{"id":"https://openalex.org/W2341343020","doi":"https://doi.org/10.1177/1094342015585845","title":"Software pipelining for graphic processing unit acceleration: Partition, scheduling and granularity","display_name":"Software pipelining for graphic processing unit acceleration: Partition, scheduling and granularity","publication_year":2015,"publication_date":"2015-06-02","ids":{"openalex":"https://openalex.org/W2341343020","doi":"https://doi.org/10.1177/1094342015585845","mag":"2341343020"},"language":"en","primary_location":{"id":"doi:10.1177/1094342015585845","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342015585845","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-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/A5070202014","display_name":"Bozhong Liu","orcid":"https://orcid.org/0000-0003-2839-1499"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bozhong Liu","raw_affiliation_strings":["School of Information Security Engineering, Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"School of Information Security Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088072972","display_name":"Weidong Qiu","orcid":"https://orcid.org/0000-0001-6428-1655"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weidong Qiu","raw_affiliation_strings":["School of Information Security Engineering, Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"School of Information Security Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025868762","display_name":"Lin Jiang","orcid":"https://orcid.org/0000-0003-0928-4583"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Jiang","raw_affiliation_strings":["School of Information Security Engineering, Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"School of Information Security Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101593687","display_name":"Zheng Gong","orcid":"https://orcid.org/0000-0002-1794-816X"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Gong","raw_affiliation_strings":["School of Computer Science, South China Normal University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, South China Normal University, China","institution_ids":["https://openalex.org/I187400657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088072972"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":3.2298,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.92457421,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"30","issue":"2","first_page":"169","last_page":"185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9984999895095825,"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":0.8698267936706543},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.8123272061347961},{"id":"https://openalex.org/keywords/software-pipelining","display_name":"Software pipelining","score":0.7865058183670044},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6574580669403076},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.6448102593421936},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5867571234703064},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5847498774528503},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.5799515843391418},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.44234970211982727},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.4105067849159241},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3785344660282135},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3592541813850403},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2574138045310974}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8698267936706543},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.8123272061347961},{"id":"https://openalex.org/C188854837","wikidata":"https://www.wikidata.org/wiki/Q268469","display_name":"Software pipelining","level":3,"score":0.7865058183670044},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6574580669403076},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.6448102593421936},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5867571234703064},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5847498774528503},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.5799515843391418},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.44234970211982727},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.4105067849159241},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3785344660282135},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3592541813850403},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2574138045310974},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342015585845","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342015585845","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W85735825","https://openalex.org/W109475151","https://openalex.org/W1494271578","https://openalex.org/W1502558230","https://openalex.org/W1536011525","https://openalex.org/W1591740858","https://openalex.org/W1651324627","https://openalex.org/W1938381964","https://openalex.org/W1965942711","https://openalex.org/W1976139981","https://openalex.org/W1976339994","https://openalex.org/W1977920247","https://openalex.org/W1984296775","https://openalex.org/W2000953215","https://openalex.org/W2027169432","https://openalex.org/W2032309817","https://openalex.org/W2043555680","https://openalex.org/W2054652902","https://openalex.org/W2057035391","https://openalex.org/W2063257142","https://openalex.org/W2065963893","https://openalex.org/W2068765112","https://openalex.org/W2084984944","https://openalex.org/W2086738738","https://openalex.org/W2087210673","https://openalex.org/W2096210558","https://openalex.org/W2099011986","https://openalex.org/W2113679613","https://openalex.org/W2121195165","https://openalex.org/W2122080725","https://openalex.org/W2133741166","https://openalex.org/W2141579716","https://openalex.org/W2143303748","https://openalex.org/W2144835250","https://openalex.org/W2150476673","https://openalex.org/W2152323824","https://openalex.org/W2157758640","https://openalex.org/W2167334577","https://openalex.org/W2536495848","https://openalex.org/W4214839236","https://openalex.org/W4231010555","https://openalex.org/W4232919122","https://openalex.org/W4248999564"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W4384937382","https://openalex.org/W2898981446"],"abstract_inverted_index":{"The":[0],"graphic":[1],"processing":[2,24],"unit":[3,25,102],"(GPU)":[4],"is":[5,33,56],"becoming":[6],"increasingly":[7],"popular":[8],"as":[9],"a":[10,22,34,50,66],"performance":[11,77,126],"accelerator":[12],"in":[13,37,72,106],"various":[14],"applications":[15],"requiring":[16],"high-performance":[17],"parallel":[18],"computing":[19],"capability.":[20],"In":[21,60],"central":[23],"(CPU)":[26],"or":[27],"GPU":[28,115],"hybrid":[29],"system,":[30],"software":[31,129],"pipelining":[32],"major":[35],"task":[36,52,70],"order":[38,73],"to":[39,74,99],"deliver":[40],"accelerated":[41],"performance,":[42],"where":[43],"hiding":[44],"CPU\u2013GPU":[45],"communication":[46],"overheads":[47],"by":[48],"splitting":[49],"large":[51],"into":[53,69,97],"small":[54],"units":[55],"the":[57,82,91],"key":[58],"challenge.":[59],"this":[61],"paper,":[62],"we":[63],"carry":[64],"out":[65],"systematic":[67],"investigation":[68],"partitioning":[71],"achieve":[75,100,121],"maximum":[76],"gain.":[78],"We":[79],"first":[80],"validate":[81],"advantage":[83],"of":[84],"even":[85],"partition":[86],"strategy,":[87],"and":[88,113],"then":[89],"propose":[90],"optimal":[92,101],"scheduling,":[93],"with":[94],"detailed":[95],"study":[96],"how":[98],"size":[103],"(data":[104],"granularity)":[105],"an":[107],"analytical":[108],"framework.":[109],"Experiments":[110],"on":[111],"AMD":[112],"NVIDIA":[114],"platforms":[116],"demonstrate":[117],"that":[118],"our":[119],"approaches":[120],"around":[122],"31":[123],"\u2013":[124],"59%":[125],"improvement":[127],"using":[128],"pipelining.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}