{"id":"https://openalex.org/W4386510480","doi":"https://doi.org/10.1145/3605731.3605904","title":"Enhancing LLVM Optimizations for Linear Recurrence Programs on RVV","display_name":"Enhancing LLVM Optimizations for Linear Recurrence Programs on RVV","publication_year":2023,"publication_date":"2023-08-07","ids":{"openalex":"https://openalex.org/W4386510480","doi":"https://doi.org/10.1145/3605731.3605904"},"language":"en","primary_location":{"id":"doi:10.1145/3605731.3605904","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3605731.3605904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd International Conference on Parallel Processing Workshops","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/A5065924524","display_name":"Hung-Ming Lai","orcid":"https://orcid.org/0000-0002-8623-0469"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Hung-Ming Lai","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038803698","display_name":"Jenq\u2010Kuen Lee","orcid":"https://orcid.org/0000-0001-9919-6258"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jenq-Kuen Lee","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041551416","display_name":"Yuan\u2010Shin Hwang","orcid":null},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yuan-Shin Hwang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taiwan","institution_ids":["https://openalex.org/I154864474"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065924524"],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":0.924,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71796482,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"79","last_page":"87"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization 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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9969000220298767,"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"}},{"id":"https://openalex.org/T11522","display_name":"VLSI and FPGA Design Techniques","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/computer-science","display_name":"Computer science","score":0.7375822067260742},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.32002636790275574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7375822067260742},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.32002636790275574}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3605731.3605904","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3605731.3605904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd International Conference on Parallel Processing Workshops","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2483814599","display_name":null,"funder_award_id":"Google-NTHU-2022-2023","funder_id":"https://openalex.org/F4320309327","funder_display_name":"Google"}],"funders":[{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1871378126","https://openalex.org/W1963965124","https://openalex.org/W1967810725","https://openalex.org/W2127324789","https://openalex.org/W2143462372","https://openalex.org/W2143964612","https://openalex.org/W2765674446","https://openalex.org/W2897836007","https://openalex.org/W3140574618","https://openalex.org/W3143155282","https://openalex.org/W4233587516","https://openalex.org/W4285147964","https://openalex.org/W4320067907"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032"],"abstract_inverted_index":{"The":[0,170],"RISC-V":[1,21],"Vector":[2],"Extension":[3],"(RVV)":[4],"has":[5],"emerged":[6],"as":[7],"a":[8,50,94,98],"promising":[9],"vector":[10,26,29,59,78],"architecture":[11],"for":[12,20,54,87,120],"high-performance":[13],"computing.":[14],"It":[15,61],"enables":[16],"parallel":[17],"computing":[18],"capability":[19],"CPUs":[22],"by":[23,133],"introducing":[24],"additional":[25],"instructions":[27],"and":[28,71,114,165],"registers.":[30],"To":[31],"fully":[32],"utilize":[33],"the":[34,43,63,68,76,125,134,150,160],"potential":[35],"of":[36,46,138,152,163],"RVV,":[37,92,158],"it":[38,74],"is":[39,49,118,131],"crucial":[40],"to":[41,66,75,148,184],"optimize":[42],"auto-vectorization":[44,86,126],"capabilities":[45],"compilers.":[47],"Auto-vectorization":[48],"widely":[51],"used":[52],"method":[53],"parallelizing":[55],"scalar":[56],"programs":[57,90,107,156],"on":[58,83,91,97,127,157,181],"machines.":[60],"examines":[62],"input":[64],"program":[65],"identify":[67],"parallelizable":[69],"section":[70],"then":[72],"maps":[73],"underlying":[77],"architecture.":[79],"This":[80],"paper":[81],"focuses":[82],"enhancing":[84],"LLVM\u2019s":[85,129,167],"linear":[88,154],"recurrence":[89,106,139,155],"with":[93],"specific":[95],"emphasis":[96],"well-studied":[99],"computation":[100],"pattern":[101],"called":[102],"scan":[103],"(all-prefix-sums).":[104],"Linear":[105],"are":[108],"prevalent":[109],"in":[110],"diverse":[111],"computational":[112],"domains,":[113],"their":[115],"efficient":[116],"execution":[117],"vital":[119],"achieving":[121],"optimal":[122],"performance.":[123],"However,":[124],"current":[128],"vectorizer":[130],"hindered":[132],"loop-carried":[135],"data":[136],"dependence":[137],"programs.":[140],"In":[141],"this":[142],"work,":[143],"we":[144],"propose":[145],"novel":[146],"techniques":[147],"address":[149],"challenges":[151],"auto-vectorizing":[153],"leveraging":[159],"unique":[161],"features":[162],"RVV":[164,182],"extending":[166],"vectorization":[168],"capabilities.":[169],"experiment":[171],"shows":[172],"that":[173],"our":[174],"auto-vectorized":[175],"plus-scan":[176],"can":[177],"achieved":[178],"17.64x":[179],"speedup":[180],"compared":[183],"LLVM":[185],"16.0.0.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}