{"id":"https://openalex.org/W7123452404","doi":"https://doi.org/10.1145/3772052.3772233","title":"Snap & Replay: A new way to analyze uarch-scale performance bottlenecks for ML accelerators","display_name":"Snap & Replay: A new way to analyze uarch-scale performance bottlenecks for ML accelerators","publication_year":2025,"publication_date":"2025-11-19","ids":{"openalex":"https://openalex.org/W7123452404","doi":"https://doi.org/10.1145/3772052.3772233"},"language":null,"primary_location":{"id":"doi:10.1145/3772052.3772233","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3772052.3772233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Symposium on Cloud 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/A5122926487","display_name":"Ioannis Zarkadas","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ioannis Zarkadas","raw_affiliation_strings":["Columbia University, New York, USA"],"raw_orcid":"https://orcid.org/0009-0000-2364-3891","affiliations":[{"raw_affiliation_string":"Columbia University, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122931544","display_name":"Amanda Tomlinson","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amanda Tomlinson","raw_affiliation_strings":["University of California, San Diego, San Diego, USA"],"raw_orcid":"https://orcid.org/0009-0003-8209-5006","affiliations":[{"raw_affiliation_string":"University of California, San Diego, San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032570570","display_name":"Asaf Cidon","orcid":"https://orcid.org/0009-0007-4046-2022"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Asaf Cidon","raw_affiliation_strings":["Columbia University, New York, USA"],"raw_orcid":"https://orcid.org/0009-0007-4046-2022","affiliations":[{"raw_affiliation_string":"Columbia University, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050964144","display_name":"Baris Kasikci","orcid":"https://orcid.org/0000-0001-6122-8998"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baris Kasikci","raw_affiliation_strings":["University of Washington, Seattle, USA"],"raw_orcid":"https://orcid.org/0000-0001-6122-8998","affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, USA","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I58610484"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082705026","display_name":"Ofir Weisse","orcid":"https://orcid.org/0000-0001-7564-6007"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ofir Weisse","raw_affiliation_strings":["Google, Sunnyvale, USA"],"raw_orcid":"https://orcid.org/0000-0001-7564-6007","affiliations":[{"raw_affiliation_string":"Google, Sunnyvale, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.65724453,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"283","last_page":"298"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8127999901771545,"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":0.8127999901771545,"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":0.02630000002682209,"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/T12127","display_name":"Software System Performance and Reliability","score":0.02630000002682209,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.44029998779296875},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.4275999963283539},{"id":"https://openalex.org/keywords/snap","display_name":"Snap","score":0.4025999903678894},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.35409998893737793},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3287999927997589},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.29170000553131104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7092000246047974},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.44029998779296875},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.4275999963283539},{"id":"https://openalex.org/C2779997099","wikidata":"https://www.wikidata.org/wiki/Q7547253","display_name":"Snap","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.35109999775886536},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.29739999771118164},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.27889999747276306},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.26649999618530273},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C2992770021","wikidata":"https://www.wikidata.org/wiki/Q7247850","display_name":"Production model","level":3,"score":0.25540000200271606},{"id":"https://openalex.org/C99862985","wikidata":"https://www.wikidata.org/wiki/Q10858068","display_name":"Production line","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3772052.3772233","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3772052.3772233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Symposium on Cloud Computing","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":23,"referenced_works":["https://openalex.org/W1979527452","https://openalex.org/W2034062945","https://openalex.org/W2147657366","https://openalex.org/W2158668620","https://openalex.org/W2160428323","https://openalex.org/W2784062457","https://openalex.org/W2789572737","https://openalex.org/W2901073342","https://openalex.org/W2953212265","https://openalex.org/W2954698171","https://openalex.org/W2979340153","https://openalex.org/W2998732502","https://openalex.org/W3017521908","https://openalex.org/W3102510044","https://openalex.org/W3122286897","https://openalex.org/W3136358373","https://openalex.org/W3157055696","https://openalex.org/W4214707742","https://openalex.org/W4285167314","https://openalex.org/W4361197980","https://openalex.org/W4380874786","https://openalex.org/W4380881154","https://openalex.org/W4387321091"],"related_works":[],"abstract_inverted_index":{"As":[0],"models":[1,72],"become":[2],"larger,":[3],"ML":[4,71],"accelerators":[5],"are":[6,23,48],"a":[7,66],"scarce":[8],"resource":[9],"whose":[10],"performance":[11,20,30],"must":[12],"be":[13],"continually":[14],"optimized":[15],"to":[16,27,50],"improve":[17],"efficiency.":[18],"Existing":[19],"analysis":[21],"tools":[22],"coarse":[24],"grained,":[25],"fail":[26],"capture":[28],"model":[29],"at":[31,73],"the":[32,74],"machine-code":[33,75],"level":[34,76],"and":[35,87],"often":[36],"do":[37],"not":[38],"provide":[39],"specific":[40],"recommendations":[41],"for":[42,69],"optimizations.":[43],"In":[44],"addition,":[45],"existing":[46],"methodologies":[47],"hard":[49],"apply":[51],"in":[52],"Google's":[53],"production":[54],"environment,":[55],"as":[56],"they":[57],"require":[58],"hardware":[59,85],"changes":[60,86],"or":[61],"recompilation.":[62,89],"We":[63],"present":[64],"SnR,":[65],"fine-grained":[67],"methodology":[68],"analyzing":[70],"that":[77],"provides":[78],"actionable":[79],"optimization":[80],"suggestions.":[81],"It":[82],"requires":[83],"no":[84,88]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-14T00:00:00"}