{"id":"https://openalex.org/W4415285479","doi":"https://doi.org/10.1145/3725843.3756132","title":"Characterizing and Optimizing Realistic Workloads on a Commercial Compute-in-SRAM Device","display_name":"Characterizing and Optimizing Realistic Workloads on a Commercial Compute-in-SRAM Device","publication_year":2025,"publication_date":"2025-10-17","ids":{"openalex":"https://openalex.org/W4415285479","doi":"https://doi.org/10.1145/3725843.3756132"},"language":null,"primary_location":{"id":"doi:10.1145/3725843.3756132","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725843.3756132","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725843.3756132","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 58th IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3725843.3756132","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059293268","display_name":"Niansong Zhang","orcid":"https://orcid.org/0000-0002-2850-0176"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Niansong Zhang","raw_affiliation_strings":["Cornell University, Ithaca, New York, USA"],"raw_orcid":"https://orcid.org/0000-0002-2850-0176","affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, New York, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069945890","display_name":"Wenbo Zhu","orcid":"https://orcid.org/0000-0002-9583-7502"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenbo Zhu","raw_affiliation_strings":["University of Southern California, Los Angeles, California, USA"],"raw_orcid":"https://orcid.org/0000-0002-9583-7502","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065082293","display_name":"Courtney Golden","orcid":"https://orcid.org/0009-0009-8874-7873"},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Courtney Golden","raw_affiliation_strings":["MIT, Cambridge, Massachusetts, USA"],"raw_orcid":"https://orcid.org/0009-0009-8874-7873","affiliations":[{"raw_affiliation_string":"MIT, Cambridge, Massachusetts, USA","institution_ids":["https://openalex.org/I4210110987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093469852","display_name":"Dan Ilan","orcid":"https://orcid.org/0000-0002-8768-2985"},"institutions":[{"id":"https://openalex.org/I4210111150","display_name":"GNA Research (Israel)","ror":"https://ror.org/01npr5x48","country_code":"IL","type":"company","lineage":["https://openalex.org/I4210111150"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Dan Ilan","raw_affiliation_strings":["GSI Inc., Tel Aviv, Israel"],"raw_orcid":"https://orcid.org/0000-0002-8768-2985","affiliations":[{"raw_affiliation_string":"GSI Inc., Tel Aviv, Israel","institution_ids":["https://openalex.org/I4210111150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008694159","display_name":"Hongzheng Chen","orcid":"https://orcid.org/0000-0002-6617-0075"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongzheng Chen","raw_affiliation_strings":["Cornell University, Ithaca, New York, USA"],"raw_orcid":"https://orcid.org/0000-0002-6617-0075","affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, New York, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091660287","display_name":"Christopher Batten","orcid":"https://orcid.org/0000-0002-2835-667X"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Batten","raw_affiliation_strings":["Cornell University, Ithaca, New York, USA"],"raw_orcid":"https://orcid.org/0000-0002-2835-667X","affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, New York, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037210004","display_name":"Zhiru Zhang","orcid":"https://orcid.org/0000-0002-0778-0308"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiru Zhang","raw_affiliation_strings":["Cornell University, Ithaca, New York, USA"],"raw_orcid":"https://orcid.org/0000-0002-0778-0308","affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, New York, USA","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5151,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.82591415,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1011","last_page":"1025"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11032","display_name":"VLSI and Analog Circuit Testing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11522","display_name":"VLSI and FPGA Design Techniques","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"}},{"id":"https://openalex.org/T10363","display_name":"Low-power high-performance VLSI design","score":0.9988999962806702,"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/key","display_name":"Key (lock)","score":0.2612000107765198},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.25679999589920044},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2506999969482422},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2500999867916107},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.24889999628067017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6036999821662903},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2973000109195709},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2506999969482422},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2500999867916107},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.24889999628067017},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.24009999632835388},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.23980000615119934},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2386000007390976}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3725843.3756132","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725843.3756132","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725843.3756132","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 58th IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3725843.3756132","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725843.3756132","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725843.3756132","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 58th IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G539115378","display_name":"Graduate Research Fellowship Program (GRFP)","funder_award_id":"2141064","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7564846446","display_name":"Collaborative Research: PPoSS: LARGE: Panorama: Integrated Rack-Scale Acceleration for Computational Pangenomics","funder_award_id":"2118709","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415285479.pdf","grobid_xml":"https://content.openalex.org/works/W4415285479.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W1521947899","https://openalex.org/W1529285927","https://openalex.org/W1969349120","https://openalex.org/W1981943579","https://openalex.org/W1990433043","https://openalex.org/W2104644701","https://openalex.org/W2112980698","https://openalex.org/W2135601680","https://openalex.org/W2331783522","https://openalex.org/W2537294823","https://openalex.org/W2591601611","https://openalex.org/W2613569094","https://openalex.org/W2775637085","https://openalex.org/W2792893539","https://openalex.org/W2894696827","https://openalex.org/W2912924812","https://openalex.org/W2949989598","https://openalex.org/W2964176059","https://openalex.org/W3026786299","https://openalex.org/W3043089744","https://openalex.org/W3090416062","https://openalex.org/W3104353813","https://openalex.org/W3108085245","https://openalex.org/W3130641740","https://openalex.org/W3159441626","https://openalex.org/W3163974534","https://openalex.org/W3185889905","https://openalex.org/W4223424212","https://openalex.org/W4226419870","https://openalex.org/W4235631643","https://openalex.org/W4251693568","https://openalex.org/W4312847929","https://openalex.org/W4312951380","https://openalex.org/W4327930469","https://openalex.org/W4360831845","https://openalex.org/W4385815501","https://openalex.org/W4386506892","https://openalex.org/W4387797345","https://openalex.org/W4388757726","https://openalex.org/W4389584391","https://openalex.org/W4389984066","https://openalex.org/W4390962868","https://openalex.org/W4400526126","https://openalex.org/W4401306886","https://openalex.org/W4407197060"],"related_works":[],"abstract_inverted_index":{"Compute-in-SRAM":[0],"architectures":[1,104],"offer":[2],"a":[3,14,40,47,161],"promising":[4],"approach":[5],"to":[6,68,125,139],"achieving":[7],"higher":[8],"performance":[9,42,74,91,179],"and":[10,43,66,73,120,203],"energy":[11,44,71],"efficiency":[12,72],"across":[13],"range":[15],"of":[16,32,46,100,180,197],"data-intensive":[17],"applications.However,":[18],"prior":[19],"evaluations":[20],"have":[21],"largely":[22],"relied":[23],"on":[24,170],"simulators":[25],"or":[26],"small":[27],"prototypes,":[28],"limiting":[29],"the":[30,51,58,97,171,178,195,208],"understanding":[31],"their":[33],"real-world":[34,201],"potential.In":[35],"this":[36,110,175],"work,":[37],"we":[38],"present":[39],"comprehensive":[41],"characterization":[45],"commercial":[48],"compute-in-SRAM":[49,82,137,173,198],"device,":[50],"GSI":[52,59],"APU,":[53],"under":[54],"realistic":[55],"workloads.We":[56],"compare":[57],"APU":[60],"against":[61],"established":[62],"architectures,":[63],"including":[64],"CPUs":[65],"GPUs,":[67],"quantify":[69],"its":[70],"potential.We":[75],"introduce":[76],"an":[77,144,181],"analytical":[78],"framework":[79],"for":[80,185,199,206],"general-purpose":[81],"devices":[83],"that":[84],"reveals":[85],"fundamental":[86],"optimization":[87],"principles":[88],"by":[89,111,142,152],"modeling":[90],"trade-offs,":[92],"thereby":[93],"guiding":[94],"program":[95],"optimizations.Exploiting":[96],"fine-grained":[98],"parallelism":[99],"tightly":[101],"integrated":[102],"memory-compute":[103],"requires":[105],"careful":[106],"data":[107,122],"management.We":[108],"address":[109],"proposing":[112],"three":[113],"optimizations:":[114],"communicationaware":[115],"reduction":[116],"mapping,":[117],"coalesced":[118],"DMA,":[119],"broadcast-friendly":[121],"layouts.When":[123],"applied":[124],"retrieval-augmented":[126],"generation":[127],"(RAG)":[128],"over":[129],"large":[130],"corpora":[131],"(10GB-200GB),":[132],"these":[133],"optimizations":[134],"enable":[135],"our":[136],"system":[138,176],"accelerate":[140],"retrieval":[141],"4.8\u00d7-6.6\u00d7over":[143],"optimized":[145],"CPU":[146],"baseline,":[147],"improving":[148],"end-to-end":[149],"RAG":[150,186],"latency":[151],"1.1\u00d7-1.8\u00d7.The":[153],"shared":[154],"off-chip":[155],"memory":[156],"bandwidth":[157],"is":[158],"modeled":[159],"using":[160],"simulated":[162],"HBM,":[163],"while":[164,187],"all":[165],"other":[166],"components":[167],"are":[168],"measured":[169],"real":[172],"device.Critically,":[174],"matches":[177],"NVIDIA":[182],"A6000":[183],"GPU":[184],"being":[188],"significantly":[189],"more":[190],"energy-efficient":[191],"(54.4\u00d7-117.9\u00d7reduction).These":[192],"findings":[193],"validate":[194],"viability":[196],"complex,":[200],"applications":[202],"provide":[204],"guidance":[205],"advancing":[207],"technology.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-17T00:00:00"}