{"id":"https://openalex.org/W4386348101","doi":"https://doi.org/10.1145/3581784.3607073","title":"Hanayo: Harnessing Wave-like Pipeline Parallelism for Enhanced Large Model Training Efficiency","display_name":"Hanayo: Harnessing Wave-like Pipeline Parallelism for Enhanced Large Model Training Efficiency","publication_year":2023,"publication_date":"2023-10-30","ids":{"openalex":"https://openalex.org/W4386348101","doi":"https://doi.org/10.1145/3581784.3607073"},"language":"en","primary_location":{"id":"doi:10.1145/3581784.3607073","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581784.3607073","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3581784.3607073","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101924544","display_name":"Ziming Liu","orcid":"https://orcid.org/0009-0009-3355-6770"},"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":"Ziming Liu","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0009-3355-6770","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","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":["School of Computing, National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7966-2941","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101874740","display_name":"Haotian Zhou","orcid":"https://orcid.org/0009-0008-1704-7354"},"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":"Haotian Zhou","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0008-1704-7354","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"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":["School of Computing, National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-2816-4384","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9977999925613403,"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":0.9977999925613403,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9976999759674072,"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/T10028","display_name":"Topic Modeling","score":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.863251268863678},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.8368836641311646},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.6922607421875},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.670656681060791},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.498305082321167},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4877406060695648},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.46951979398727417},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.43446481227874756},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.36846429109573364},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14718523621559143},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10494410991668701}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.863251268863678},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.8368836641311646},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.6922607421875},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.670656681060791},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.498305082321167},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4877406060695648},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.46951979398727417},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.43446481227874756},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36846429109573364},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14718523621559143},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10494410991668701},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3581784.3607073","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581784.3607073","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2308.15762","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.15762","pdf_url":"https://arxiv.org/pdf/2308.15762","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3581784.3607073","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581784.3607073","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320320698","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1565253099","https://openalex.org/W1967810725","https://openalex.org/W2338908902","https://openalex.org/W2612387305","https://openalex.org/W2734941459","https://openalex.org/W2763421725","https://openalex.org/W2766736793","https://openalex.org/W2896457183","https://openalex.org/W2962747323","https://openalex.org/W2962950660","https://openalex.org/W2967558351","https://openalex.org/W2973727699","https://openalex.org/W2980268386","https://openalex.org/W2991040477","https://openalex.org/W3020605687","https://openalex.org/W3038581078","https://openalex.org/W3081168214","https://openalex.org/W3094502228","https://openalex.org/W3099748883","https://openalex.org/W3129831491","https://openalex.org/W3137550677","https://openalex.org/W3138516171","https://openalex.org/W3156643189","https://openalex.org/W3159351344","https://openalex.org/W3164253193","https://openalex.org/W3174394143","https://openalex.org/W3180473732","https://openalex.org/W3189259198","https://openalex.org/W3204998121","https://openalex.org/W3205803342","https://openalex.org/W3206832494","https://openalex.org/W3213938204","https://openalex.org/W4221167110","https://openalex.org/W4286987939","https://openalex.org/W4287235399","https://openalex.org/W4287756266","https://openalex.org/W4288089799","https://openalex.org/W4288094025","https://openalex.org/W4292779060","https://openalex.org/W4293775467","https://openalex.org/W4294433898","https://openalex.org/W4295312788","https://openalex.org/W4385245566","https://openalex.org/W4386709668"],"related_works":["https://openalex.org/W2359178629","https://openalex.org/W4380433113","https://openalex.org/W4386072068","https://openalex.org/W252339960","https://openalex.org/W2375218795","https://openalex.org/W2390529043","https://openalex.org/W2378320433","https://openalex.org/W2358343511","https://openalex.org/W2051877971","https://openalex.org/W1970117064"],"abstract_inverted_index":{"Large-scale":[0],"language":[1],"models":[2],"have":[3],"become":[4],"increasingly":[5],"challenging":[6],"and":[7,46,70,94,98],"expensive":[8],"to":[9,23,55,80,103,108,116],"train.":[10],"Among":[11],"various":[12],"methods":[13],"addressing":[14],"this":[15],"issue,":[16],"Pipeline":[17],"Parallelism":[18],"has":[19],"been":[20],"widely":[21],"employed":[22],"accommodate":[24],"massive":[25],"model":[26,81],"weights":[27],"within":[28],"limited":[29],"GPU":[30],"memory.":[31],"This":[32],"paper":[33],"introduces":[34],"Hanayo,":[35],"a":[36,43,50,109],"wave-like":[37],"pipeline":[38,52,60,68],"parallelism":[39],"strategy":[40,61],"that":[41],"boasts":[42],"concise":[44],"structure":[45],"practical":[47],"applicability,":[48],"alongside":[49],"high-performance":[51],"execution":[53],"runtime":[54],"tackle":[56],"the":[57,65,117],"challenges":[58],"of":[59,67],"implementation.":[62],"Hanayo":[63],"mitigates":[64],"issues":[66],"bubbles":[69],"excessive":[71],"memory":[72],"consumption":[73],"prevalent":[74],"in":[75,84,113],"existing":[76],"schemes,":[77],"without":[78],"resorting":[79],"duplicates":[82],"as":[83],"Chimera.":[85],"Our":[86],"evaluation,":[87],"conducted":[88],"on":[89],"four":[90],"distinct":[91],"computing":[92],"clusters":[93],"involving":[95],"both":[96],"GPT-like":[97],"BERT-like":[99],"architectures":[100],"with":[101],"up":[102,107],"32":[104],"GPUs,":[105],"demonstrates":[106],"30.4":[110],"%":[111],"increase":[112],"throughput":[114],"compared":[115],"state-of-the-art":[118],"approach.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2023-09-02T00:00:00"}