{"id":"https://openalex.org/W4378715336","doi":"https://doi.org/10.1145/3603113","title":"MPU: Memory-centric SIMT Processor via In-DRAM Near-bank Computing","display_name":"MPU: Memory-centric SIMT Processor via In-DRAM Near-bank Computing","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4378715336","doi":"https://doi.org/10.1145/3603113"},"language":"en","primary_location":{"id":"doi:10.1145/3603113","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3603113","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3603113","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3603113","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047767267","display_name":"Xinfeng Xie","orcid":"https://orcid.org/0000-0001-7285-6682"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xinfeng Xie","raw_affiliation_strings":["University of California, Santa Barbara, USA","of , , of , , ,","DIMIN NIU, HONGZHONG ZHENG, and YUAN XIE, Alibaba Group Inc., USA"],"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, USA","institution_ids":["https://openalex.org/I154570441"]},{"raw_affiliation_string":"of , , of , , ,","institution_ids":[]},{"raw_affiliation_string":"DIMIN NIU, HONGZHONG ZHENG, and YUAN XIE, Alibaba Group Inc., USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101934720","display_name":"Peng Gu","orcid":"https://orcid.org/0000-0002-7206-2396"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peng Gu","raw_affiliation_strings":["University of California, Santa Barbara, USA","DIMIN NIU, HONGZHONG ZHENG, and YUAN XIE, Alibaba Group Inc., USA","of , , of , , ,"],"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, USA","institution_ids":["https://openalex.org/I154570441"]},{"raw_affiliation_string":"DIMIN NIU, HONGZHONG ZHENG, and YUAN XIE, Alibaba Group Inc., USA","institution_ids":[]},{"raw_affiliation_string":"of , , of , , ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048052285","display_name":"Yufei Ding","orcid":"https://orcid.org/0000-0002-8716-5793"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yufei Ding","raw_affiliation_strings":["University of California, Santa Barbara, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068606980","display_name":"Dimin Niu","orcid":"https://orcid.org/0000-0001-8440-3875"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimin Niu","raw_affiliation_strings":["Alibaba Group Inc., USA"],"affiliations":[{"raw_affiliation_string":"Alibaba Group Inc., USA","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046896624","display_name":"Hongzhong Zheng","orcid":"https://orcid.org/0000-0001-7696-9799"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongzhong Zheng","raw_affiliation_strings":["Alibaba Group Inc., USA"],"affiliations":[{"raw_affiliation_string":"Alibaba Group Inc., USA","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100385325","display_name":"Yuan Xie","orcid":"https://orcid.org/0000-0002-0771-4992"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Xie","raw_affiliation_strings":["Alibaba Group Inc., USA"],"affiliations":[{"raw_affiliation_string":"Alibaba Group Inc., USA","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5047767267"],"corresponding_institution_ids":["https://openalex.org/I154570441"],"apc_list":null,"apc_paid":null,"fwci":0.6263,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60813507,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"20","issue":"3","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9998000264167786,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9991999864578247,"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/computer-science","display_name":"Computer science","score":0.869488000869751},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6293259859085083},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6184645295143127},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6054655909538269},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5392455458641052},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5069620609283447},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4984924793243408},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.4933883249759674},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4909113049507141},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.44143080711364746},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4337999224662781},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.31603890657424927},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.25789010524749756},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09761098027229309}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.869488000869751},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6293259859085083},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6184645295143127},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6054655909538269},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5392455458641052},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5069620609283447},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4984924793243408},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.4933883249759674},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4909113049507141},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.44143080711364746},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4337999224662781},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.31603890657424927},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.25789010524749756},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09761098027229309}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3603113","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3603113","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3603113","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-153873","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-153873","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Article"}],"best_oa_location":{"id":"doi:10.1145/3603113","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3603113","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3603113","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.7900000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4378715336.pdf","grobid_xml":"https://content.openalex.org/works/W4378715336.grobid-xml"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W1975237352","https://openalex.org/W1979527452","https://openalex.org/W1982825626","https://openalex.org/W2034861439","https://openalex.org/W2048466306","https://openalex.org/W2080592089","https://openalex.org/W2092324191","https://openalex.org/W2094332102","https://openalex.org/W2112181056","https://openalex.org/W2112980698","https://openalex.org/W2116784058","https://openalex.org/W2118703320","https://openalex.org/W2141546789","https://openalex.org/W2162639668","https://openalex.org/W2169880332","https://openalex.org/W2291192530","https://openalex.org/W2414912620","https://openalex.org/W2508602506","https://openalex.org/W2513721464","https://openalex.org/W2517869808","https://openalex.org/W2518281301","https://openalex.org/W2520782513","https://openalex.org/W2543989436","https://openalex.org/W2575503711","https://openalex.org/W2605347906","https://openalex.org/W2613989746","https://openalex.org/W2761132374","https://openalex.org/W2764172931","https://openalex.org/W2767588966","https://openalex.org/W2802367674","https://openalex.org/W2887018074","https://openalex.org/W2896090304","https://openalex.org/W2897709121","https://openalex.org/W2904929935","https://openalex.org/W2912888224","https://openalex.org/W2913245236","https://openalex.org/W2914262686","https://openalex.org/W2939504873","https://openalex.org/W2950138172","https://openalex.org/W2967163762","https://openalex.org/W2979823675","https://openalex.org/W2980235049","https://openalex.org/W2985229340","https://openalex.org/W3006451002","https://openalex.org/W3039617420","https://openalex.org/W3042598257","https://openalex.org/W3098742859","https://openalex.org/W3099365437","https://openalex.org/W3158275024","https://openalex.org/W3189166979","https://openalex.org/W4206700688","https://openalex.org/W4206802316","https://openalex.org/W4244457258","https://openalex.org/W4244607449","https://openalex.org/W4245268430","https://openalex.org/W4247176905","https://openalex.org/W4251637954","https://openalex.org/W4255681033"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2013643406","https://openalex.org/W2891987081","https://openalex.org/W4376647684","https://openalex.org/W4221139464"],"abstract_inverted_index":{"With":[0],"the":[1,10,18,42,77,97,122,137,178],"growing":[2],"number":[3],"of":[4,124,185,204],"data-intensive":[5,206],"workloads,":[6],"GPU,":[7],"which":[8],"is":[9,15],"state-of-the-art":[11],"single-instruction-multiple-thread":[12],"(SIMT)":[13],"processor,":[14],"hindered":[16],"by":[17,37],"memory":[19,145],"bandwidth":[20,36],"wall.":[21],"To":[22,87,166],"alleviate":[23],"this":[24],"bottleneck,":[25],"previously":[26],"proposed":[27],"3D-stacking":[28,103],"near-bank":[29,104,128,143],"computing":[30,105],"accelerators":[31,47],"benefit":[32],"from":[33],"abundant":[34],"bank-internal":[35],"bringing":[38],"computations":[39],"closer":[40],"to":[41,108,127,162],"DRAM":[43],"banks.":[44],"However,":[45],"these":[46,89],"are":[48],"specialized":[49],"for":[50,70,76,136,160,177],"certain":[51],"application":[52],"domains":[53],"with":[54,113,121,195],"simple":[55],"architecture":[56],"data":[57,72,111],"paths":[58,112],"and":[59,81,147,190],"customized":[60],"software":[61,83],"mapping":[62],"schemes.":[63],"For":[64],"general-purpose":[65],"scenarios,":[66],"lightweight":[67],"hardware":[68],"designs":[69],"diverse":[71,110],"paths,":[73],"architectural":[74,134],"supports":[75,135],"SIMT":[78,99,138],"programming":[79,139],"model,":[80,140],"end-to-end":[82,157],"optimizations":[84],"remain":[85],"challenging.":[86],"address":[88],"issues,":[90],"we":[91,131,154,172],"propose":[92],"Memory-centric":[93],"Processing":[94],"Unit":[95],"(MPU),":[96],"first":[98],"processor":[100],"based":[101],"on":[102,201],"architecture.":[106],"First,":[107],"realize":[109],"small":[114],"overheads,":[115],"MPU":[116,161,186],"adopts":[117],"a":[118,142,148,174,202],"hybrid":[119,170],"pipeline":[120],"capability":[123],"offloading":[125,180],"instructions":[126],"compute-logic.":[129],"Second,":[130],"explore":[132],"two":[133],"including":[141],"shared":[144],"design":[146],"multiple":[149],"activated":[150],"row-buffers":[151],"enhancement.":[152],"Third,":[153],"present":[155],"an":[156,196],"compilation":[158],"flow":[159],"support":[163],"CUDA":[164],"programs.":[165],"fully":[167],"utilize":[168],"MPU\u2019s":[169],"pipeline,":[171],"develop":[173],"backend":[175],"optimization":[176],"instruction":[179],"decision.":[181],"The":[182],"evaluation":[183],"results":[184],"demonstrate":[187],"3.46\u00d7":[188],"speedup":[189],"2.57\u00d7":[191],"energy":[192],"reduction":[193],"compared":[194],"NVIDIA":[197],"Tesla":[198],"V100":[199],"GPU":[200],"set":[203],"representative":[205],"workloads.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}
