","display_name":"Rodolfo Pellizzoni","orcid":"https://orcid.org/0000-0002-7331-804X"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Rodolfo Pellizzoni","raw_affiliation_strings":["University of Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102189754"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09100101,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1249","last_page":"1254"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9980999827384949,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9969000220298767,"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":0.8678428530693054},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7887346744537354},{"id":"https://openalex.org/keywords/loop-tiling","display_name":"Loop tiling","score":0.679945170879364},{"id":"https://openalex.org/keywords/nested-loop-join","display_name":"Nested loop join","score":0.6356251835823059},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5796260237693787},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5574832558631897},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.5299583077430725},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.4282098114490509},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.4200914204120636},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4179193079471588},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.23308098316192627},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.14417153596878052}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8678428530693054},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7887346744537354},{"id":"https://openalex.org/C11799548","wikidata":"https://www.wikidata.org/wiki/Q6675847","display_name":"Loop tiling","level":3,"score":0.679945170879364},{"id":"https://openalex.org/C1306188","wikidata":"https://www.wikidata.org/wiki/Q4060687","display_name":"Nested loop join","level":2,"score":0.6356251835823059},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5796260237693787},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5574832558631897},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5299583077430725},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.4282098114490509},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.4200914204120636},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4179193079471588},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.23308098316192627},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.14417153596878052},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3489517.3530610","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3489517.3530610","pdf_url":null,"source":{"id":"https://openalex.org/S4363608816","display_name":"Proceedings of the 59th ACM/IEEE Design Automation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 59th ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8535661903","display_name":null,"funder_award_id":"RGPIN-2017-05029","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1598202309","https://openalex.org/W2077143534","https://openalex.org/W2147657366","https://openalex.org/W2605317797","https://openalex.org/W2724694202","https://openalex.org/W4232900548","https://openalex.org/W4246500121","https://openalex.org/W4321782335","https://openalex.org/W6884900269"],"related_works":["https://openalex.org/W2093683727","https://openalex.org/W2103891735","https://openalex.org/W2624440775","https://openalex.org/W2168442270","https://openalex.org/W2734488036","https://openalex.org/W1980336221","https://openalex.org/W2155731617","https://openalex.org/W1513212651","https://openalex.org/W217231416","https://openalex.org/W2165782970"],"abstract_inverted_index":{"We":[0,26,41,86],"consider":[1],"automatic":[2],"parallelization":[3],"of":[4,63,83],"a":[5,28,37,60,89],"computational":[6],"kernel":[7,51],"executed":[8,35],"according":[9],"to":[10,48,79,112],"the":[11,50,81,84,113,119],"PRedictable":[12],"Execution":[13],"Model":[14],"(PREM),":[15],"where":[16,31],"each":[17],"thread":[18],"is":[19,71,77],"divided":[20],"into":[21,53],"execution":[22,52,66],"and":[23,45,55,65,98,105,109],"memory":[24,32],"phases.":[25],"target":[27],"scratchpad-based":[29],"architecture,":[30],"phases":[33],"are":[34],"by":[36],"dedicated":[38],"DMA":[39],"component.":[40],"employ":[42],"data":[43,64],"analysis":[44],"loop":[46],"tiling":[47],"split":[49],"segments,":[54],"schedule":[56],"them":[57],"based":[58],"on":[59],"DAG":[61],"representation":[62],"dependencies.":[67],"Our":[68],"main":[69],"observation":[70],"that":[72,91],"properly":[73],"selecting":[74],"tile":[75,96],"sizes":[76],"key":[78],"optimize":[80],"makespan":[82],"kernel.":[85],"thus":[87],"propose":[88],"heuristic":[90],"efficiently":[92],"searches":[93],"for":[94],"optimized":[95],"size":[97],"core":[99],"assignments":[100],"over":[101],"deeply":[102],"nested":[103],"loops,":[104],"demonstrate":[106],"its":[107],"applicability":[108],"performance":[110],"compared":[111],"state-of-the-art":[114],"in":[115],"PREM":[116],"compilation":[117],"using":[118],"PolyBench-NN":[120],"benchmark":[121],"suite.":[122]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}