{"id":"https://openalex.org/W4412610800","doi":"https://doi.org/10.1109/hpcc64274.2024.00072","title":"swYAKL: A Data Parallel Runtime on Manycore Architecture","display_name":"swYAKL: A Data Parallel Runtime on Manycore Architecture","publication_year":2024,"publication_date":"2024-12-13","ids":{"openalex":"https://openalex.org/W4412610800","doi":"https://doi.org/10.1109/hpcc64274.2024.00072"},"language":"en","primary_location":{"id":"doi:10.1109/hpcc64274.2024.00072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc64274.2024.00072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on High Performance Computing and Communications (HPCC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101814635","display_name":"Yanghui Ye","orcid":"https://orcid.org/0000-0002-5912-1910"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwei Ye","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101436158","display_name":"Junshi Chen","orcid":"https://orcid.org/0000-0002-6487-3658"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junshi Chen","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050039619","display_name":"Hong Qian","orcid":"https://orcid.org/0000-0002-3756-5019"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Qian","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kunxian Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kunxian Lin","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101951458","display_name":"Yuanhang Li","orcid":"https://orcid.org/0000-0002-3542-4466"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanhang Li","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085758579","display_name":"Hong An","orcid":"https://orcid.org/0000-0002-3900-3722"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong An","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43909087,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"490","last_page":"497"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.980400025844574,"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"}},"topics":[{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.980400025844574,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9782999753952026,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9352999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8279674053192139},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6800792217254639},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6194883584976196},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.504348635673523},{"id":"https://openalex.org/keywords/parallel-architecture","display_name":"Parallel architecture","score":0.47048476338386536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8279674053192139},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6800792217254639},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6194883584976196},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.504348635673523},{"id":"https://openalex.org/C2985918086","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel architecture","level":3,"score":0.47048476338386536},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpcc64274.2024.00072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc64274.2024.00072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on High Performance Computing and Communications (HPCC)","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":11,"referenced_works":["https://openalex.org/W2034761517","https://openalex.org/W2965444073","https://openalex.org/W3195293013","https://openalex.org/W3206784402","https://openalex.org/W4214645457","https://openalex.org/W4310887952","https://openalex.org/W4327930438","https://openalex.org/W6771627663","https://openalex.org/W6772200146","https://openalex.org/W6781061403","https://openalex.org/W6840226296"],"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/W2038503502","https://openalex.org/W2158228144","https://openalex.org/W206792560","https://openalex.org/W1965117583"],"abstract_inverted_index":{"The":[0,24],"traditional":[1],"architecture":[2,135],"of":[3,26,37,54,87,94,151,182,222],"supercomputers":[4],"comprises":[5],"a":[6,38,70,126,168,193],"control":[7],"unit":[8],"and":[9,65,96,115,136,156,158,163,192,214],"heterogeneous":[10,43],"accelerators":[11],"with":[12,57],"distinct":[13],"memory":[14],"spaces,":[15],"necessitating":[16],"developers":[17],"to":[18,32,49,81,101,105,112,118,139,177,206],"code":[19,48],"separately":[20],"for":[21,131,173,211],"each":[22],"accelerator.":[23],"notion":[25],"performance":[27,53,103,221],"portability":[28,104],"has":[29],"been":[30],"introduced":[31],"facilitate":[33],"the":[34,46,52,85,132,148,179,220,223],"swift":[35],"adaptation":[36],"singular":[39],"codebase":[40],"across":[41],"multiple":[42],"accelerators,":[44],"enabling":[45],"same":[47],"efficiently":[50],"harness":[51],"various":[55,212],"platforms":[56],"minimal":[58],"alterations.":[59],"Frameworks":[60],"such":[61],"as":[62],"Kokkos,":[63],"RAJA,":[64],"YAKL":[66,138],"accomplish":[67],"this":[68,140],"through":[69],"data":[71,127],"parallel":[72,128],"model,":[73],"primarily":[74],"targeting":[75],"SIMT":[76],"devices":[77],"but":[78],"also":[79],"applicable":[80],"SIMD":[82],"devices.":[83],"With":[84],"advent":[86],"manycore":[88,134],"architectures":[89],"that":[90,199],"provide":[91],"high":[92],"levels":[93],"parallelism":[95],"performance,":[97],"it":[98,218],"becomes":[99],"imperative":[100],"extend":[102],"these":[106],"architectures,":[107],"which":[108],"currently":[109],"require":[110],"users":[111],"manually":[113],"partition":[114],"map":[116],"tasks":[117],"fully":[119],"exploit":[120],"their":[121],"capabilities.":[122],"This":[123,144],"paper":[124],"introduces":[125],"programming":[129],"runtime":[130,145],"Sunway":[133],"adapts":[137],"platform,":[141],"termed":[142],"swYAKL.":[143],"capitalizes":[146],"on":[147,208],"computational":[149,190],"characteristics":[150],"Sunway,":[152],"including":[153],"task":[154,170],"division":[155,171],"mapping,":[157],"supports":[159],"Sunway\u2019s":[160,183,209],"CPE":[161],"LDM":[162],"native":[164],"vectorization.":[165],"It":[166],"employs":[167],"specialized":[169],"method":[172],"multi-dimensional":[174],"stencil":[175],"kernels":[176,191],"leverage":[178],"DMA":[180],"capabilities":[181],"CPE.":[184],"Performance":[185],"evaluations":[186],"using":[187],"several":[188],"common":[189],"proxy":[194],"application":[195],"named":[196],"miniWeather":[197],"indicate":[198],"swYAKL":[200],"achieves":[201],"speedups":[202],"exceeding":[203],"100x":[204],"compared":[205],"execution":[207],"MPE":[210],"workloads,":[213],"under":[215],"specific":[216],"conditions,":[217],"surpasses":[219],"NVIDIA":[224],"A100":[225],"GPU.":[226]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
