{"id":"https://openalex.org/W4409248620","doi":"https://doi.org/10.1109/hpca61900.2025.00101","title":"LEGO: Spatial Accelerator Generation and Optimization for Tensor Applications","display_name":"LEGO: Spatial Accelerator Generation and Optimization for Tensor Applications","publication_year":2025,"publication_date":"2025-03-01","ids":{"openalex":"https://openalex.org/W4409248620","doi":"https://doi.org/10.1109/hpca61900.2025.00101"},"language":"en","primary_location":{"id":"doi:10.1109/hpca61900.2025.00101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca61900.2025.00101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on High Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.12053","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037235064","display_name":"Yujun Lin","orcid":"https://orcid.org/0000-0001-8313-4642"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yujun Lin","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065492534","display_name":"Zhekai Zhang","orcid":"https://orcid.org/0000-0002-9777-3792"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhekai Zhang","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070926896","display_name":"Song Han","orcid":"https://orcid.org/0000-0002-4186-7618"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Song Han","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037235064"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07747288,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1335","last_page":"1347"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9916999936103821,"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":0.9916999936103821,"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":0.9812999963760376,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9366999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5992998480796814},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.4757644534111023},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11879560351371765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5992998480796814},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.4757644534111023},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11879560351371765},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hpca61900.2025.00101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca61900.2025.00101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on High Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.12053","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.12053","pdf_url":"https://arxiv.org/pdf/2509.12053","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.12053","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.12053","pdf_url":"https://arxiv.org/pdf/2509.12053","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":0.5799999833106995,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1974338211","https://openalex.org/W1988615825","https://openalex.org/W2067523571","https://openalex.org/W2096949479","https://openalex.org/W2194775991","https://openalex.org/W2289252105","https://openalex.org/W2606722458","https://openalex.org/W2618530766","https://openalex.org/W2899644485","https://openalex.org/W2936278485","https://openalex.org/W2940862705","https://openalex.org/W2963125977","https://openalex.org/W2963163009","https://openalex.org/W2963367920","https://openalex.org/W2963956318","https://openalex.org/W2980200167","https://openalex.org/W2997929983","https://openalex.org/W3017024317","https://openalex.org/W3042501387","https://openalex.org/W3122286897","https://openalex.org/W3130920634","https://openalex.org/W3159727696","https://openalex.org/W3190092209","https://openalex.org/W3206429150","https://openalex.org/W3206453033","https://openalex.org/W3212403328","https://openalex.org/W3212867926","https://openalex.org/W3213229701","https://openalex.org/W3213528054","https://openalex.org/W4244024631","https://openalex.org/W4293023583","https://openalex.org/W4312933868","https://openalex.org/W4385245566","https://openalex.org/W6719768283","https://openalex.org/W6755207826","https://openalex.org/W6779823529","https://openalex.org/W6785439968","https://openalex.org/W6793164127","https://openalex.org/W6796931752","https://openalex.org/W6850625674"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","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"],"abstract_inverted_index":{"Modern":[0],"tensor":[1,64],"applications,":[2],"especially":[3],"foundation":[4,174],"models":[5,175],"and":[6,16,35,66,72,99,125,137,157,166],"generative":[7,177],"AI":[8,178],"applications":[9,65],"require":[10],"multiple":[11],"input":[12],"modalities":[13],"(both":[14],"vision":[15],"language),":[17],"which":[18,62],"increases":[19],"the":[20,30,51,59,83,96,115,139],"demand":[21],"for":[22,171],"flexible":[23],"accelerator":[24],"architecture.":[25],"Existing":[26],"frameworks":[27],"suffer":[28],"from":[29],"trade-off":[31],"between":[32,92],"design":[33,71,80],"flexibility":[34],"productivity":[36],"of":[37,129,141],"RTL":[38,75,79],"generation:":[39],"either":[40],"limited":[41],"to":[42,121,132,162],"very":[43],"few":[44],"hand-written":[45],"templates":[46],"or":[47],"cannot":[48],"automatically":[49,67],"generate":[50,168],"RTL.":[52],"To":[53],"address":[54],"this":[55],"challenge,":[56],"we":[57],"propose":[58],"LEGO":[60,87,110,152],"framework,":[61],"targets":[63],"generates":[68],"spatial":[69,102,146],"architecture":[70,85,170],"outputs":[73],"synthesizable":[74],"code":[76],"without":[77],"handwritten":[78],"templates.":[81],"Leveraging":[82],"affine-transformation-based":[84],"representation,":[86],"front":[88],"end":[89,112],"finds":[90],"interconnections":[91],"function":[93],"units,":[94],"synthesizes":[95],"memory":[97],"system,":[98],"fuses":[100],"different":[101],"dataflow":[103],"designs":[104],"based":[105],"on":[106],"data":[107],"reuse":[108],"analysis.":[109],"back":[111],"then":[113],"translates":[114],"hardware":[116],"in":[117,176],"a":[118,127],"primitive-level":[119],"graph":[120],"perform":[122],"lower-level":[123],"optimizations,":[124],"applies":[126],"set":[128],"linear-programming":[130],"algorithms":[131],"optimally":[133],"insert":[134],"pipeline":[135],"registers":[136],"reduce":[138],"overhead":[140],"unused":[142],"logic":[143],"when":[144],"switching":[145],"dataflows.":[147],"Our":[148],"evaluation":[149],"demonstrates":[150],"that":[151],"can":[153,167],"achieve":[154],"3.2x":[155],"speedup":[156],"2.4x":[158],"energy":[159],"efficiency":[160],"compared":[161],"previous":[163],"work":[164],"Gemmini,":[165],"one":[169],"diverse":[172],"modern":[173],"applications.":[179]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}