{"id":"https://openalex.org/W4411726700","doi":"https://doi.org/10.1109/iscas56072.2025.11043684","title":"Improve GPGPU Front-end Efficiency Via Inter-Warp Instruction Sharing","display_name":"Improve GPGPU Front-end Efficiency Via Inter-Warp Instruction Sharing","publication_year":2025,"publication_date":"2025-05-25","ids":{"openalex":"https://openalex.org/W4411726700","doi":"https://doi.org/10.1109/iscas56072.2025.11043684"},"language":"en","primary_location":{"id":"doi:10.1109/iscas56072.2025.11043684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas56072.2025.11043684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Circuits and Systems (ISCAS)","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/A5053181769","display_name":"Yu\u2010Yu Hsiao","orcid":"https://orcid.org/0000-0001-9296-4517"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Yu Hsiao","raw_affiliation_strings":["National Cheng Kung University,Department of Electrical Engineering,Tainan,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Cheng Kung University,Department of Electrical Engineering,Tainan,Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019482259","display_name":"L.- Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Liang-Chou Chen","raw_affiliation_strings":["National Cheng Kung University,Department of Electrical Engineering,Tainan,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Cheng Kung University,Department of Electrical Engineering,Tainan,Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111582905","display_name":"Chung\u2010Ho Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Ho Chen","raw_affiliation_strings":["National Cheng Kung University,Department of Electrical Engineering,Tainan,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Cheng Kung University,Department of Electrical Engineering,Tainan,Taiwan","institution_ids":["https://openalex.org/I91807558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06614439,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.7644000053405762,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.7644000053405762,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7597000002861023,"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":0.7113999724388123,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7751067876815796},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.7359226942062378},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.561249315738678},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4506072700023651},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.43794792890548706},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4070923924446106},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3294981122016907},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.23345455527305603},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19595414400100708},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.1172839105129242}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7751067876815796},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.7359226942062378},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.561249315738678},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4506072700023651},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.43794792890548706},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4070923924446106},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3294981122016907},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.23345455527305603},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19595414400100708},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.1172839105129242}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas56072.2025.11043684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas56072.2025.11043684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8399999737739563,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W18104785","https://openalex.org/W1979527452","https://openalex.org/W2152198615","https://openalex.org/W2203504382","https://openalex.org/W2794160862","https://openalex.org/W2919358988","https://openalex.org/W2989532353","https://openalex.org/W3100327344","https://openalex.org/W4389476360","https://openalex.org/W4401211787","https://openalex.org/W6687070517","https://openalex.org/W6760272376"],"related_works":["https://openalex.org/W1998013902","https://openalex.org/W1656096860","https://openalex.org/W2550108858","https://openalex.org/W2095928260","https://openalex.org/W2268149564","https://openalex.org/W1781968824","https://openalex.org/W4247993032","https://openalex.org/W2117274229","https://openalex.org/W2125503095","https://openalex.org/W1963867998"],"abstract_inverted_index":{"General-purpose":[0],"GPUs":[1],"(GPGPUs)":[2],"leverage":[3],"thousands":[4],"of":[5,119],"threads":[6],"per":[7],"core":[8],"to":[9,40,51,69,86,98,112],"attain":[10],"high":[11,29],"throughput.":[12],"Threads":[13],"executing":[14],"the":[15,33,42],"same":[16],"program":[17],"are":[18],"dynamically":[19],"grouped":[20],"into":[21],"SIMD":[22],"batches":[23],"known":[24],"as":[25],"warps,":[26],"which":[27],"exhibit":[28],"localities":[30],"in":[31,46],"accessing":[32],"instruction":[34,43,93],"cache.":[35],"Current":[36],"designs":[37],"allow":[38],"warps":[39],"access":[41],"cache":[44],"independently":[45],"a":[47,64,83,91,115],"time-sharing":[48],"manner,":[49],"leading":[50],"significant":[52],"fetch":[53,79,84],"redundancies.":[54],"To":[55],"address":[56],"this":[57],"issue,":[58],"we":[59],"introduce":[60],"Inter-Warp":[61],"Instruction":[62],"Sharing,":[63],"lightweight":[65],"yet":[66],"effective":[67],"technique":[68],"improve":[70],"GPGPU":[71],"front-end":[72],"efficiency.":[73],"The":[74],"mechanism":[75],"incorporates":[76],"an":[77],"improved":[78],"request":[80],"arbitration":[81],"algorithm,":[82],"filter":[85],"prevent":[87],"redundant":[88],"fetching,":[89],"and":[90],"modified":[92],"buffer":[94],"that":[95,104],"broadcasts":[96],"instructions":[97],"all":[99],"active":[100],"warps.":[101],"We":[102],"show":[103],"our":[105],"approach":[106],"reduces":[107],"I-Cache":[108],"accesses":[109],"by":[110],"up":[111],"85%,":[113],"achieving":[114],"geometric":[116],"mean":[117],"reduction":[118],"68%":[120],"without":[121],"performance":[122],"degradation.":[123]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}