{"id":"https://openalex.org/W4402454163","doi":"https://doi.org/10.1145/3659997.3660032","title":"Mapping Parallel Matrix Multiplication in GotoBLAS2 to the AMD Versal ACAP for Deep Learning","display_name":"Mapping Parallel Matrix Multiplication in GotoBLAS2 to the AMD Versal ACAP for Deep Learning","publication_year":2024,"publication_date":"2024-06-03","ids":{"openalex":"https://openalex.org/W4402454163","doi":"https://doi.org/10.1145/3659997.3660032"},"language":"en","primary_location":{"id":"doi:10.1145/3659997.3660032","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3659997.3660032","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 4th Workshop on Performance and Energy Efficiency in Concurrent and Distributed Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3659997.3660032","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100324371","display_name":"Jie Lei","orcid":"https://orcid.org/0000-0002-9998-9503"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jie Lei","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain"],"raw_orcid":"https://orcid.org/0000-0002-9998-9503","affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012806004","display_name":"Enrique S. Quintana\u2013Ort\u0301\u0131","orcid":"https://orcid.org/0000-0002-5454-165X"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Enrique S. Quintana-Ort\u00ed","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain"],"raw_orcid":"https://orcid.org/0000-0002-5454-165X","affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60053951"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9958999752998352,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9902999997138977,"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/multiplication","display_name":"Multiplication (music)","score":0.7085561752319336},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6396195292472839},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5080459117889404},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41579437255859375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37287065386772156},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.34806302189826965},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21702635288238525},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07790827751159668},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.052242130041122437}],"concepts":[{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.7085561752319336},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6396195292472839},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5080459117889404},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41579437255859375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37287065386772156},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.34806302189826965},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21702635288238525},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07790827751159668},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.052242130041122437},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3659997.3660032","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3659997.3660032","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 4th Workshop on Performance and Energy Efficiency in Concurrent and Distributed Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3659997.3660032","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3659997.3660032","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 4th Workshop on Performance and Energy Efficiency in Concurrent and Distributed Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2073061372","https://openalex.org/W2168732909","https://openalex.org/W2516525699","https://openalex.org/W2981712449","https://openalex.org/W3093682266","https://openalex.org/W4379031105","https://openalex.org/W4386826409"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W3009238340","https://openalex.org/W4321369474","https://openalex.org/W4360585206","https://openalex.org/W3099313426","https://openalex.org/W4285208911","https://openalex.org/W4287593139","https://openalex.org/W3082895349","https://openalex.org/W4213079790"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,40,48,56,60,70,74,78,91,115,130,135],"design":[4,106],"of":[5,43,59,73,134],"parallel":[6,105,132],"general":[7],"matrix":[8],"multiplication":[9],"(gemm)":[10],"for":[11,85,94,107],"a":[12,21,104],"Versal":[13,49,61],"Adaptive":[14],"Compute":[15],"Accelerated":[16],"Platform":[17],"(ACAP)":[18],"equipped":[19],"with":[20,122],"VC1902":[22],"system-on-chip":[23],"and":[24,100],"multiple":[25,111],"Artificial":[26],"Intelligence":[27],"Engines":[28],"(AIEs).":[29],"Our":[30],"efforts":[31],"aim":[32],"to":[33,47,89,124],"port":[34],"standard":[35],"optimization":[36],"techniques":[37],"applied":[38],"in":[39,77,97],"high-performance":[41],"realization":[42],"gemm":[44,108],"on":[45],"CPUs":[46],"ACAP.":[50],"In":[51],"particular,":[52],"1)":[53],"we":[54,67,102],"address":[55,90],"flexible":[57],"exploitation":[58],"ACAP's":[62],"multilevel":[63],"memory":[64],"hierarchy;":[65],"2)":[66],"delve":[68],"into":[69],"efficient":[71],"use":[72],"vector":[75],"units":[76],"AIE":[79,112],"tiles,":[80,113],"proposing":[81],"an":[82],"architecture-specific":[83],"micro-kernel":[84],"mixed":[86],"precision":[87],"arithmetic":[88],"strong":[92],"demand":[93],"adaptive-precision":[95],"inference":[96],"deep":[98],"learning;":[99],"3)":[101],"introduce":[103],"that":[109,128],"spans":[110],"enhancing":[114],"computational":[116],"throughput.":[117],"We":[118],"conduct":[119],"experimental":[120],"profiling,":[121],"up":[123],"32":[125],"AI":[126],"Engines,":[127],"demonstrates":[129],"high":[131],"scalability":[133],"solution.":[136]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}