{"id":"https://openalex.org/W7133523832","doi":"https://doi.org/10.1109/hpca68181.2026.11408476","title":"ReThermal: Co-Design of Thermal-Aware Static and Dynamic Scheduling for LLM Training on Liquid-Cooled Wafer-Scale Chips","display_name":"ReThermal: Co-Design of Thermal-Aware Static and Dynamic Scheduling for LLM Training on Liquid-Cooled Wafer-Scale Chips","publication_year":2026,"publication_date":"2026-01-31","ids":{"openalex":"https://openalex.org/W7133523832","doi":"https://doi.org/10.1109/hpca68181.2026.11408476"},"language":null,"primary_location":{"id":"doi:10.1109/hpca68181.2026.11408476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca68181.2026.11408476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)","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/A5016680015","display_name":"Chengran Li","orcid":"https://orcid.org/0009-0005-2650-6506"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chengran Li","raw_affiliation_strings":["School of Integrated circuits, Tsinghua University,BNRist,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"School of Integrated circuits, Tsinghua University,BNRist,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089405414","display_name":"Huizheng Wang","orcid":"https://orcid.org/0000-0002-9763-8208"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huizheng Wang","raw_affiliation_strings":["School of Integrated circuits, Tsinghua University,BNRist,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"School of Integrated circuits, Tsinghua University,BNRist,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383758","display_name":"Jiaxin Liu","orcid":"https://orcid.org/0000-0001-9204-3988"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxin Liu","raw_affiliation_strings":["School of Integrated circuits, Tsinghua University,BNRist,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"School of Integrated circuits, Tsinghua University,BNRist,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108086414","display_name":"Jingyao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyao Liu","raw_affiliation_strings":["School of Integrated circuits, Tsinghua University,BNRist,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"School of Integrated circuits, Tsinghua University,BNRist,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009692777","display_name":"Zhiheng Yue","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiheng Yue","raw_affiliation_strings":["School of Integrated circuits, Tsinghua University,BNRist,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"School of Integrated circuits, Tsinghua University,BNRist,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128074019","display_name":"Xia Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xia Li","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory,Shanghai,China,200433"],"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory,Shanghai,China,200433","institution_ids":["https://openalex.org/I4391012619","https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067578634","display_name":"Shenfei Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenfei Jiang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory,Shanghai,China,200433"],"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory,Shanghai,China,200433","institution_ids":["https://openalex.org/I4391012619","https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070641802","display_name":"Jinyi Deng","orcid":"https://orcid.org/0000-0001-8666-8463"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinyi Deng","raw_affiliation_strings":["School of Integrated circuits, Tsinghua University,BNRist,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"School of Integrated circuits, Tsinghua University,BNRist,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068155662","display_name":"Yuanming Hu","orcid":"https://orcid.org/0000-0002-1136-9909"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Hu","raw_affiliation_strings":["School of Integrated circuits, Tsinghua University,BNRist,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"School of Integrated circuits, Tsinghua University,BNRist,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078843314","display_name":"Shouyi Yin","orcid":"https://orcid.org/0000-0002-8438-8588"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shouyi Yin","raw_affiliation_strings":["School of Integrated circuits, Tsinghua University,BNRist,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"School of Integrated circuits, Tsinghua University,BNRist,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5016680015"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40565493,"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":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.19869999587535858,"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":0.19869999587535858,"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/T10998","display_name":"Heat Transfer and Optimization","score":0.07739999890327454,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T11527","display_name":"3D IC and TSV technologies","score":0.07000000029802322,"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/scheduling","display_name":"Scheduling (production processes)","score":0.46299999952316284},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.40540000796318054},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.26750001311302185},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.2434999942779541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6136000156402588},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.46299999952316284},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.40540000796318054},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3407999873161316},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.30059999227523804},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2824999988079071},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.25270000100135803},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.2434999942779541},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.23569999635219574}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpca68181.2026.11408476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca68181.2026.11408476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.622677206993103}],"awards":[{"id":"https://openalex.org/G1187591493","display_name":null,"funder_award_id":"2022ZD0115200","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G3053168118","display_name":null,"funder_award_id":"62502255,62125403,U24B20164,U24A20234,92464302","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329777","display_name":"Beijing National Research Center For Information Science And Technology","ror":null},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W88816938","https://openalex.org/W2023372719","https://openalex.org/W2046826146","https://openalex.org/W2060733183","https://openalex.org/W2099648605","https://openalex.org/W2130841580","https://openalex.org/W2140020798","https://openalex.org/W2145135695","https://openalex.org/W2170382128","https://openalex.org/W2185864411","https://openalex.org/W2295332056","https://openalex.org/W2545981026","https://openalex.org/W2595507424","https://openalex.org/W2604319603","https://openalex.org/W2607754171","https://openalex.org/W2743542620","https://openalex.org/W2885213983","https://openalex.org/W2887610787","https://openalex.org/W2969388332","https://openalex.org/W2973029716","https://openalex.org/W2980104813","https://openalex.org/W2991040477","https://openalex.org/W3031421697","https://openalex.org/W3047766185","https://openalex.org/W3127658360","https://openalex.org/W3132191748","https://openalex.org/W3133446571","https://openalex.org/W3163019281","https://openalex.org/W3189273774","https://openalex.org/W3204998121","https://openalex.org/W3216238950","https://openalex.org/W4245911027","https://openalex.org/W4294991347","https://openalex.org/W4297097426","https://openalex.org/W4298148678","https://openalex.org/W4312786694","https://openalex.org/W4324292875","https://openalex.org/W4352977393","https://openalex.org/W4386693657","https://openalex.org/W4387480490","https://openalex.org/W4389365381","https://openalex.org/W4392058134","https://openalex.org/W4392567268","https://openalex.org/W4396732723","https://openalex.org/W4399431532","https://openalex.org/W4400237250","https://openalex.org/W4401211750","https://openalex.org/W4403570806","https://openalex.org/W4405220108","https://openalex.org/W4406107053","https://openalex.org/W4408894415","https://openalex.org/W4411486243","https://openalex.org/W4411486513","https://openalex.org/W4411486567","https://openalex.org/W4413431245","https://openalex.org/W4413769320","https://openalex.org/W4415792806"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,20,59,63,68,103],"increasing":[2],"demand":[3],"for":[4,172],"high":[5],"computational":[6],"power":[7],"in":[8],"Large":[9],"Language":[10],"Models,":[11],"wafer-scale":[12,111,175],"chips":[13],"have":[14],"emerged":[15],"as":[16],"a":[17,79,109,165],"solution,":[18],"providing":[19,164],"necessary":[21],"integration":[22],"and":[23,34,55,67,98,117,136,156,167],"computing":[24],"capability":[25],"to":[26,93,139,153,161],"meet":[27],"these":[28,74],"needs.":[29],"However,":[30],"their":[31],"ultralarge":[32],"area":[33],"extreme":[35],"heat":[36,99],"dissipation":[37],"introduce":[38,89],"critical":[39],"thermal":[40,91,112,169],"management":[41],"challenges":[42],"under":[43],"liquid-cooling":[44],"environments.":[45],"In":[46],"addressing":[47],"this":[48],"issue,":[49],"we":[50,76,88,107,126],"identify":[51],"two":[52],"key":[53],"opportunities":[54],"three":[56,85],"major":[57],"challenges:":[58],"behavior-thermal":[60],"black":[61],"box,":[62],"waferscale":[64],"simulation":[65,123],"bottleneck,":[66],"runtime":[69,137],"heat-schedule":[70],"drift.":[71],"To":[72],"tackle":[73],"challenges,":[75],"propose":[77],"ReThermal,":[78],"holistic":[80],"scheduling":[81,131],"framework":[82],"that":[83,114,133,146],"integrates":[84],"innovations.":[86],"First,":[87],"behavior-driven":[90],"modeling":[92],"capture":[94],"workload-induced":[95],"compute,":[96],"communication,":[97],"coupling":[100],"patterns":[101],"at":[102],"system":[104],"level.":[105],"Second,":[106],"develop":[108],"DNNaccelerated":[110],"simulator":[113],"enables":[115],"fast":[116],"accurate":[118],"temperature":[119,150],"prediction,":[120],"significantly":[121],"reducing":[122],"time.":[124],"Third,":[125],"implement":[127],"an":[128],"adaptive":[129],"thermal-aware":[130],"strategy":[132],"coordinates":[134],"compile-time":[135],"decisions":[138],"dynamically":[140],"optimize":[141],"task":[142],"placement.":[143],"Evaluations":[144],"show":[145],"ReThermal":[147],"reduces":[148],"peak":[149],"by":[151,159],"up":[152,160],"8.0\u00b0":[154],"C":[155],"improves":[157],"throughput":[158],"39.23":[162],"%,":[163],"scalable":[166],"effective":[168],"control":[170],"solution":[171],"future":[173],"liquid-cooled":[174],"systems.":[176]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-03-05T00:00:00"}
