{"id":"https://openalex.org/W4402044800","doi":"https://doi.org/10.1145/3625549.3658693","title":"Near-Optimal Wafer-Scale Reduce","display_name":"Near-Optimal Wafer-Scale Reduce","publication_year":2024,"publication_date":"2024-06-03","ids":{"openalex":"https://openalex.org/W4402044800","doi":"https://doi.org/10.1145/3625549.3658693"},"language":"en","primary_location":{"id":"doi:10.1145/3625549.3658693","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3625549.3658693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd International Symposium on High-Performance Parallel and Distributed Computing","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/A5082165381","display_name":"Piotr \u0141uczy\u0144ski","orcid":"https://orcid.org/0000-0002-8779-4223"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Piotr Luczynski","raw_affiliation_strings":["Department of Computer Science, ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-8779-4223","affiliations":[{"raw_affiliation_string":"Department of Computer Science, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052014295","display_name":"Lukas Gianinazzi","orcid":"https://orcid.org/0000-0001-5975-4526"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Lukas Gianinazzi","raw_affiliation_strings":["Department of Computer Science, ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-5975-4526","affiliations":[{"raw_affiliation_string":"Department of Computer Science, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060901174","display_name":"Patrick Iff","orcid":"https://orcid.org/0000-0001-5979-4915"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Patrick Iff","raw_affiliation_strings":["Department of Computer Science, ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-5979-4915","affiliations":[{"raw_affiliation_string":"Department of Computer Science, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014335702","display_name":"Leighton Wilson","orcid":"https://orcid.org/0000-0003-1676-8156"},"institutions":[{"id":"https://openalex.org/I4401726927","display_name":"Cerebras Systems (United States)","ror":"https://ror.org/040zz8080","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726927"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leighton Wilson","raw_affiliation_strings":["Cerebras Systems, Sunnyvale, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1676-8156","affiliations":[{"raw_affiliation_string":"Cerebras Systems, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4401726927"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056277459","display_name":"Daniele De Sensi","orcid":"https://orcid.org/0000-0002-7244-639X"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Daniele De Sensi","raw_affiliation_strings":["Department of Computer Science, Sapienza University of Rome, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0002-7244-639X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Sapienza University of Rome, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026990786","display_name":"Torsten Hoefler","orcid":"https://orcid.org/0000-0002-1333-9797"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Torsten Hoefler","raw_affiliation_strings":["Department of Computer Science, ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-1333-9797","affiliations":[{"raw_affiliation_string":"Department of Computer Science, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5082165381"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":1.2017,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79146188,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"334","last_page":"347"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11527","display_name":"3D IC and TSV technologies","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"}},"topics":[{"id":"https://openalex.org/T11527","display_name":"3D IC and TSV technologies","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/T10472","display_name":"Semiconductor materials and devices","score":0.998199999332428,"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/T10623","display_name":"Thin-Film Transistor Technologies","score":0.998199999332428,"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/wafer","display_name":"Wafer","score":0.6921103596687317},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5939255952835083},{"id":"https://openalex.org/keywords/wafer-scale-integration","display_name":"Wafer-scale integration","score":0.5808775424957275},{"id":"https://openalex.org/keywords/environmental-science","display_name":"Environmental science","score":0.4349689185619354},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.42393797636032104},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.29733943939208984},{"id":"https://openalex.org/keywords/optoelectronics","display_name":"Optoelectronics","score":0.2459435760974884},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0893431305885315},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.05775132775306702}],"concepts":[{"id":"https://openalex.org/C160671074","wikidata":"https://www.wikidata.org/wiki/Q267131","display_name":"Wafer","level":2,"score":0.6921103596687317},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5939255952835083},{"id":"https://openalex.org/C2778638305","wikidata":"https://www.wikidata.org/wiki/Q7406100","display_name":"Wafer-scale integration","level":3,"score":0.5808775424957275},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.4349689185619354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42393797636032104},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.29733943939208984},{"id":"https://openalex.org/C49040817","wikidata":"https://www.wikidata.org/wiki/Q193091","display_name":"Optoelectronics","level":1,"score":0.2459435760974884},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0893431305885315},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.05775132775306702}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3625549.3658693","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3625549.3658693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniroma1.it:11573/1737587","is_oa":false,"landing_page_url":"https://hdl.handle.net/11573/1737587","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1518038022","https://openalex.org/W1570056235","https://openalex.org/W1572016165","https://openalex.org/W1860827079","https://openalex.org/W1970537620","https://openalex.org/W1976417857","https://openalex.org/W1977492904","https://openalex.org/W1997674404","https://openalex.org/W2000882268","https://openalex.org/W2013475701","https://openalex.org/W2025177582","https://openalex.org/W2036341441","https://openalex.org/W2038423000","https://openalex.org/W2057332538","https://openalex.org/W2080803508","https://openalex.org/W2081612620","https://openalex.org/W2087124296","https://openalex.org/W2100697281","https://openalex.org/W2104487100","https://openalex.org/W2131613942","https://openalex.org/W2149658259","https://openalex.org/W2170796499","https://openalex.org/W2741661236","https://openalex.org/W2918037051","https://openalex.org/W2972087877","https://openalex.org/W2985025837","https://openalex.org/W3037182822","https://openalex.org/W3129251660","https://openalex.org/W3133446571","https://openalex.org/W3147460469","https://openalex.org/W3149736422","https://openalex.org/W3206328251","https://openalex.org/W3206778761","https://openalex.org/W3211226062","https://openalex.org/W4223480868","https://openalex.org/W4237651079","https://openalex.org/W4280630071","https://openalex.org/W4281249911","https://openalex.org/W4293731257","https://openalex.org/W4298180343","https://openalex.org/W4321636758","https://openalex.org/W4362707004","https://openalex.org/W4376130831","https://openalex.org/W4381327281","https://openalex.org/W4388697601","https://openalex.org/W4390431167","https://openalex.org/W4400411684","https://openalex.org/W6642567307","https://openalex.org/W6929031163","https://openalex.org/W6947595712"],"related_works":["https://openalex.org/W2970498257","https://openalex.org/W2140660040","https://openalex.org/W2041316527","https://openalex.org/W2036313051","https://openalex.org/W4400034431","https://openalex.org/W2065601166","https://openalex.org/W2160598879","https://openalex.org/W2082419378","https://openalex.org/W2146366317","https://openalex.org/W993605666"],"abstract_inverted_index":{"Efficient":[0],"Reduce":[1,22,106,135],"and":[2,23,45,66,85,136],"AllReduce":[3,24,137],"communication":[4,160],"collectives":[5,161],"are":[6],"a":[7,53,72,98,105,182],"critical":[8],"cornerstone":[9],"of":[10,21,61,75,104,127,165,175],"high-performance":[11],"computing":[12],"(HPC)":[13],"applications.":[14],"We":[15,51],"present":[16],"the":[17,26,58,64,93,102,109,124,140,163,172,176,188],"first":[18],"systematic":[19],"investigation":[20],"on":[25,63,108,112,194],"Cerebras":[27],"Wafer-Scale":[28],"Engine":[29],"(WSE).":[30],"This":[31],"architecture":[32],"has":[33],"been":[34],"shown":[35],"to":[36,56,80,92,146,190],"achieve":[37],"unprecedented":[38],"performance":[39,54,122,152],"both":[40],"for":[41,71,101],"machine":[42],"learning":[43],"workloads":[44],"other":[46],"computational":[47],"problems":[48],"like":[49],"FFT.":[50],"introduce":[52],"model":[55,150],"estimate":[57],"execution":[59],"time":[60],"algorithms":[62,89,138],"WSE":[65],"validate":[67],"our":[68,113,133,149],"predictions":[69],"experimentally":[70],"wide":[73],"range":[74,126,164],"input":[76,128],"sizes.":[77,129],"In":[78],"addition":[79],"existing":[81],"implementations,":[82],"we":[83,96,115],"design":[84],"implement":[86],"several":[87],"new":[88,134],"specifically":[90],"tailored":[91],"architecture.":[94],"Moreover,":[95],"establish":[97],"lower":[99],"bound":[100],"runtime":[103],"operation":[107],"WSE.":[110,177],"Based":[111],"model,":[114],"automatically":[116],"generate":[117],"code":[118],"that":[119,132,168,185],"achieves":[120],"near-optimal":[121],"across":[123],"whole":[125],"Experiments":[130],"demonstrate":[131],"outperform":[139],"current":[141],"vendor":[142],"solution":[143],"by":[144],"up":[145],"3.27\u00d7.":[147],"Additionally,":[148],"predicts":[151],"with":[153],"less":[154],"than":[155],"4%":[156],"error.":[157],"The":[158],"proposed":[159],"increase":[162],"HPC":[166],"applications":[167],"can":[169,186],"benefit":[170],"from":[171],"high":[173],"throughput":[174],"Our":[178],"model-driven":[179],"methodology":[180],"demonstrates":[181],"disciplined":[183],"approach":[184],"lead":[187],"way":[189],"further":[191],"algorithmic":[192],"advancements":[193],"wafer-scale":[195],"architectures.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}