{"id":"https://openalex.org/W4407245202","doi":"https://doi.org/10.1145/3696443.3708952","title":"A Multi-level Compiler Backend for Accelerated Micro-kernels Targeting RISC-V ISA Extensions","display_name":"A Multi-level Compiler Backend for Accelerated Micro-kernels Targeting RISC-V ISA Extensions","publication_year":2025,"publication_date":"2025-02-22","ids":{"openalex":"https://openalex.org/W4407245202","doi":"https://doi.org/10.1145/3696443.3708952"},"language":"en","primary_location":{"id":"doi:10.1145/3696443.3708952","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3696443.3708952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM/IEEE International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.04063","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093264943","display_name":"Alexandre Lopoukhine","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Alexandre Lopoukhine","raw_affiliation_strings":["University of Cambridge, Cambridge, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064922215","display_name":"Federico Ficarelli","orcid":"https://orcid.org/0000-0003-1447-8278"},"institutions":[{"id":"https://openalex.org/I4210119786","display_name":"Cineca","ror":"https://ror.org/02f013h18","country_code":"IT","type":"other","lineage":["https://openalex.org/I4210119786"]},{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Federico Ficarelli","raw_affiliation_strings":["Cineca, Bologna, Italy","University of Bologna, Bologna, Italy"],"affiliations":[{"raw_affiliation_string":"Cineca, Bologna, Italy","institution_ids":["https://openalex.org/I4210119786"]},{"raw_affiliation_string":"University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039051400","display_name":"Christos Vasiladiotis","orcid":"https://orcid.org/0000-0001-7936-2183"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christos Vasiladiotis","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092672044","display_name":"Anton Lydike","orcid":"https://orcid.org/0009-0001-9389-8512"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anton Lydike","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092876696","display_name":"Josse Van Delm","orcid":"https://orcid.org/0000-0002-9503-403X"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Josse Van Delm","raw_affiliation_strings":["KU Leuven, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093992804","display_name":"Alban Dutilleul","orcid":"https://orcid.org/0009-0004-7978-0608"},"institutions":[{"id":"https://openalex.org/I4210146044","display_name":"\u00c9cole Normale Sup\u00e9rieure de Rennes","ror":"https://ror.org/03rxtdc22","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210146044","https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Alban Dutilleul","raw_affiliation_strings":["ENS Rennes, Rennes, France"],"affiliations":[{"raw_affiliation_string":"ENS Rennes, Rennes, France","institution_ids":["https://openalex.org/I4210146044"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043408422","display_name":"Luca Benini","orcid":"https://orcid.org/0000-0001-8068-3806"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]},{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["CH","IT"],"is_corresponding":false,"raw_author_name":"Luca Benini","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland","University of Bologna, Bologna, Italy"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012150553","display_name":"Marian Verhelst","orcid":"https://orcid.org/0000-0003-3495-9263"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Marian Verhelst","raw_affiliation_strings":["KU Leuven, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055618037","display_name":"Tobias Grosser","orcid":"https://orcid.org/0000-0003-3874-6003"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tobias Grosser","raw_affiliation_strings":["University of Cambridge, Cambridge, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5093264943"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":6.6786,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.95570734,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"163","last_page":"178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987000226974487,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9939000010490417,"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":0.8836797475814819},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8718230724334717},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.5598961710929871},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5489495396614075},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.5282499194145203},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.5070500373840332},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.48338642716407776},{"id":"https://openalex.org/keywords/abstraction-layer","display_name":"Abstraction layer","score":0.4678317606449127},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4656553864479065},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.45183265209198},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4459025263786316},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44580236077308655},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.437614381313324},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.43724918365478516},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.4228602349758148},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.40623682737350464},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.38050782680511475},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3073393702507019},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.29426151514053345},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.2422913908958435}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8836797475814819},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8718230724334717},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.5598961710929871},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5489495396614075},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.5282499194145203},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5070500373840332},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.48338642716407776},{"id":"https://openalex.org/C147358964","wikidata":"https://www.wikidata.org/wiki/Q1200992","display_name":"Abstraction layer","level":3,"score":0.4678317606449127},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4656553864479065},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.45183265209198},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4459025263786316},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44580236077308655},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.437614381313324},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.43724918365478516},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.4228602349758148},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.40623682737350464},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.38050782680511475},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3073393702507019},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29426151514053345},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2422913908958435},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3696443.3708952","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3696443.3708952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM/IEEE International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.04063","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.04063","pdf_url":"https://arxiv.org/pdf/2502.04063","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:cris.unibo.it:11585/1040754","is_oa":false,"landing_page_url":"https://hdl.handle.net/11585/1040754","pdf_url":null,"source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/9eb510f9-9ba6-4de3-818d-6ff2bbe004fc","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/9eb510f9-9ba6-4de3-818d-6ff2bbe004fc","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lopoukhine, A, Ficarelli, F, Vasiladiotis, C, Lydike, A, Delm, J V, Dutilleul, A, Benini, L, Verhelst, M & Grosser, T 2025, A Multi-level Compiler Backend for Accelerated Micro-kernels Targeting RISC-V ISA Extensions. in CGO '25: Proceedings of the 23rd ACM/IEEE International Symposium on Code Generation and Optimization. International Symposium on Code Generation and Optimization, vol. 23, pp. 163-178. https://doi.org/10.1145/3696443.3708952","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/382568","is_oa":false,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/382568","pdf_url":null,"source":{"id":"https://openalex.org/S4306401776","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Object"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.04063","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.04063","pdf_url":"https://arxiv.org/pdf/2502.04063","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407245202.pdf","grobid_xml":"https://content.openalex.org/works/W4407245202.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W1883303451","https://openalex.org/W1998983218","https://openalex.org/W2002257715","https://openalex.org/W2018768276","https://openalex.org/W2055312318","https://openalex.org/W2070566991","https://openalex.org/W2073061372","https://openalex.org/W2102976251","https://openalex.org/W2167850096","https://openalex.org/W2412152731","https://openalex.org/W2590246587","https://openalex.org/W2618530766","https://openalex.org/W2798482398","https://openalex.org/W2804500013","https://openalex.org/W2898231337","https://openalex.org/W2905135312","https://openalex.org/W2912012512","https://openalex.org/W2946485102","https://openalex.org/W2946705112","https://openalex.org/W2954698171","https://openalex.org/W2963255460","https://openalex.org/W3002612001","https://openalex.org/W3013692244","https://openalex.org/W3016309475","https://openalex.org/W3059812300","https://openalex.org/W3090487264","https://openalex.org/W3092864146","https://openalex.org/W3105514082","https://openalex.org/W3112773671","https://openalex.org/W3122286897","https://openalex.org/W3123054690","https://openalex.org/W3155384757","https://openalex.org/W3156745629","https://openalex.org/W3196320218","https://openalex.org/W4206371601","https://openalex.org/W4220850685","https://openalex.org/W4226443139","https://openalex.org/W4240382083","https://openalex.org/W4244254628","https://openalex.org/W4246166885","https://openalex.org/W4281707342","https://openalex.org/W4285167314","https://openalex.org/W4297676683","https://openalex.org/W4308596141","https://openalex.org/W4312342987","https://openalex.org/W4318256790","https://openalex.org/W4376562663","https://openalex.org/W4388685623","https://openalex.org/W4392265981","https://openalex.org/W4395106400","https://openalex.org/W6912007422"],"related_works":["https://openalex.org/W2127497159","https://openalex.org/W2172096703","https://openalex.org/W1989702012","https://openalex.org/W1987578288","https://openalex.org/W3140187916","https://openalex.org/W4242404469","https://openalex.org/W2132832499","https://openalex.org/W1933077055","https://openalex.org/W2553760675","https://openalex.org/W4213087105"],"abstract_inverted_index":{"High-performance":[0],"micro-kernels":[1,34],"must":[2],"fully":[3],"exploit":[4],"today\u2019s":[5],"diverse":[6,90],"and":[7,62,84,119,152],"specialized":[8,38,179],"hardware":[9,117,126],"to":[10,14,37,78,95,100,155,178],"deliver":[11],"peak":[12],"performance":[13],"deep":[15],"neural":[16],"networks":[17],"(DNNs).":[18],"While":[19],"higher-level":[20],"optimizations":[21],"for":[22,70,112],"DNNs":[23],"are":[24,35],"offered":[25],"by":[26,107],"numerous":[27],"compilers":[28,47],"(e.g.,":[29,48],"MLIR,":[30],"TVM,":[31],"OpenXLA),":[32],"performance-critical":[33],"left":[36],"code":[39,68,98],"generators":[40],"or":[41],"handwritten":[42],"assembly.":[43],"Even":[44],"though":[45],"widely-adopted":[46],"LLVM,":[49],"GCC)":[50],"offer":[51],"tuned":[52],"backends,":[53],"their":[54],"CPU-focused":[55],"input":[56],"abstraction,":[57],"unstructured":[58],"intermediate":[59],"representation":[60],"(IR)":[61],"general-purpose":[63],"best-effort":[64],"design":[65],"inhibit":[66],"tailored":[67],"generation":[69,99],"innovative":[71],"hardware.":[72,180],"We":[73,103,139],"think":[74],"it":[75],"is":[76],"time":[77],"widen":[79],"the":[80,125,167,173],"classical":[81,149],"hourglass":[82,169],"backend":[83,111,168],"embrace":[85],"progressive":[86],"lowering":[87],"across":[88,161],"a":[89,109,113],"set":[91,136],"of":[92,129],"structured":[93,145],"abstractions":[94,177],"bring":[96],"domain-specific":[97,176],"compiler":[101],"backends.":[102],"demonstrate":[104],"this":[105],"concept":[106],"implementing":[108],"custom":[110,134],"RISC-V-based":[114],"accelerator":[115],"with":[116],"loops":[118],"streaming":[120],"registers,":[121],"leveraging":[122],"knowledge":[123],"about":[124],"at":[127],"levels":[128],"abstraction":[130],"that":[131],"match":[132],"its":[133],"instruction":[135],"architecture":[137],"(ISA).":[138],"use":[140],"incremental":[141],"register":[142],"allocation":[143],"over":[144],"IRs,":[146],"while":[147],"dropping":[148],"spilling":[150],"heuristics,":[151],"show":[153],"up":[154],"90%":[156],"floating-point":[157],"unit":[158],"(FPU)":[159],"utilization":[160],"key":[162],"DNN":[163],"kernels.":[164],"By":[165],"breaking":[166],"model,":[170],"we":[171],"reopen":[172],"path":[174],"from":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
