{"id":"https://openalex.org/W3033848804","doi":"https://doi.org/10.1109/hpec43674.2020.9286183","title":"Vyasa: A High-Performance Vectorizing Compiler for Tensor Convolutions on the Xilinx AI Engine","display_name":"Vyasa: A High-Performance Vectorizing Compiler for Tensor Convolutions on the Xilinx AI Engine","publication_year":2020,"publication_date":"2020-09-22","ids":{"openalex":"https://openalex.org/W3033848804","doi":"https://doi.org/10.1109/hpec43674.2020.9286183","mag":"3033848804"},"language":"en","primary_location":{"id":"doi:10.1109/hpec43674.2020.9286183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.01331","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000520819","display_name":"Prasanth Chatarasi","orcid":"https://orcid.org/0000-0002-0974-4001"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Prasanth Chatarasi","raw_affiliation_strings":["Georgia Institute of Technology","#N#\u2021#N#Georgia Institute of Technology#N#"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014827775","display_name":"Stephen Neuendorffer","orcid":"https://orcid.org/0000-0003-2956-8428"},"institutions":[{"id":"https://openalex.org/I32923980","display_name":"Xilinx (United States)","ror":"https://ror.org/01rb7bk56","country_code":"US","type":"company","lineage":["https://openalex.org/I32923980"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen Neuendorffer","raw_affiliation_strings":["Xilinx Research Labs","xilinx"],"affiliations":[{"raw_affiliation_string":"Xilinx Research Labs","institution_ids":["https://openalex.org/I32923980"]},{"raw_affiliation_string":"xilinx","institution_ids":["https://openalex.org/I32923980"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085413241","display_name":"Samuel Bayliss","orcid":null},"institutions":[{"id":"https://openalex.org/I32923980","display_name":"Xilinx (United States)","ror":"https://ror.org/01rb7bk56","country_code":"US","type":"company","lineage":["https://openalex.org/I32923980"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Bayliss","raw_affiliation_strings":["Xilinx Research Labs","xilinx"],"affiliations":[{"raw_affiliation_string":"Xilinx Research Labs","institution_ids":["https://openalex.org/I32923980"]},{"raw_affiliation_string":"xilinx","institution_ids":["https://openalex.org/I32923980"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011464762","display_name":"Kees Vissers","orcid":"https://orcid.org/0000-0002-6249-315X"},"institutions":[{"id":"https://openalex.org/I32923980","display_name":"Xilinx (United States)","ror":"https://ror.org/01rb7bk56","country_code":"US","type":"company","lineage":["https://openalex.org/I32923980"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kees Vissers","raw_affiliation_strings":["Xilinx Research Labs","xilinx"],"affiliations":[{"raw_affiliation_string":"Xilinx Research Labs","institution_ids":["https://openalex.org/I32923980"]},{"raw_affiliation_string":"xilinx","institution_ids":["https://openalex.org/I32923980"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043513001","display_name":"Vivek Sarkar","orcid":"https://orcid.org/0000-0002-3433-8830"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vivek Sarkar","raw_affiliation_strings":["Georgia Institute of Technology","#N#\u2021#N#Georgia Institute of Technology#N#"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5000520819"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0695825,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9947999715805054,"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"}},{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8296427726745605},{"id":"https://openalex.org/keywords/intrinsics","display_name":"Intrinsics","score":0.7854374647140503},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.765198826789856},{"id":"https://openalex.org/keywords/operand","display_name":"Operand","score":0.764501690864563},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.6974925994873047},{"id":"https://openalex.org/keywords/digital-subscriber-line","display_name":"Digital subscriber line","score":0.668274998664856},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6096880435943604},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5548770427703857},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.46870893239974976},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.43777161836624146},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.41917678713798523},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.38049614429473877},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2863064408302307},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1912500560283661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8296427726745605},{"id":"https://openalex.org/C2908650547","wikidata":"https://www.wikidata.org/wiki/Q20999234","display_name":"Intrinsics","level":2,"score":0.7854374647140503},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.765198826789856},{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.764501690864563},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.6974925994873047},{"id":"https://openalex.org/C201374245","wikidata":"https://www.wikidata.org/wiki/Q104534","display_name":"Digital subscriber line","level":2,"score":0.668274998664856},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6096880435943604},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5548770427703857},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.46870893239974976},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.43777161836624146},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.41917678713798523},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.38049614429473877},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2863064408302307},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1912500560283661},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/hpec43674.2020.9286183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2006.01331","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.01331","pdf_url":"https://arxiv.org/pdf/2006.01331","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"mag:3033848804","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2006.01331","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2006.01331","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2006.01331","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2006.01331","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.01331","pdf_url":"https://arxiv.org/pdf/2006.01331","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3033848804.pdf","grobid_xml":"https://content.openalex.org/works/W3033848804.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1595548352","https://openalex.org/W1905882502","https://openalex.org/W1964031104","https://openalex.org/W1982008951","https://openalex.org/W1999594683","https://openalex.org/W2018641575","https://openalex.org/W2022508996","https://openalex.org/W2034971312","https://openalex.org/W2048275941","https://openalex.org/W2055312318","https://openalex.org/W2068384324","https://openalex.org/W2084917734","https://openalex.org/W2094756095","https://openalex.org/W2102182691","https://openalex.org/W2113325037","https://openalex.org/W2117539524","https://openalex.org/W2125840772","https://openalex.org/W2146269912","https://openalex.org/W2157758640","https://openalex.org/W2163605009","https://openalex.org/W2328375319","https://openalex.org/W2471164860","https://openalex.org/W2517689844","https://openalex.org/W2522774385","https://openalex.org/W2544002786","https://openalex.org/W2582073145","https://openalex.org/W2584311934","https://openalex.org/W2606722458","https://openalex.org/W2613264175","https://openalex.org/W2775727048","https://openalex.org/W2784561332","https://openalex.org/W2804032941","https://openalex.org/W2806891462","https://openalex.org/W2896983500","https://openalex.org/W2905135312","https://openalex.org/W2918037051","https://openalex.org/W2928999112","https://openalex.org/W2941583287","https://openalex.org/W2950001020","https://openalex.org/W2961619211","https://openalex.org/W2962835968","https://openalex.org/W2979365412","https://openalex.org/W3006145057","https://openalex.org/W4232919122","https://openalex.org/W4247949726","https://openalex.org/W4251637954","https://openalex.org/W6637151318","https://openalex.org/W6637373629","https://openalex.org/W6641237240","https://openalex.org/W6684191040","https://openalex.org/W6751349269","https://openalex.org/W6773534042","https://openalex.org/W6856891780"],"related_works":["https://openalex.org/W3117440043","https://openalex.org/W2147423491","https://openalex.org/W2569816949","https://openalex.org/W2750782719","https://openalex.org/W2019746620","https://openalex.org/W2552803129","https://openalex.org/W2116796716","https://openalex.org/W2053968119","https://openalex.org/W1546698345","https://openalex.org/W2019488907","https://openalex.org/W2014855281","https://openalex.org/W2046673373","https://openalex.org/W2908736411","https://openalex.org/W1827234896","https://openalex.org/W2099063269","https://openalex.org/W2894643122","https://openalex.org/W619811882","https://openalex.org/W2041702636","https://openalex.org/W1486016446","https://openalex.org/W96757589"],"abstract_inverted_index":{"Xilinx's":[0],"AI":[1,30,87],"Engine":[2,31],"is":[3],"a":[4,34,52,71],"recent":[5],"industry":[6],"example":[7],"of":[8,54,61,100,115],"energy-efficient":[9],"vector":[10,38],"processing":[11],"that":[12,75],"includes":[13],"novel":[14],"support":[15],"for":[16,37,85,105],"2D":[17],"SIMD":[18],"datapaths":[19],"and":[20,96,102,107,113],"shuffle":[21],"interconnection":[22],"network.":[23],"The":[24],"current":[25],"approach":[26],"to":[27,50,81],"programming":[28,73],"the":[29,48,62,77,86,116],"relies":[32],"on":[33,58,92],"C/C++":[35],"API":[36],"intrinsics.":[39],"While":[40],"an":[41],"advance":[42],"over":[43],"assembly-level":[44],"programming,":[45],"it":[46],"requires":[47],"programmer":[49],"specify":[51],"number":[53],"low-level":[55],"operations":[56],"based":[57],"detailed":[59],"knowledge":[60],"hardware.":[63],"To":[64],"address":[65],"these":[66],"challenges,":[67],"we":[68],"introduce":[69],"Vyasa,":[70],"new":[72],"system":[74],"extends":[76],"Halide":[78],"DSL":[79],"compiler":[80],"automatically":[82],"generate":[83],"code":[84],"Engine.":[88],"We":[89],"evaluated":[90],"Vyasa":[91],"36":[93],"CONV2D":[94],"workloads,":[95],"achieved":[97],"geometric":[98],"means":[99],"7.6":[101],"24.2":[103],"MACs/cycle":[104],"32-bit":[106],"16-bit":[108],"operands":[109],"(which":[110],"represent":[111],"95.9%":[112],"75.6%":[114],"peak":[117],"performance":[118],"respectively).":[119]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}