{"id":"https://openalex.org/W3012406028","doi":"https://doi.org/10.1145/3373376.3378520","title":"Dimensionality-Aware Redundant SIMT Instruction Elimination","display_name":"Dimensionality-Aware Redundant SIMT Instruction Elimination","publication_year":2020,"publication_date":"2020-03-09","ids":{"openalex":"https://openalex.org/W3012406028","doi":"https://doi.org/10.1145/3373376.3378520","mag":"3012406028"},"language":"en","primary_location":{"id":"doi:10.1145/3373376.3378520","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3373376.3378520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems","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/A5019259173","display_name":"Tsung Tai Yeh","orcid":"https://orcid.org/0000-0002-2401-9916"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tsung Tai Yeh","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089147958","display_name":"Roland N. Green","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roland N. Green","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038577900","display_name":"Timothy G. Rogers","orcid":"https://orcid.org/0009-0002-0736-3149"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Timothy G. Rogers","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019259173"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":1.8711,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.85056818,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1327","last_page":"1340"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9987999796867371,"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":0.996999979019165,"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":0.8655782341957092},{"id":"https://openalex.org/keywords/operand","display_name":"Operand","score":0.8396763205528259},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7319196462631226},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6688447594642639},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6657372713088989},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5800591111183167},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.46733248233795166},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.46442094445228577},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.46360787749290466},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.45821210741996765},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.45699024200439453},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.23001673817634583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1208983063697815}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8655782341957092},{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.8396763205528259},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7319196462631226},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6688447594642639},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6657372713088989},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5800591111183167},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.46733248233795166},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.46442094445228577},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.46360787749290466},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.45821210741996765},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.45699024200439453},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.23001673817634583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1208983063697815},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","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/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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3373376.3378520","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3373376.3378520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1482635212","https://openalex.org/W1979527452","https://openalex.org/W1983235612","https://openalex.org/W1991518265","https://openalex.org/W1998886328","https://openalex.org/W2005826155","https://openalex.org/W2020517863","https://openalex.org/W2021211271","https://openalex.org/W2042411977","https://openalex.org/W2080592089","https://openalex.org/W2093043622","https://openalex.org/W2095667776","https://openalex.org/W2095872092","https://openalex.org/W2098505406","https://openalex.org/W2103246828","https://openalex.org/W2118826546","https://openalex.org/W2124861237","https://openalex.org/W2129232868","https://openalex.org/W2130653499","https://openalex.org/W2134705409","https://openalex.org/W2138761132","https://openalex.org/W2142444503","https://openalex.org/W2144334298","https://openalex.org/W2149234156","https://openalex.org/W2150073849","https://openalex.org/W2153963140","https://openalex.org/W2154790323","https://openalex.org/W2237817213","https://openalex.org/W2322230929","https://openalex.org/W2486564422","https://openalex.org/W2604269348","https://openalex.org/W2626935846","https://openalex.org/W2795002137","https://openalex.org/W4252742548","https://openalex.org/W4300461182","https://openalex.org/W4302344769"],"related_works":["https://openalex.org/W2556282987","https://openalex.org/W99277194","https://openalex.org/W2111180768","https://openalex.org/W2162270818","https://openalex.org/W2125561225","https://openalex.org/W1938177223","https://openalex.org/W4250699891","https://openalex.org/W4316658886","https://openalex.org/W3091978438","https://openalex.org/W2371766777"],"abstract_inverted_index":{"In":[0],"massively":[1],"multithreaded":[2],"architectures,":[3],"redundantly":[4],"executing":[5],"the":[6,10,47,68],"same":[7,11],"instruction":[8,33],"with":[9],"operands":[12],"in":[13,40,83],"different":[14],"threads":[15],"is":[16,77],"a":[17,31,72],"significant":[18,78],"source":[19],"of":[20,67],"inefficiency.":[21],"This":[22],"paper":[23],"introduces":[24],"Dimensionality-Aware":[25],"Redundant":[26],"SIMT":[27],"Instruction":[28],"Elimination":[29],"(DARSIE),":[30],"non-speculative":[32],"skipping":[34],"mechanism":[35],"to":[36,56],"reduce":[37],"redundant":[38,58],"operations":[39],"GPUs.":[41],"DARSIE":[42,70],"uses":[43],"static":[44],"markings":[45],"from":[46],"compiler":[48],"and":[49],"information":[50],"obtained":[51],"at":[52],"kernel":[53],"launch":[54],"time":[55],"skip":[57],"instructions":[59,82],"before":[60],"they":[61],"are":[62],"fetched,":[63],"keeping":[64],"them":[65],"out":[66],"pipeline.":[69],"exploits":[71],"new":[73],"observation":[74],"that":[75],"there":[76],"redundancy":[79],"across":[80],"warp":[81],"multi-dimensional":[84],"threadblocks.":[85]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}
