{"id":"https://openalex.org/W4413059409","doi":"https://doi.org/10.1145/3708035.3736101","title":"Evaluating Pretraining Efficiency of Language Models on AI Accelerators","display_name":"Evaluating Pretraining Efficiency of Language Models on AI Accelerators","publication_year":2025,"publication_date":"2025-07-18","ids":{"openalex":"https://openalex.org/W4413059409","doi":"https://doi.org/10.1145/3708035.3736101"},"language":"en","primary_location":{"id":"doi:10.1145/3708035.3736101","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3708035.3736101","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":"Practice and Experience in Advanced Research Computing 2025: The Power of Collaboration","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3708035.3736101","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065726189","display_name":"Mei-Yu Wang","orcid":"https://orcid.org/0000-0002-8226-6237"},"institutions":[{"id":"https://openalex.org/I35765314","display_name":"Pittsburgh Supercomputing Center","ror":"https://ror.org/04tac1482","country_code":"US","type":"facility","lineage":["https://openalex.org/I35765314"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mei-Yu Wang","raw_affiliation_strings":["Pittsburgh Supercomputing Center, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8226-6237","affiliations":[{"raw_affiliation_string":"Pittsburgh Supercomputing Center, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I35765314","https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070778782","display_name":"Paola A. Buitrago","orcid":"https://orcid.org/0000-0001-5023-8410"},"institutions":[{"id":"https://openalex.org/I35765314","display_name":"Pittsburgh Supercomputing Center","ror":"https://ror.org/04tac1482","country_code":"US","type":"facility","lineage":["https://openalex.org/I35765314"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paola Buitrago","raw_affiliation_strings":["Pittsburgh Supercomputing Center, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5023-8410","affiliations":[{"raw_affiliation_string":"Pittsburgh Supercomputing Center, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I35765314","https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.15716814,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9952999949455261,"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/T10260","display_name":"Software Engineering Research","score":0.984000027179718,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/computer-science","display_name":"Computer science","score":0.6898218989372253},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5308718681335449},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47120851278305054},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3822103440761566}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6898218989372253},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5308718681335449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47120851278305054},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3822103440761566}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3708035.3736101","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3708035.3736101","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":"Practice and Experience in Advanced Research Computing 2025: The Power of Collaboration","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3708035.3736101","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3708035.3736101","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":"Practice and Experience in Advanced Research Computing 2025: The Power of Collaboration","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2899070097","https://openalex.org/W2963341956","https://openalex.org/W2966412802","https://openalex.org/W3127393641","https://openalex.org/W4386585194"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
