{"id":"https://openalex.org/W4395110738","doi":"https://doi.org/10.1145/3620666.3655592","title":"AWS Trainium: The Journey for Designing and Optimization Full Stack ML Hardware","display_name":"AWS Trainium: The Journey for Designing and Optimization Full Stack ML Hardware","publication_year":2024,"publication_date":"2024-04-24","ids":{"openalex":"https://openalex.org/W4395110738","doi":"https://doi.org/10.1145/3620666.3655592"},"language":"en","primary_location":{"id":"doi:10.1145/3620666.3655592","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3620666.3655592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","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/A5044798349","display_name":"Nafea Bshara","orcid":"https://orcid.org/0009-0000-7696-6563"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nafea Bshara","raw_affiliation_strings":["Amazon, Cupertino, California, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, Cupertino, California, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5044798349"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":2.6595,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.90556207,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9950000047683716,"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":0.9950000047683716,"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":0.974399983882904,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9596999883651733,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/stack","display_name":"Stack (abstract data type)","score":0.7570640444755554},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6738000512123108},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.48115360736846924},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4228765368461609},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3684385418891907},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3573191165924072},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.26339173316955566}],"concepts":[{"id":"https://openalex.org/C9395851","wikidata":"https://www.wikidata.org/wiki/Q177929","display_name":"Stack (abstract data type)","level":2,"score":0.7570640444755554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6738000512123108},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.48115360736846924},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4228765368461609},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3684385418891907},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3573191165924072},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.26339173316955566}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3620666.3655592","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3620666.3655592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2380576232","https://openalex.org/W2937054111","https://openalex.org/W2066223521","https://openalex.org/W2013178899","https://openalex.org/W373327546","https://openalex.org/W2321534397","https://openalex.org/W2058958858","https://openalex.org/W2077601556","https://openalex.org/W2148243540","https://openalex.org/W1835805572"],"abstract_inverted_index":{"Machine":[0],"learning":[1],"accelerators":[2],"present":[3],"a":[4],"unique":[5],"set":[6],"of":[7,53,69,72,84],"design":[8,43,60],"challenges":[9],"across":[10,46],"chip":[11,33],"architecture,":[12],"instruction":[13],"set,":[14],"server":[15],"design,":[16],"compiler,":[17],"and":[18,21,38,44,51,63],"both":[19],"inter-":[20],"intra-chip":[22],"connectivity.":[23],"With":[24],"AWS":[25,73,85],"Trainium,":[26],"we've":[27],"utilized":[28],"AWS's":[29],"end-to-end":[30],"ownership":[31],"from":[32,76],"to":[34,41,78],"server,":[35],"network,":[36],"compilers,":[37],"runtime":[39],"tools":[40],"collaboratively":[42],"optimize":[45],"all":[47],"layers,":[48],"emphasizing":[49],"simplicity":[50],"ease":[52],"use.":[54],"This":[55],"talk":[56],"will":[57],"illustrate":[58],"the":[59,67,82],"principles,":[61],"tradeoffs,":[62],"lessons":[64],"learned":[65],"during":[66],"development":[68],"three":[70],"generations":[71],"ML":[74],"products,":[75],"conceptualization":[77],"placing":[79],"systems":[80],"in":[81],"hands":[83],"customers.":[86]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}
