{"id":"https://openalex.org/W4285147964","doi":"https://doi.org/10.1109/mm.2022.3184867","title":"Performance Left on the Table: An Evaluation of Compiler Autovectorization for RISC-V","display_name":"Performance Left on the Table: An Evaluation of Compiler Autovectorization for RISC-V","publication_year":2022,"publication_date":"2022-06-21","ids":{"openalex":"https://openalex.org/W4285147964","doi":"https://doi.org/10.1109/mm.2022.3184867"},"language":"en","primary_location":{"id":"doi:10.1109/mm.2022.3184867","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mm.2022.3184867","pdf_url":null,"source":{"id":"https://openalex.org/S59697426","display_name":"IEEE Micro","issn_l":"0272-1732","issn":["0272-1732","1937-4143"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Micro","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/A5027611597","display_name":"Neil Adit","orcid":"https://orcid.org/0000-0003-1126-5920"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Neil Adit","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004782337","display_name":"Adrian Sampson","orcid":"https://orcid.org/0000-0003-0837-8924"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adrian Sampson","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5027611597"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":6.0653,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.9723171,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"42","issue":"5","first_page":"41","last_page":"48"},"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":0.9987000226974487,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9976999759674072,"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":0.8697326183319092},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7132695317268372},{"id":"https://openalex.org/keywords/reduced-instruction-set-computing","display_name":"Reduced instruction set computing","score":0.6902053952217102},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5939959287643433},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5697923302650452},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4650871157646179},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.43577840924263},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.37886881828308105},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3231567144393921},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.16121110320091248}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8697326183319092},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7132695317268372},{"id":"https://openalex.org/C126298526","wikidata":"https://www.wikidata.org/wiki/Q189376","display_name":"Reduced instruction set computing","level":3,"score":0.6902053952217102},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5939959287643433},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5697923302650452},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4650871157646179},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.43577840924263},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.37886881828308105},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3231567144393921},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.16121110320091248}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mm.2022.3184867","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mm.2022.3184867","pdf_url":null,"source":{"id":"https://openalex.org/S59697426","display_name":"IEEE Micro","issn_l":"0272-1732","issn":["0272-1732","1937-4143"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Micro","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3465611464","display_name":null,"funder_award_id":"1723715","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4502277801","display_name":null,"funder_award_id":"FA8650-18-2-7863","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8209250081","display_name":null,"funder_award_id":"1845952","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2013156670","https://openalex.org/W2111394443","https://openalex.org/W2147657366","https://openalex.org/W2613264175","https://openalex.org/W2741674747","https://openalex.org/W2979513934","https://openalex.org/W3035844627","https://openalex.org/W3086504363","https://openalex.org/W3102724434","https://openalex.org/W3123542955","https://openalex.org/W3140574618","https://openalex.org/W3153044352","https://openalex.org/W4244894488","https://openalex.org/W4249544322","https://openalex.org/W4251637954","https://openalex.org/W4294560773","https://openalex.org/W6720647260"],"related_works":["https://openalex.org/W2538644970","https://openalex.org/W4376881175","https://openalex.org/W4310584696","https://openalex.org/W4364295250","https://openalex.org/W4237840813","https://openalex.org/W2128502296","https://openalex.org/W4385730960","https://openalex.org/W1998013902","https://openalex.org/W2993622674","https://openalex.org/W1833044483"],"abstract_inverted_index":{"Next-generation":[0],"length-agnostic":[1,54,70,142],"vector":[2,10,15,25,82,86,143],"instruction":[3],"set":[4,91,127],"architecture":[5],"(ISA)":[6],"designs,":[7],"the":[8,59,64,80,98,103],"RISC-V":[9,81,118],"extension,":[11],"and":[12,37,71,84,106,133,138],"ARM\u2019s":[13],"scalable":[14],"extension":[16,83],"enable":[17],"software":[18],"portability":[19],"across":[20],"hardware":[21],"implementations":[22],"with":[23],"different":[24],"engines.":[26],"While":[27],"traditional,":[28],"fixed-length":[29,72],"single-instruction\u2013multiple-data":[30],"ISA":[31],"instructions,":[32],"such":[33],"as":[34],"Intel":[35],"AVX":[36],"ARM":[38],"Neon,":[39],"enjoy":[40],"mature":[41],"compiler":[42,47,60],"support":[43,48,77,101],"for":[44,52,78,130,141],"automatic":[45],"vectorization,":[46],"is":[49],"still":[50],"emerging":[51],"these":[53],"ISAs.":[55,87],"This":[56],"work":[57],"studies":[58,123],"shortcomings":[61],"that":[62],"constitute":[63],"gap":[65],"in":[66,102,136],"autovectorization":[67],"capabilities":[68],"between":[69],"architectures.":[73],"We":[74,88,120],"examine":[75,108],"LLVM\u2019s":[76],"both":[79,122],"traditional":[85],"study":[89],"a":[90,109,126],"of":[92,100,128],"synthetic":[93],"scalar":[94],"loops":[95],"to":[96,113,116,124],"compare":[97,114],"breadth":[99],"two":[104],"settings,":[105],"we":[107],"real":[110],"benchmark":[111],"suite":[112],"autovectorized":[115],"hand-vectorized":[117],"code.":[119],"use":[121],"distill":[125],"recommendations":[129],"engineering":[131],"improvements":[132],"future":[134],"research":[135],"compilers":[137],"programming":[139],"models":[140],"programming.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
