{"id":"https://openalex.org/W4410583032","doi":"https://doi.org/10.23919/date64628.2025.10993090","title":"RGHT-Q: Reconfigurable GEMM Unit for Heterogeneous-Homogeneous Tensor Quantization","display_name":"RGHT-Q: Reconfigurable GEMM Unit for Heterogeneous-Homogeneous Tensor Quantization","publication_year":2025,"publication_date":"2025-03-31","ids":{"openalex":"https://openalex.org/W4410583032","doi":"https://doi.org/10.23919/date64628.2025.10993090"},"language":"en","primary_location":{"id":"doi:10.23919/date64628.2025.10993090","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date64628.2025.10993090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Design, Automation &amp;amp; Test in Europe Conference (DATE)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100363400","display_name":"Seungho Lee","orcid":"https://orcid.org/0000-0002-4574-5511"},"institutions":[{"id":"https://openalex.org/I4210147194","display_name":"Convergence","ror":"https://ror.org/03kcznq08","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210147194"]},{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR","US"],"is_corresponding":true,"raw_author_name":"Seungho Lee","raw_affiliation_strings":["Sungkyunkwan University,Dept. of Semiconductor Convergence Engineering"],"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University,Dept. of Semiconductor Convergence Engineering","institution_ids":["https://openalex.org/I848706","https://openalex.org/I4210147194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119059827","display_name":"Dongjin Nam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210147194","display_name":"Convergence","ror":"https://ror.org/03kcznq08","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210147194"]},{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Donghyun Nam","raw_affiliation_strings":["Sungkyunkwan University,Dept. of Semiconductor Convergence Engineering"],"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University,Dept. of Semiconductor Convergence Engineering","institution_ids":["https://openalex.org/I848706","https://openalex.org/I4210147194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089174485","display_name":"Jeongwoo Park","orcid":"https://orcid.org/0000-0002-9603-9588"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeongwoo Park","raw_affiliation_strings":["Sungkyunkwan University,Dept. of Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University,Dept. of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I848706"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100363400"],"corresponding_institution_ids":["https://openalex.org/I4210147194","https://openalex.org/I848706"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05680063,"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":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13650","display_name":"Computational Physics and Python Applications","score":0.9861999750137329,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T13650","display_name":"Computational Physics and Python Applications","score":0.9861999750137329,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.954200029373169,"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"}},{"id":"https://openalex.org/T11808","display_name":"Superconducting Materials and Applications","score":0.9283000230789185,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/homogeneous","display_name":"Homogeneous","score":0.6397687792778015},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5781951546669006},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5310930013656616},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5027859210968018},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.4706631898880005},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.31167107820510864},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2716826796531677},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.20852655172348022},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.0731198787689209}],"concepts":[{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.6397687792778015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5781951546669006},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5310930013656616},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5027859210968018},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.4706631898880005},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31167107820510864},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2716826796531677},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.20852655172348022},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0731198787689209},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date64628.2025.10993090","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date64628.2025.10993090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Design, Automation &amp;amp; Test in Europe Conference (DATE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2971946864","https://openalex.org/W3113606433","https://openalex.org/W3217237164"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2072657027","https://openalex.org/W2962838298","https://openalex.org/W2600246793"],"abstract_inverted_index":{"The":[0,53],"high":[1],"computational":[2],"demands":[3],"of":[4,14],"large":[5],"language":[6],"models":[7],"(LLMs)":[8],"are":[9],"limited":[10],"by":[11],"the":[12],"lack":[13],"GPU":[15],"hardware":[16],"support":[17],"for":[18,46],"heterogeneous":[19,48],"quantization,":[20],"which":[21,39],"mixes":[22],"integers":[23],"and":[24,49,63,79],"floating":[25],"points.":[26],"To":[27],"address":[28],"this":[29],"limitation,":[30],"we":[31,69],"propose":[32],"an":[33],"LLM":[34],"processing":[35],"element":[36],"(PE),":[37],"RGHT-Q,":[38],"features":[40],"reconfigurable":[41],"general-matrix":[42],"multiplication":[43],"(GEMM)":[44],"operations":[45],"both":[47],"homogeneous":[50],"tensor":[51],"quantization.":[52],"RGHT-Q":[54],"introduces":[55],"a":[56,67],"novel":[57],"design":[58],"that":[59],"leverages":[60],"butterfly":[61],"routing":[62],"multi-precision":[64],"multipliers.":[65],"As":[66],"result,":[68],"achieve":[70],"significant":[71],"performance":[72],"improvements,":[73],"offering":[74],"3.14\u00d7":[75],"higher":[76],"energy":[77],"efficiency,":[78],"1.56\u00d7":[80],"better":[81],"area":[82],"efficiency":[83],"compared":[84],"to":[85],"prior":[86],"designs.":[87]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
