{"id":"https://openalex.org/W4416003958","doi":"https://doi.org/10.1145/3731599.3767407","title":"Batch Tiling on Attention: Efficient Mixture of Experts Training on Wafer-Scale Processors","display_name":"Batch Tiling on Attention: Efficient Mixture of Experts Training on Wafer-Scale Processors","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416003958","doi":"https://doi.org/10.1145/3731599.3767407"},"language":null,"primary_location":{"id":"doi:10.1145/3731599.3767407","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767407","pdf_url":null,"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 SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3731599.3767407","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057449462","display_name":"Daria Soboleva","orcid":"https://orcid.org/0009-0003-2654-3767"},"institutions":[{"id":"https://openalex.org/I4210140540","display_name":"Singularity University","ror":"https://ror.org/04rv9a088","country_code":"US","type":"education","lineage":["https://openalex.org/I4210140540"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daria Soboleva","raw_affiliation_strings":["Cerebras, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Cerebras, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210140540"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029166672","display_name":"\u00c9tienne Goffinet","orcid":"https://orcid.org/0000-0002-0120-0392"},"institutions":[{"id":"https://openalex.org/I2801277386","display_name":"Emirates Foundation","ror":"https://ror.org/05nd26619","country_code":"AE","type":"other","lineage":["https://openalex.org/I2801277386"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Etienne Goffinet","raw_affiliation_strings":["Cerebras, Abu Dabi, United Arab Emirates"],"affiliations":[{"raw_affiliation_string":"Cerebras, Abu Dabi, United Arab Emirates","institution_ids":["https://openalex.org/I2801277386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112908554","display_name":"Hui Zeng","orcid":"https://orcid.org/0009-0006-9719-309X"},"institutions":[{"id":"https://openalex.org/I4210140540","display_name":"Singularity University","ror":"https://ror.org/04rv9a088","country_code":"US","type":"education","lineage":["https://openalex.org/I4210140540"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hui Zeng","raw_affiliation_strings":["Cerebras, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Cerebras, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210140540"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044322147","display_name":"Sangamesh Nagashattappa Ragate","orcid":"https://orcid.org/0009-0008-9189-2310"},"institutions":[{"id":"https://openalex.org/I4210140540","display_name":"Singularity University","ror":"https://ror.org/04rv9a088","country_code":"US","type":"education","lineage":["https://openalex.org/I4210140540"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sangamesh Ragate","raw_affiliation_strings":["Cerebras, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Cerebras, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210140540"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085405060","display_name":"E. Albuz","orcid":"https://orcid.org/0009-0006-9203-0611"},"institutions":[{"id":"https://openalex.org/I4210140540","display_name":"Singularity University","ror":"https://ror.org/04rv9a088","country_code":"US","type":"education","lineage":["https://openalex.org/I4210140540"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elif Albuz","raw_affiliation_strings":["Cerebras, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Cerebras, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210140540"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5099338040","display_name":"Natalia Vassilieva","orcid":"https://orcid.org/0009-0003-1038-1572"},"institutions":[{"id":"https://openalex.org/I4210140540","display_name":"Singularity University","ror":"https://ror.org/04rv9a088","country_code":"US","type":"education","lineage":["https://openalex.org/I4210140540"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Natalia Vassilieva","raw_affiliation_strings":["Cerebras, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Cerebras, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210140540"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5057449462"],"corresponding_institution_ids":["https://openalex.org/I4210140540"],"apc_list":null,"apc_paid":null,"fwci":0.8073,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78296616,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"540","last_page":"544"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.1306000053882599,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.1306000053882599,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.0869000032544136,"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"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.06840000301599503,"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/training","display_name":"Training (meteorology)","score":0.5604000091552734},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.4578999876976013},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4542999863624573},{"id":"https://openalex.org/keywords/batch-processing","display_name":"Batch processing","score":0.3416000008583069},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.32170000672340393},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.29809999465942383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.744700014591217},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5604000091552734},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.4578999876976013},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4542999863624573},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.43849998712539673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35350000858306885},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28060001134872437},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2583000063896179}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731599.3767407","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767407","pdf_url":null,"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 SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3731599.3767407","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767407","pdf_url":null,"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 SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W4220967350","https://openalex.org/W4376652719","https://openalex.org/W4386709668","https://openalex.org/W4394923534","https://openalex.org/W4401211627","https://openalex.org/W4413500911"],"related_works":[],"abstract_inverted_index":{"Mixture":[0],"of":[1],"Experts":[2],"(MoE)":[3],"models":[4],"face":[5],"significant":[6],"computational":[7],"bottlenecks":[8],"on":[9,45],"wafer-scale":[10],"processors":[11],"due":[12,30],"to":[13,31,40],"conflicting":[14],"batch":[15,28],"size":[16],"requirements":[17],"between":[18],"attention":[19,24],"and":[20],"MLP":[21,35],"layers.":[22],"While":[23],"mechanisms":[25],"demand":[26],"smaller":[27],"sizes":[29],"memory":[32],"constraints,":[33],"routable":[34],"layers":[36],"require":[37],"larger":[38],"batches":[39],"achieve":[41],"optimal":[42],"compute":[43],"density":[44],"massively":[46],"parallel":[47],"architectures.":[48]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-07T00:00:00"}
