{"id":"https://openalex.org/W7167032945","doi":"https://doi.org/10.1145/3797905.3800537","title":"SPPO: Making Million-Token LLM Training Practical on Modest GPU Clusters","display_name":"SPPO: Making Million-Token LLM Training Practical on Modest GPU Clusters","publication_year":2026,"publication_date":"2026-07-02","ids":{"openalex":"https://openalex.org/W7167032945","doi":"https://doi.org/10.1145/3797905.3800537"},"language":null,"primary_location":{"id":"doi:10.1145/3797905.3800537","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3800537","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 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3797905.3800537","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066190624","display_name":"Q J Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"qiaoling chen","raw_affiliation_strings":["Nanyang Technology University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0007-0779-3305","affiliations":[{"raw_affiliation_string":"Nanyang Technology University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055716015","display_name":"Shenggui Li","orcid":"https://orcid.org/0000-0003-2037-2496"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shenggui Li","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-2037-2496","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100732619","display_name":"Wei Gao","orcid":"https://orcid.org/0000-0002-7048-1722"},"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":"Wei Gao","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hongkong, China"],"raw_orcid":"https://orcid.org/0000-0002-7048-1722","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hongkong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614087","display_name":"Peng Sun","orcid":"https://orcid.org/0000-0001-8456-0491"},"institutions":[{"id":"https://openalex.org/I4210162556","display_name":"Shangri-la Institute","ror":"https://ror.org/05e0fad36","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210162556"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Sun","raw_affiliation_strings":["Shanghai AI Laboratory, SHANG HAI, China"],"raw_orcid":"https://orcid.org/0000-0001-8456-0491","affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, SHANG HAI, China","institution_ids":["https://openalex.org/I4210162556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041572550","display_name":"Yonggang Wen","orcid":"https://orcid.org/0000-0002-2751-5114"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yonggang Wen","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-2751-5114","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101591101","display_name":"Tianwei Zhang","orcid":"https://orcid.org/0000-0001-6595-6650"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tianwei Zhang","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6595-6650","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"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":"342","last_page":"352"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.2508000135421753,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.2508000135421753,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.11379999667406082,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T14347","display_name":"Big Data and Digital Economy","score":0.0632999986410141,"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/training","display_name":"Training (meteorology)","score":0.7008000016212463},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6958000063896179},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.6664000153541565},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6116999983787537},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5249000191688538},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5080999732017517}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7972000241279602},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7008000016212463},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6958000063896179},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.6664000153541565},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6116999983787537},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5249000191688538},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5080999732017517},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.49630001187324524},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.4934000074863434},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3386000096797943},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.31040000915527344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3077999949455261},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2680000066757202},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.26330000162124634},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.259799987077713},{"id":"https://openalex.org/C46355384","wikidata":"https://www.wikidata.org/wiki/Q726686","display_name":"Compromise","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3797905.3800537","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3800537","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 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3797905.3800537","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3800537","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 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2964174152","https://openalex.org/W2969388332","https://openalex.org/W3012514909","https://openalex.org/W3132107458","https://openalex.org/W3204998121","https://openalex.org/W4210352519","https://openalex.org/W4383218913","https://openalex.org/W4390872297","https://openalex.org/W4411120118"],"related_works":[],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"have":[7],"exhibited":[8],"remarkable":[9],"capabilities,":[10],"driving":[11],"advancements":[12],"in":[13],"real-world":[14],"applications.":[15],"However,":[16],"training":[17,53],"LLMs":[18],"on":[19],"increasingly":[20],"long":[21],"input":[22,67],"sequences":[23],"imposes":[24],"significant":[25],"challenges":[26],"due":[27],"to":[28],"high":[29],"GPU":[30,61],"memory":[31,42],"and":[32,49],"computational":[33],"demands.":[34],"Existing":[35],"solutions":[36],"face":[37],"two":[38],"key":[39],"limitations:":[40],"(1)":[41],"reduction":[43],"techniques,":[44],"such":[45],"as":[46],"activation":[47],"recomputation":[48],"CPU":[50],"offloading,":[51],"compromise":[52],"efficiency;":[54],"(2)":[55],"distributed":[56],"parallelism":[57],"strategies":[58],"require":[59],"excessive":[60],"resources,":[62],"limiting":[63],"the":[64],"scalability":[65],"of":[66],"sequence":[68],"length.":[69]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-07-03T00:00:00"}