{"id":"https://openalex.org/W2335340700","doi":"https://doi.org/10.1109/hpca.2016.7446071","title":"Efficient GPU hardware transactional memory through early conflict resolution","display_name":"Efficient GPU hardware transactional memory through early conflict resolution","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2335340700","doi":"https://doi.org/10.1109/hpca.2016.7446071","mag":"2335340700"},"language":"en","primary_location":{"id":"doi:10.1109/hpca.2016.7446071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca.2016.7446071","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Symposium on High Performance Computer Architecture (HPCA)","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/A5012107181","display_name":"Sui Chen","orcid":"https://orcid.org/0000-0001-7251-7760"},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sui Chen","raw_affiliation_strings":["Division of Electrical & Computer Engineering, Louisiana State University"],"affiliations":[{"raw_affiliation_string":"Division of Electrical & Computer Engineering, Louisiana State University","institution_ids":["https://openalex.org/I121820613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101893942","display_name":"Lu Peng","orcid":"https://orcid.org/0000-0002-8579-5687"},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lu Peng","raw_affiliation_strings":["Louisiana State University Paul M Hebert Law Center, Baton Rouge, LA, US"],"affiliations":[{"raw_affiliation_string":"Louisiana State University Paul M Hebert Law Center, Baton Rouge, LA, US","institution_ids":["https://openalex.org/I121820613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5012107181"],"corresponding_institution_ids":["https://openalex.org/I121820613"],"apc_list":null,"apc_paid":null,"fwci":3.1849,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.92189497,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"274","last_page":"284"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998999834060669,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9986000061035156,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9922000169754028,"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/transactional-memory","display_name":"Transactional memory","score":0.923642635345459},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8727825880050659},{"id":"https://openalex.org/keywords/commit","display_name":"Commit","score":0.7544926404953003},{"id":"https://openalex.org/keywords/software-transactional-memory","display_name":"Software transactional memory","score":0.6313925981521606},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5347805023193359},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4884723722934723},{"id":"https://openalex.org/keywords/speculative-execution","display_name":"Speculative execution","score":0.42622458934783936},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4154263436794281},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.32722580432891846},{"id":"https://openalex.org/keywords/database-transaction","display_name":"Database transaction","score":0.2931457459926605},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.16323024034500122},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09491541981697083},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08028140664100647}],"concepts":[{"id":"https://openalex.org/C134277064","wikidata":"https://www.wikidata.org/wiki/Q878206","display_name":"Transactional memory","level":3,"score":0.923642635345459},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8727825880050659},{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.7544926404953003},{"id":"https://openalex.org/C167149655","wikidata":"https://www.wikidata.org/wiki/Q1189004","display_name":"Software transactional memory","level":4,"score":0.6313925981521606},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5347805023193359},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4884723722934723},{"id":"https://openalex.org/C141331961","wikidata":"https://www.wikidata.org/wiki/Q2164465","display_name":"Speculative execution","level":2,"score":0.42622458934783936},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4154263436794281},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.32722580432891846},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.2931457459926605},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.16323024034500122},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09491541981697083},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08028140664100647},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpca.2016.7446071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca.2016.7446071","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Symposium on High Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.9200000166893005,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1991397056","https://openalex.org/W1993179651","https://openalex.org/W2024122052","https://openalex.org/W2025252760","https://openalex.org/W2040490564","https://openalex.org/W2057769886","https://openalex.org/W2092656977","https://openalex.org/W2093043622","https://openalex.org/W2100716766","https://openalex.org/W2101209730","https://openalex.org/W2101997431","https://openalex.org/W2105055683","https://openalex.org/W2113751407","https://openalex.org/W2138218143","https://openalex.org/W2167729440","https://openalex.org/W2169656512","https://openalex.org/W2545744347","https://openalex.org/W2611473431","https://openalex.org/W3151404106","https://openalex.org/W3152011683","https://openalex.org/W4238433345","https://openalex.org/W4244583165","https://openalex.org/W6674957326","https://openalex.org/W6685014038"],"related_works":["https://openalex.org/W3148592861","https://openalex.org/W1566614300","https://openalex.org/W2301426996","https://openalex.org/W2247767253","https://openalex.org/W2150395102","https://openalex.org/W119258518","https://openalex.org/W2121462962","https://openalex.org/W2074024830","https://openalex.org/W2178806497","https://openalex.org/W1491272544"],"abstract_inverted_index":{"It":[0],"has":[1],"been":[2],"proposed":[3,18],"that":[4,34,96,107,120,133],"Transactional":[5],"Memory":[6],"be":[7,111],"added":[8],"to":[9,25,49,98,110],"Graphics":[10],"Processing":[11],"Units":[12,118,125],"(GPUs)":[13],"in":[14,122],"recent":[15],"years.":[16],"One":[17],"hardware":[19,155],"design,":[20],"Warp":[21],"TM,":[22],"can":[23,35],"scale":[24],"1000s":[26],"of":[27,40,58,64,88,137,143,162],"concurrent":[28],"transactions.":[29,146],"As":[30],"a":[31,69,153],"programming":[32],"method":[33],"atomicize":[36],"an":[37],"arbitrary":[38],"number":[39],"memory":[41,54],"access":[42],"locations":[43],"and":[44,72,84,90,92,128,139],"greatly":[45,166],"reduce":[46],"the":[47,56,86,116,123,135,140,160,163],"efforts":[48],"program":[50],"parallel":[51],"applications,":[52],"transactional":[53],"handles":[55],"complexity":[57],"inter-thread":[59],"synchronization.":[60],"However,":[61],"when":[62],"thousands":[63],"transactions":[65],"run":[66],"concurrently":[67],"on":[68],"GPU,":[70],"conflicts":[71,89,100,109],"resource":[73],"contentions":[74,91],"arise,":[75],"causing":[76],"performance":[77,141],"loss.":[78],"In":[79],"this":[80],"paper,":[81],"we":[82],"identify":[83],"analyze":[85],"cause":[87],"propose":[93],"two":[94,148,164],"enhancements":[95,149,165],"try":[97],"resolve":[99],"early:":[101],"(1)":[102],"Early-Abort":[103],"global":[104],"conflict":[105,138],"resolution":[106],"allows":[108],"detected":[112],"before":[113],"they":[114],"reach":[115],"Commit":[117,124],"so":[119],"contention":[121],"is":[126],"reduced":[127],"(2)":[129],"Pause-and-Go":[130],"execution":[131,169],"scheme":[132],"reduces":[134],"chance":[136],"penalty":[142],"re-executing":[144],"long":[145],"These":[147],"are":[150],"enabled":[151],"by":[152],"single":[154],"modification.":[156],"Our":[157],"evaluation":[158],"shows":[159],"combination":[161],"improves":[167],"overall":[168],"speed":[170],"while":[171],"reducing":[172],"energy":[173],"consumption.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
