{"id":"https://openalex.org/W2885093895","doi":"https://doi.org/10.4149/cai_2018_3_533","title":"Accelerating Stencil Computation on GPGPU by Novel Mapping Method Between the Global Memory and the Shared Memory","display_name":"Accelerating Stencil Computation on GPGPU by Novel Mapping Method Between the Global Memory and the Shared Memory","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2885093895","doi":"https://doi.org/10.4149/cai_2018_3_533","mag":"2885093895"},"language":"en","primary_location":{"id":"doi:10.4149/cai_2018_3_533","is_oa":true,"landing_page_url":"https://doi.org/10.4149/cai_2018_3_533","pdf_url":null,"source":{"id":"https://openalex.org/S4210200093","display_name":"Computing and Informatics","issn_l":"1335-9150","issn":["1335-9150","2585-8807"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing and Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.4149/cai_2018_3_533","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061508960","display_name":"Tieqiang Mo","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tieqiang Mo","raw_affiliation_strings":["College of Information Science and Engineering, Hunan University, Changsha, Hunan, 410082"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, Changsha, Hunan, 410082","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019444969","display_name":"Renfa Li","orcid":"https://orcid.org/0000-0003-4573-7375"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renfa Li","raw_affiliation_strings":["College of Information Science and Engineering, Hunan University, Changsha, Hunan, 410082"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, Changsha, Hunan, 410082","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5061508960"],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09227573,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"3","first_page":"533","last_page":"552"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9987000226974487,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/stencil","display_name":"Stencil","score":0.9818558692932129},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7855780720710754},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7480072975158691},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6605859994888306},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.4908662438392639},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.48809731006622314},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.483405739068985},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.24677911400794983},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2429792582988739},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08390653133392334}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.9818558692932129},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7855780720710754},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7480072975158691},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6605859994888306},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.4908662438392639},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.48809731006622314},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.483405739068985},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.24677911400794983},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2429792582988739},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08390653133392334}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.4149/cai_2018_3_533","is_oa":true,"landing_page_url":"https://doi.org/10.4149/cai_2018_3_533","pdf_url":null,"source":{"id":"https://openalex.org/S4210200093","display_name":"Computing and Informatics","issn_l":"1335-9150","issn":["1335-9150","2585-8807"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing and Informatics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.4149/cai_2018_3_533","is_oa":true,"landing_page_url":"https://doi.org/10.4149/cai_2018_3_533","pdf_url":null,"source":{"id":"https://openalex.org/S4210200093","display_name":"Computing and Informatics","issn_l":"1335-9150","issn":["1335-9150","2585-8807"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing and Informatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2003798513","https://openalex.org/W2315600872","https://openalex.org/W2151764765","https://openalex.org/W2890431355","https://openalex.org/W4376875029","https://openalex.org/W3149084271","https://openalex.org/W4247008888","https://openalex.org/W2150319905","https://openalex.org/W2039378765","https://openalex.org/W2149537422"],"abstract_inverted_index":{"Acceleration":[0],"of":[1,23,72,107,115],"stencil":[2,49,80,116],"computation":[3,50,81],"can":[4],"be":[5],"effectively":[6],"improved":[7],"by":[8,57],"utilizing":[9],"the":[10,20,28,32,43,47,63],"memory":[11,30,108],"resource.":[12],"In":[13,66],"this":[14],"paper,":[15],"in":[16,41,52,78,105],"order":[17],"to":[18,61,89,103],"reduce":[19,62,90],"branch":[21],"divergence":[22],"traditional":[24],"mapping":[25,39],"method":[26],"between":[27],"global":[29],"and":[31,86,111],"shared":[33],"memory,":[34],"we":[35,68],"devise":[36],"a":[37],"new":[38],"mechanism":[40],"which":[42],"conditional":[44],"statements":[45],"loading":[46],"boundary":[48],"points":[51],"every":[53,79],"XY-tile":[54,74],"are":[55,101],"removed":[56],"aligning":[58],"ghost":[59],"zone":[60],"synchronization":[64],"overhead.":[65,91],"addition,":[67],"make":[69],"full":[70],"use":[71],"single":[73],"loaded":[75],"into":[76],"registers":[77],"point,":[82],"common":[83],"sub-expression":[84],"elimination":[85],"software":[87],"prefetching":[88],"At":[92],"last":[93],"detailed":[94],"performance":[95,114],"evaluation":[96],"demonstrates":[97],"our":[98],"optimized":[99],"policies":[100],"close":[102],"optimal":[104],"terms":[106],"bandwidth":[109],"utilization":[110],"achieve":[112],"higher":[113],"computation.":[117]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}