{"id":"https://openalex.org/W2962989815","doi":"https://doi.org/10.1145/3333060","title":"Memory-access-aware Safety and Profitability Analysis for Transformation of Accelerator-bound OpenMP Loops","display_name":"Memory-access-aware Safety and Profitability Analysis for Transformation of Accelerator-bound OpenMP Loops","publication_year":2019,"publication_date":"2019-07-18","ids":{"openalex":"https://openalex.org/W2962989815","doi":"https://doi.org/10.1145/3333060","mag":"2962989815"},"language":"en","primary_location":{"id":"doi:10.1145/3333060","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3333060","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3333060","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3333060","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048684499","display_name":"Artem Chikin","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Artem Chikin","raw_affiliation_strings":["Intel Corporation, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Intel Corporation, Toronto, ON, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028682148","display_name":"Taylor Lloyd","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taylor Lloyd","raw_affiliation_strings":["Amazon, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048554669","display_name":"Jos\u00e9 Nelson Amaral","orcid":"https://orcid.org/0000-0002-9943-1809"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Nelson Amaral","raw_affiliation_strings":["University of Alberta, Edmonton, AB, Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000717061","display_name":"Ettore Tiotto","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113654","display_name":"IBM (Canada)","ror":"https://ror.org/025sxka56","country_code":"CA","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210113654"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ettore Tiotto","raw_affiliation_strings":["IBM Canada, Markham, ON, Canada"],"affiliations":[{"raw_affiliation_string":"IBM Canada, Markham, ON, Canada","institution_ids":["https://openalex.org/I4210113654"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032072592","display_name":"Muhammad Usman","orcid":"https://orcid.org/0000-0003-3083-9010"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Muhammad Usman","raw_affiliation_strings":["University of Alberta, Edmonton, AB, Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5048684499"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.08074615,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"16","issue":"3","first_page":"1","last_page":"26"},"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":0.9994000196456909,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9977999925613403,"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":0.8924955725669861},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8253780603408813},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6782732605934143},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6518757343292236},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6368393898010254},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.6045511960983276},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.584862470626831},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5689311623573303},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.52940833568573},{"id":"https://openalex.org/keywords/loop-unrolling","display_name":"Loop unrolling","score":0.5235199928283691},{"id":"https://openalex.org/keywords/static-analysis","display_name":"Static analysis","score":0.46342742443084717},{"id":"https://openalex.org/keywords/control-flow","display_name":"Control flow","score":0.45265454053878784},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.42574673891067505},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2982741594314575},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.26124459505081177}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8924955725669861},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8253780603408813},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6782732605934143},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6518757343292236},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6368393898010254},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.6045511960983276},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.584862470626831},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5689311623573303},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.52940833568573},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.5235199928283691},{"id":"https://openalex.org/C97686452","wikidata":"https://www.wikidata.org/wiki/Q7604153","display_name":"Static analysis","level":2,"score":0.46342742443084717},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.45265454053878784},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.42574673891067505},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2982741594314575},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.26124459505081177},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3333060","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3333060","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3333060","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3333060","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3333060","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3333060","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2962989815.pdf","grobid_xml":"https://content.openalex.org/works/W2962989815.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1524877046","https://openalex.org/W1536051636","https://openalex.org/W1554879197","https://openalex.org/W1565360684","https://openalex.org/W1715710234","https://openalex.org/W1979527452","https://openalex.org/W1980390491","https://openalex.org/W1982020565","https://openalex.org/W1987588924","https://openalex.org/W2000857901","https://openalex.org/W2017486666","https://openalex.org/W2034761517","https://openalex.org/W2039571393","https://openalex.org/W2043100293","https://openalex.org/W2065971634","https://openalex.org/W2078113878","https://openalex.org/W2078314687","https://openalex.org/W2082263366","https://openalex.org/W2096862145","https://openalex.org/W2111365507","https://openalex.org/W2116299797","https://openalex.org/W2148597203","https://openalex.org/W2158406801","https://openalex.org/W2164890169","https://openalex.org/W2166536280","https://openalex.org/W2170634604","https://openalex.org/W2211541975","https://openalex.org/W2546751105","https://openalex.org/W2560405840","https://openalex.org/W2916922955"],"related_works":["https://openalex.org/W2120421136","https://openalex.org/W2889297400","https://openalex.org/W156668154","https://openalex.org/W4384302888","https://openalex.org/W2128467905","https://openalex.org/W141487401","https://openalex.org/W2111825754","https://openalex.org/W2135849267","https://openalex.org/W1543331277","https://openalex.org/W4214517608"],"abstract_inverted_index":{"Iteration":[0],"Point":[1],"Difference":[2],"Analysis":[3],"is":[4,58,93],"a":[5,115,125],"new":[6],"static":[7],"analysis":[8,46,69],"framework":[9,70],"that":[10,23,63],"can":[11,47],"be":[12],"used":[13],"to":[14,28,97,109],"determine":[15],"the":[16,37,90],"memory":[17,42],"coalescing":[18],"characteristics":[19],"of":[20,33,39,60,107,122,128],"parallel":[21],"loops":[22],"target":[24],"GPU":[25,85],"offloading":[26],"and":[27,31,57,73,140],"ascertain":[29],"safety":[30],"profitability":[32],"loop":[34,75],"transformations":[35],"with":[36,103,124],"goal":[38],"improving":[40],"their":[41],"access":[43],"characteristics.":[44],"This":[45,68,130],"propagate":[48],"definitions":[49],"through":[50],"control":[51],"flow,":[52],"works":[53],"for":[54,81],"non-affine":[55],"expressions,":[56],"capable":[59],"analyzing":[61],"expressions":[62],"reference":[64],"conditionally":[65],"defined":[66],"values.":[67],"enables":[71],"safe":[72],"profitable":[74],"transformations.":[76],"Experimental":[77],"results":[78],"demonstrate":[79],"potential":[80],"dramatic":[82],"performance":[83],"improvements.":[84],"kernel":[86,120],"execution":[87],"time":[88],"across":[89],"Polybench":[91],"suite":[92],"improved":[94],"by":[95],"up":[96,108],"25.5\u00d7":[98],"on":[99],"an":[100],"Nvidia":[101],"P100":[102],"benchmark":[104,118,126],"overall":[105],"improvement":[106,127],"3.2\u00d7.":[110],"An":[111],"opportunity":[112],"detected":[113],"in":[114],"SPEC":[116],"ACCEL":[117],"yields":[119],"speedup":[121],"86.5\u00d7":[123],"3.3\u00d7.":[129],"work":[131],"also":[132],"demonstrates":[133],"how":[134],"architecture-aware":[135],"compilers":[136],"improve":[137],"code":[138],"portability":[139],"reduce":[141],"programmer":[142],"effort.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
