{"id":"https://openalex.org/W4410492753","doi":"https://doi.org/10.1109/cicc63670.2025.10982878","title":"A 28nm 20.9-137.2 TOPS/W Output-Stationary SRAM Compute-in-Memory Macro Featuring Dynamic Look-ahead Zero Weight Skipping and Runtime Partial Sum Quantization","display_name":"A 28nm 20.9-137.2 TOPS/W Output-Stationary SRAM Compute-in-Memory Macro Featuring Dynamic Look-ahead Zero Weight Skipping and Runtime Partial Sum Quantization","publication_year":2025,"publication_date":"2025-04-13","ids":{"openalex":"https://openalex.org/W4410492753","doi":"https://doi.org/10.1109/cicc63670.2025.10982878"},"language":"en","primary_location":{"id":"doi:10.1109/cicc63670.2025.10982878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cicc63670.2025.10982878","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Custom Integrated Circuits Conference (CICC)","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Xiaofeng Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]},{"id":"https://openalex.org/I4405261073","display_name":"Cornell Tech","ror":"https://ror.org/04qscbg47","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295","https://openalex.org/I4405261073"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaofeng Hu","raw_affiliation_strings":["Cornell Tech,New York,NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell Tech,New York,NY","institution_ids":["https://openalex.org/I205783295","https://openalex.org/I4405261073"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133767555","display_name":"Han-Gyeol Mun","orcid":"https://orcid.org/0000-0002-8532-1385"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]},{"id":"https://openalex.org/I4405261073","display_name":"Cornell Tech","ror":"https://ror.org/04qscbg47","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295","https://openalex.org/I4405261073"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"HanGyeol Mun","raw_affiliation_strings":["Cornell Tech,New York,NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell Tech,New York,NY","institution_ids":["https://openalex.org/I205783295","https://openalex.org/I4405261073"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063343008","display_name":"Jian Meng","orcid":"https://orcid.org/0000-0002-7703-5020"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]},{"id":"https://openalex.org/I4405261073","display_name":"Cornell Tech","ror":"https://ror.org/04qscbg47","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295","https://openalex.org/I4405261073"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Meng","raw_affiliation_strings":["Cornell Tech,New York,NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell Tech,New York,NY","institution_ids":["https://openalex.org/I205783295","https://openalex.org/I4405261073"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086372580","display_name":"Yuan Liao","orcid":"https://orcid.org/0009-0007-5040-2381"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]},{"id":"https://openalex.org/I4405261073","display_name":"Cornell Tech","ror":"https://ror.org/04qscbg47","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295","https://openalex.org/I4405261073"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Liao","raw_affiliation_strings":["Cornell Tech,New York,NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell Tech,New York,NY","institution_ids":["https://openalex.org/I205783295","https://openalex.org/I4405261073"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050934336","display_name":"Amitesh Sridharan","orcid":"https://orcid.org/0009-0005-5620-9385"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amitesh Sridharan","raw_affiliation_strings":["Arizona State University,Tempe,AZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University,Tempe,AZ","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007690955","display_name":"Jae-sun Seo","orcid":"https://orcid.org/0000-0002-4551-7789"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]},{"id":"https://openalex.org/I4405261073","display_name":"Cornell Tech","ror":"https://ror.org/04qscbg47","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295","https://openalex.org/I4405261073"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jae-sun Seo","raw_affiliation_strings":["Cornell Tech,New York,NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell Tech,New York,NY","institution_ids":["https://openalex.org/I205783295","https://openalex.org/I4405261073"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11032","display_name":"VLSI and Analog Circuit Testing","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/T11032","display_name":"VLSI and Analog Circuit Testing","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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.994700014591217,"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/static-random-access-memory","display_name":"Static random-access memory","score":0.7226331233978271},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6516146659851074},{"id":"https://openalex.org/keywords/macro","display_name":"Macro","score":0.6291364431381226},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.579740583896637},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4955545663833618},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.486932635307312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47488564252853394},{"id":"https://openalex.org/keywords/tops","display_name":"TOPS","score":0.4224683344364166},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3481203615665436},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32744818925857544},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.21445932984352112}],"concepts":[{"id":"https://openalex.org/C68043766","wikidata":"https://www.wikidata.org/wiki/Q267416","display_name":"Static random-access memory","level":2,"score":0.7226331233978271},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6516146659851074},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.6291364431381226},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.579740583896637},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4955545663833618},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.486932635307312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47488564252853394},{"id":"https://openalex.org/C2777675136","wikidata":"https://www.wikidata.org/wiki/Q835642","display_name":"TOPS","level":3,"score":0.4224683344364166},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3481203615665436},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32744818925857544},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.21445932984352112},{"id":"https://openalex.org/C159737794","wikidata":"https://www.wikidata.org/wiki/Q124274","display_name":"Azimuth","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cicc63670.2025.10982878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cicc63670.2025.10982878","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Custom Integrated Circuits Conference (CICC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W3040024858","https://openalex.org/W3114479342","https://openalex.org/W4318256712","https://openalex.org/W4360605703","https://openalex.org/W4360606939","https://openalex.org/W4360607288","https://openalex.org/W4388692445","https://openalex.org/W4389352483","https://openalex.org/W4392739417","https://openalex.org/W4392745879","https://openalex.org/W4396918658","https://openalex.org/W4396940000","https://openalex.org/W4399880783","https://openalex.org/W4401880123","https://openalex.org/W6776767859","https://openalex.org/W6789946416","https://openalex.org/W6798034730","https://openalex.org/W6810281471","https://openalex.org/W6866762435"],"related_works":["https://openalex.org/W2811109569","https://openalex.org/W2385933648","https://openalex.org/W2381557761","https://openalex.org/W4231398535","https://openalex.org/W4245680303","https://openalex.org/W1996292569","https://openalex.org/W4210522299","https://openalex.org/W2043153436","https://openalex.org/W4251921734","https://openalex.org/W2113085768"],"abstract_inverted_index":{"SRAM-based":[0],"compute-in-memory":[1],"(CIM)":[2],"designs":[3,139],"have":[4,132],"shown":[5],"im-pressive":[6],"energy":[7],"efficiency":[8],"for":[9,143,159],"vector-matrix":[10],"multiplications":[11],"of":[12,61,253],"AI":[13,89],"work-loads":[14],"[1]\u2013[9].":[15],"As":[16],"many":[17],"prior":[18],"CIM":[19,43,63,94,161,175,198],"works":[20,113],"primarily":[21],"focus":[22],"on":[23],"macro-level":[24],"energy-efficiency,":[25,71],"there":[26],"are":[27,55,157],"often":[28],"big":[29],"gaps":[30],"between":[31],"macro":[32,177,199],"vs.":[33],"system":[34,70],"energy-efficiencies":[35],"in":[36,88,196],"real":[37],"applications":[38],"[10],":[39],"[11].":[40],"Conventional":[41],"SRAM":[42,58,173,190,211],"macros":[44,95],"naturally":[45],"adopt":[46],"the":[47,62,68,170,194,197,202,206,250],"weight-stationary":[48],"(WS)":[49],"dataflow,":[50],"and":[51,108,153,178,200,235,240],"computed":[52],"partial":[53,77],"sums":[54],"communicated":[56],"to":[57,74,105,192,210,248],"buffers":[59],"outside":[60],"macro.":[64],"This":[65],"largely":[66],"degrades":[67],"WS-CIM":[69],"especially":[72],"due":[73,104],"frequent":[75],"high-precision":[76,254],"sum":[78],"(Psum)":[79],"read/write":[80],"operations":[81],"(Fig.":[82],"1).":[83],"Further,":[84],"while":[85],"weight":[86,101,110,217,232],"sparsity":[87,120,233],"models":[90],"can":[91],"be":[92],"high,":[93],"with":[96,127,185,223],"WS":[97],"dataflow":[98],"make":[99],"zero":[100],"skipping":[102,141,218],"infeasible":[103],"shared":[106],"acti-vation":[107],"static":[109],"storage.":[111],"Previous":[112],"only":[114,123],"support":[115],"lim-ited":[116],"structured":[117],"(e.g.":[118],"block-wise)":[119],"[4],":[121],"or":[122],"store":[124,193],"non-zero":[125],"weights":[126],"indices":[128],"but":[129,147],"do":[130],"not":[131],"latency":[133,228],"benefits":[134],"[7].":[135],"Several":[136],"systolic":[137],"array":[138],"presented":[140],"techniques":[142],"sparse":[144],"ma-trices":[145],"[12]\u2013[14],":[146],"they":[148],"all":[149],"require":[150],"large":[151],"registers":[152],"complex":[154],"con-nections,":[155],"which":[156,225],"unsuitable":[158],"compact":[160],"macros.":[162],"To":[163],"ad-dress":[164],"these":[165],"challenges,":[166],"this":[167],"paper":[168],"presents":[169],"first":[171],"output-stationary":[172],"digital":[174],"(OS-CIM)":[176],"system,":[179],"featuring":[180],"(1)":[181],"an":[182],"OS-CIM":[183],"structure":[184],"custom":[186],"single-cycle":[187],"read-and-write":[188],"8T":[189],"cell":[191],"Psum":[195,208,244],"perform":[201],"accumulation":[203],"locally,":[204],"eliminating":[205],"expensive":[207],"access":[209],"buffers,":[212],"(2)":[213],"a":[214,242],"dynamic":[215],"look-ahead":[216],"(DLS)":[219],"scheme,":[220],"well":[221],"aligned":[222],"OS-CIM,":[224],"achieves":[226],"high":[227],"reduction":[229],"across":[230],"various":[231],"patterns":[234],"significantly":[236],"improves":[237],"workload":[238],"balance,":[239],"(3)":[241],"runtime":[243],"quantization":[245],"(RPQ)":[246],"method":[247],"mitigate":[249],"hardware":[251],"cost":[252],"accumulation.":[255]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}