{"id":"https://openalex.org/W7163575291","doi":"https://doi.org/10.23919/date69613.2026.11539481","title":"FlashGEMM: Mesh-Aware Efficient GEMM for 3D-Stacked LLM Accelerators","display_name":"FlashGEMM: Mesh-Aware Efficient GEMM for 3D-Stacked LLM Accelerators","publication_year":2026,"publication_date":"2026-04-20","ids":{"openalex":"https://openalex.org/W7163575291","doi":"https://doi.org/10.23919/date69613.2026.11539481"},"language":"en","primary_location":{"id":"doi:10.23919/date69613.2026.11539481","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date69613.2026.11539481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 Design, Automation &amp;amp; Test in Europe Conference (DATE)","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":"https://openalex.org/A5137893159","display_name":"Xin Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xin Fan","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100662676","display_name":"Chen Bai","orcid":"https://orcid.org/0000-0002-1742-0090"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chen Bai","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009617323","display_name":"Xin Yang","orcid":"https://orcid.org/0000-0001-9499-4170"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Yang","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137890018","display_name":"Zhenhua Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhenhua Zhu","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100633632","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0003-0098-5359"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yanhong Wang","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137892688","display_name":"Zhaode Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhaode Zhang","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137846052","display_name":"Yuan Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuan Xie","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.186599999666214,"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":0.186599999666214,"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":0.11299999803304672,"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/T10951","display_name":"Cryptographic Implementations and Security","score":0.07810000330209732,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.295199990272522},{"id":"https://openalex.org/keywords/troubleshooting","display_name":"Troubleshooting","score":0.24070000648498535},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2370000034570694},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.22949999570846558},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.22589999437332153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5566999912261963},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2660999894142151},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.24699999392032623},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.24469999969005585},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.24070000648498535},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2370000034570694},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.22949999570846558},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.22589999437332153},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.2184000015258789}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/date69613.2026.11539481","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date69613.2026.11539481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 Design, Automation &amp;amp; Test in Europe Conference (DATE)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-172849","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-172849","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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.5713455080986023}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2056999868","https://openalex.org/W2118231264","https://openalex.org/W2565436413","https://openalex.org/W2970073801","https://openalex.org/W3005962614","https://openalex.org/W3130554079","https://openalex.org/W3136346557","https://openalex.org/W3157657667","https://openalex.org/W3192636176","https://openalex.org/W4324292875","https://openalex.org/W4352977393","https://openalex.org/W4362566357","https://openalex.org/W4362714630","https://openalex.org/W4376130831","https://openalex.org/W4380874786","https://openalex.org/W4388031315","https://openalex.org/W4389518760","https://openalex.org/W4392746501","https://openalex.org/W4396712969","https://openalex.org/W4401211711","https://openalex.org/W4407692602","https://openalex.org/W4410583555","https://openalex.org/W4411471720","https://openalex.org/W4414197293","https://openalex.org/W4416429485"],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"are":[4],"foundational":[5],"to":[6,41,51,56,118],"artificial":[7],"general":[8],"intelligence":[9],"(AGI),":[10],"while":[11],"imposing":[12],"stringent":[13],"hardware":[14],"demands":[15],"in":[16,28,47,67,121,127],"computational":[17],"power":[18],"and":[19,76,104,124],"memory":[20],"bandwidth.":[21],"To":[22,87],"meet":[23],"these":[24,89],"demands,":[25],"recent":[26],"advances":[27],"hybrid":[29],"bonding":[30],"offer":[31],"new":[32],"opportunities":[33],"through":[34],"high-bandwidth,":[35],"low-latency":[36],"logic-memory":[37],"3D":[38],"integration.":[39],"Due":[40],"the":[42,58,64],"spatial":[43],"distribution":[44],"of":[45],"bandwidth":[46],"3D-stacked":[48,109],"DRAM,":[49],"accesses":[50],"remote":[52],"DRAM":[53],"banks":[54],"need":[55],"traverse":[57],"network-on-chip":[59],"(NoC).":[60],"Since":[61],"GEMM":[62,74,97],"is":[63],"dominant":[65],"operator":[66],"LLM":[68,110],"workloads,":[69],"we":[70,91],"analyze":[71],"existing":[72],"distributed":[73,96],"algorithms":[75],"show":[77,113],"that":[78,99,114],"they":[79],"suffer":[80],"from":[81],"communication":[82],"inefficiency":[83],"on":[84],"mesh":[85],"topologies.":[86],"address":[88],"challenges,":[90],"present":[92],"FlashGEMM,":[93],"a":[94],"mesh-aware":[95],"algorithm":[98],"achieves":[100],"efficient":[101],"communication-computation":[102],"overlap":[103],"optimized":[105],"execution":[106],"flow":[107],"for":[108],"accelerators.":[111],"Evaluations":[112],"FlashGEMM":[115],"delivers":[116],"up":[117],"1.50\u00d7":[119],"improvement":[120,126],"time-to-first-token":[122],"(TTFT)":[123],"7.11\u00d7":[125],"throughput":[128],"over":[129],"prior":[130],"methods.":[131]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-06-05T00:00:00"}
