{"id":"https://openalex.org/W4391952907","doi":"https://doi.org/10.1145/3627535.3638465","title":"FastFold: Optimizing AlphaFold Training and Inference on GPU Clusters","display_name":"FastFold: Optimizing AlphaFold Training and Inference on GPU Clusters","publication_year":2024,"publication_date":"2024-02-20","ids":{"openalex":"https://openalex.org/W4391952907","doi":"https://doi.org/10.1145/3627535.3638465"},"language":"en","primary_location":{"id":"doi:10.1145/3627535.3638465","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627535.3638465","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3627535.3638465","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 29th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3627535.3638465","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037038779","display_name":"Shenggan Cheng","orcid":"https://orcid.org/0000-0002-7966-2941"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shenggan Cheng","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7966-2941","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102796963","display_name":"Xuanlei Zhao","orcid":"https://orcid.org/0009-0000-4877-3115"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuanlei Zhao","raw_affiliation_strings":["HPC-AI Tech, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-4877-3115","affiliations":[{"raw_affiliation_string":"HPC-AI Tech, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029831171","display_name":"Guangyang Lu","orcid":"https://orcid.org/0009-0003-8474-4516"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guangyang Lu","raw_affiliation_strings":["HPC-AI Tech, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-8474-4516","affiliations":[{"raw_affiliation_string":"HPC-AI Tech, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069911612","display_name":"Jiarui Fang","orcid":"https://orcid.org/0000-0002-6724-2763"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiarui Fang","raw_affiliation_strings":["HPC-AI Tech, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6724-2763","affiliations":[{"raw_affiliation_string":"HPC-AI Tech, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101612260","display_name":"Tian Zheng","orcid":"https://orcid.org/0000-0002-6164-7778"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian Zheng","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-6164-7778","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064754528","display_name":"Ruidong Wu","orcid":"https://orcid.org/0009-0002-6402-4717"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruidong Wu","raw_affiliation_strings":["HeliXon, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-6402-4717","affiliations":[{"raw_affiliation_string":"HeliXon, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102744898","display_name":"Xiwen Zhang","orcid":"https://orcid.org/0009-0006-7134-366X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiwen Zhang","raw_affiliation_strings":["HeliXon, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-7134-366X","affiliations":[{"raw_affiliation_string":"HeliXon, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061177999","display_name":"Jian Peng","orcid":"https://orcid.org/0000-0002-1736-2978"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Peng","raw_affiliation_strings":["HeliXon, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1736-2978","affiliations":[{"raw_affiliation_string":"HeliXon, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100658705","display_name":"Yang You","orcid":"https://orcid.org/0000-0003-2816-4384"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yang You","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-2816-4384","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.837,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.84520859,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"417","last_page":"430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9991000294685364,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9991000294685364,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9986000061035156,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials 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":0.8438875675201416},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8223704099655151},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7669203281402588},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6544926166534424},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6444235444068909},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.4352447986602783},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3682228624820709},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2807411551475525},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.2586899697780609}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8438875675201416},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8223704099655151},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7669203281402588},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6544926166534424},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6444235444068909},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.4352447986602783},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3682228624820709},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2807411551475525},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.2586899697780609}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627535.3638465","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627535.3638465","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3627535.3638465","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 29th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3627535.3638465","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627535.3638465","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3627535.3638465","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 29th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391952907.pdf","grobid_xml":"https://content.openalex.org/works/W4391952907.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2045777307","https://openalex.org/W2115540209","https://openalex.org/W2161151688","https://openalex.org/W2606722458","https://openalex.org/W2734941459","https://openalex.org/W2963341956","https://openalex.org/W2967606876","https://openalex.org/W3129831491","https://openalex.org/W3130716829","https://openalex.org/W3132107458","https://openalex.org/W3133458480","https://openalex.org/W3172198372","https://openalex.org/W3177828909","https://openalex.org/W3204998121","https://openalex.org/W3205803342","https://openalex.org/W3207457994","https://openalex.org/W4214612132","https://openalex.org/W4376131109","https://openalex.org/W4386348101","https://openalex.org/W6893899980"],"related_works":["https://openalex.org/W2317245370","https://openalex.org/W4249323025","https://openalex.org/W2097707447","https://openalex.org/W198851386","https://openalex.org/W2030310580","https://openalex.org/W947442053","https://openalex.org/W1980160788","https://openalex.org/W2148915962","https://openalex.org/W2283866686","https://openalex.org/W2319266294"],"abstract_inverted_index":{"Protein":[0],"structure":[1,34],"prediction":[2],"helps":[3],"to":[4,28,50,122,134,147],"understand":[5],"gene":[6],"translation":[7],"and":[8,16,42,54,71,99,111,139,150],"protein":[9,33],"function,":[10],"which":[11,24],"is":[12],"of":[13,44,66,91],"growing":[14],"interest":[15],"importance":[17],"in":[18,32],"structural":[19],"biology.":[20],"The":[21],"AlphaFold":[22,45,67],"model,":[23],"used":[25],"transformer":[26],"architecture":[27],"achieve":[29],"atomic-level":[30],"accuracy":[31],"prediction,":[35],"was":[36],"a":[37,80,89],"significant":[38],"breakthrough.":[39],"However,":[40],"training":[41,70,142],"inference":[43,169],"model":[46,82],"are":[47],"challenging":[48],"due":[49],"its":[51],"high":[52],"computation":[53],"memory":[55,100,124,163],"cost.":[56],"In":[57],"this":[58],"work,":[59],"we":[60,86],"present":[61],"FastFold,":[62],"an":[63],"efficient":[64],"implementation":[65],"for":[68,156],"both":[69],"inference.":[72,158],"We":[73],"propose":[74],"Dynamic":[75],"Axial":[76],"Parallelism":[77],"(DAP)":[78],"as":[79],"novel":[81],"parallelism":[83],"method.":[84],"Additionally,":[85],"have":[87],"implemented":[88],"series":[90],"low-level":[92],"optimizations":[93,103],"aimed":[94],"at":[95],"reducing":[96],"communication,":[97],"computation,":[98],"costs.":[101],"These":[102],"include":[104],"Duality":[105],"Async":[106],"Operations,":[107],"highly":[108],"optimized":[109],"kernels,":[110],"AutoChunk":[112,160],"(an":[113],"automated":[114],"search":[115],"algorithm":[116],"finds":[117],"the":[118,173,177],"best":[119],"chunk":[120],"strategy":[121],"reduce":[123,162],"peaks).":[125],"Experimental":[126],"results":[127],"show":[128],"that":[129],"FastFold":[130],"can":[131,161],"efficiently":[132],"scale":[133],"more":[135],"GPUs":[136],"using":[137],"DAP":[138],"reduces":[140],"overall":[141],"time":[143],"from":[144],"11":[145],"days":[146],"67":[148],"hours":[149],"achieves":[151],"7.5":[152],"~":[153],"9.5\u00d7":[154],"speedup":[155],"long-sequence":[157],"Furthermore,":[159],"cost":[164],"by":[165,170],"over":[166],"80%":[167],"during":[168,176],"automatically":[171],"partitioning":[172],"intermediate":[174],"tensors":[175],"computation.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}