{"id":"https://openalex.org/W7166654449","doi":"https://doi.org/10.1145/3774895.3812195","title":"RV-IR: An MLIR-Based Architecture-Aware Intermediate Representation for Heterogeneous RISC-V AI Acceleration","display_name":"RV-IR: An MLIR-Based Architecture-Aware Intermediate Representation for Heterogeneous RISC-V AI Acceleration","publication_year":2026,"publication_date":"2026-06-30","ids":{"openalex":"https://openalex.org/W7166654449","doi":"https://doi.org/10.1145/3774895.3812195"},"language":null,"primary_location":{"id":"doi:10.1145/3774895.3812195","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774895.3812195","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM International Conference on Supercomputing - Workshops","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774895.3812195","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109724239","display_name":"Zexin Jian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zexin Jian","raw_affiliation_strings":["SKLP, Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-4129-8304","affiliations":[{"raw_affiliation_string":"SKLP, Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081221505","display_name":"Shi Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhui Jia","raw_affiliation_strings":["SKLP, Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-5364-0816","affiliations":[{"raw_affiliation_string":"SKLP, Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095381671","display_name":"Chunwei Xia","orcid":"https://orcid.org/0000-0003-2014-5453"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chunwei Xia","raw_affiliation_strings":["University of Leeds, Leads, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-2014-5453","affiliations":[{"raw_affiliation_string":"University of Leeds, Leads, United Kingdom","institution_ids":["https://openalex.org/I130828816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401412","display_name":"Di Wang","orcid":"https://orcid.org/0000-0002-2418-7987"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Wang","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2418-7987","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100334369","display_name":"Chenxi Wang","orcid":"https://orcid.org/0000-0002-1451-3101"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxi Wang","raw_affiliation_strings":["SKLP, Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1451-3101","affiliations":[{"raw_affiliation_string":"SKLP, Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":2,"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":0.78826185,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"45","last_page":"49"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.5436999797821045,"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":0.5436999797821045,"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":0.06310000270605087,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.044199999421834946,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/compiler","display_name":"Compiler","score":0.7353000044822693},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.576200008392334},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5616999864578247},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5608000159263611},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.478300005197525},{"id":"https://openalex.org/keywords/modularity","display_name":"Modularity (biology)","score":0.41929998993873596},{"id":"https://openalex.org/keywords/invocation","display_name":"Invocation","score":0.4052000045776367},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.3571999967098236}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8341000080108643},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7353000044822693},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.7246000170707703},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.576200008392334},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5616999864578247},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5608000159263611},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.478300005197525},{"id":"https://openalex.org/C2779478453","wikidata":"https://www.wikidata.org/wiki/Q6889748","display_name":"Modularity (biology)","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4189000129699707},{"id":"https://openalex.org/C2776527387","wikidata":"https://www.wikidata.org/wiki/Q1671839","display_name":"Invocation","level":2,"score":0.4052000045776367},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3479999899864197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3467000126838684},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.3303000032901764},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C2776834041","wikidata":"https://www.wikidata.org/wiki/Q25346349","display_name":"Execution model","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.28690001368522644},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2847000062465668},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C77660490","wikidata":"https://www.wikidata.org/wiki/Q244916","display_name":"Intermediate language","level":3,"score":0.26440000534057617},{"id":"https://openalex.org/C2982832238","wikidata":"https://www.wikidata.org/wiki/Q5531640","display_name":"General purpose","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C2779019669","wikidata":"https://www.wikidata.org/wiki/Q25203946","display_name":"Asynchrony (computer programming)","level":3,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774895.3812195","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774895.3812195","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM International Conference on Supercomputing - Workshops","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774895.3812195","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774895.3812195","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM International Conference on Supercomputing - Workshops","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6347491145133972,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W3213528054","https://openalex.org/W4246166885","https://openalex.org/W4308090791"],"related_works":[],"abstract_inverted_index":{"The":[0],"growing":[1],"interest":[2],"in":[3],"RISC-V-based":[4],"AI":[5,83],"accelerators":[6],"creates":[7],"an":[8],"opportunity":[9],"to":[10],"build":[11],"open":[12],"and":[13,29,51,65],"customizable":[14],"machine":[15],"learning":[16],"systems,":[17],"but":[18],"it":[19],"also":[20],"exposes":[21],"a":[22],"compiler":[23,39],"gap":[24],"between":[25],"generic":[26,70],"tensor":[27,63],"programs":[28],"accelerator-specific":[30],"execution":[31],"semantics.":[32],"In":[33],"practical":[34],"heterogeneous":[35],"CPU\u2013NPU":[36],"deployments,":[37],"the":[38,77],"must":[40],"reason":[41],"about":[42],"explicit":[43],"memory":[44],"spaces,":[45],"accelerator":[46],"invocation":[47],"boundaries,":[48],"asynchronous":[49],"coordination,":[50],"software-managed":[52],"data":[53],"movement.":[54],"Existing":[55],"MLIR":[56],"infrastructures":[57],"provide":[58],"strong":[59],"support":[60],"for":[61],"high-level":[62],"optimization":[64],"progressive":[66],"lowering,":[67],"yet":[68],"these":[69],"abstractions":[71],"do":[72],"not":[73],"always":[74],"directly":[75],"encode":[76],"architectural":[78],"contracts":[79],"needed":[80],"by":[81],"RISC-V":[82],"backends.":[84]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-01T00:00:00"}
