{"id":"https://openalex.org/W4409134128","doi":"https://doi.org/10.1109/tpds.2025.3557444","title":"Cube-fx: Mapping Taylor Expansion Onto Matrix Multiplier-Accumulators of Huawei Ascend AI Processors","display_name":"Cube-fx: Mapping Taylor Expansion Onto Matrix Multiplier-Accumulators of Huawei Ascend AI Processors","publication_year":2025,"publication_date":"2025-04-03","ids":{"openalex":"https://openalex.org/W4409134128","doi":"https://doi.org/10.1109/tpds.2025.3557444"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2025.3557444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2025.3557444","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","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/A5111472589","display_name":"Yifeng Tang","orcid":"https://orcid.org/0009-0009-0921-4930"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Yifeng Tang","raw_affiliation_strings":["Department of Computer Science, University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024438027","display_name":"Huaman Zhou","orcid":"https://orcid.org/0000-0002-6421-664X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaman Zhou","raw_affiliation_strings":["School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030309370","display_name":"Zhuoran Ji","orcid":"https://orcid.org/0000-0001-9767-2767"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuoran Ji","raw_affiliation_strings":["School of Cyber Science and Technology, Shandong University, Qingdao, Shandong, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Shandong University, Qingdao, Shandong, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036576232","display_name":"Cho-Li Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Cho-Li Wang","raw_affiliation_strings":["Department of Computer Science, University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5111472589"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":0.6973,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.69241212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"36","issue":"6","first_page":"1115","last_page":"1129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.15639999508857727,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.15639999508857727,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11347","display_name":"Neural Networks Stability and Synchronization","score":0.1500999927520752,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hydraulic-accumulator","display_name":"Hydraulic accumulator","score":0.8005589246749878},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7183898687362671},{"id":"https://openalex.org/keywords/taylor-series","display_name":"Taylor series","score":0.5533120036125183},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5313962697982788},{"id":"https://openalex.org/keywords/cube","display_name":"Cube (algebra)","score":0.5082921385765076},{"id":"https://openalex.org/keywords/multiplier","display_name":"Multiplier (economics)","score":0.47997570037841797},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.41598784923553467},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.40968868136405945},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.34949201345443726},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.12688007950782776},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10946667194366455},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1004418432712555}],"concepts":[{"id":"https://openalex.org/C19221803","wikidata":"https://www.wikidata.org/wiki/Q4668679","display_name":"Hydraulic accumulator","level":2,"score":0.8005589246749878},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7183898687362671},{"id":"https://openalex.org/C158946198","wikidata":"https://www.wikidata.org/wiki/Q131187","display_name":"Taylor series","level":2,"score":0.5533120036125183},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5313962697982788},{"id":"https://openalex.org/C53051483","wikidata":"https://www.wikidata.org/wiki/Q861555","display_name":"Cube (algebra)","level":2,"score":0.5082921385765076},{"id":"https://openalex.org/C124584101","wikidata":"https://www.wikidata.org/wiki/Q1053266","display_name":"Multiplier (economics)","level":2,"score":0.47997570037841797},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.41598784923553467},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.40968868136405945},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.34949201345443726},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.12688007950782776},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10946667194366455},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1004418432712555},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2025.3557444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2025.3557444","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5129669197","display_name":null,"funder_award_id":"62402282","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1493163583","https://openalex.org/W1522342588","https://openalex.org/W1651666045","https://openalex.org/W1989584178","https://openalex.org/W2115452265","https://openalex.org/W2157464008","https://openalex.org/W2165027654","https://openalex.org/W2417863416","https://openalex.org/W2606722458","https://openalex.org/W2786627679","https://openalex.org/W2901549770","https://openalex.org/W2982219368","https://openalex.org/W3043303806","https://openalex.org/W3090444025","https://openalex.org/W3133588229","https://openalex.org/W3139454985","https://openalex.org/W3157657667","https://openalex.org/W4213195788","https://openalex.org/W4225869830","https://openalex.org/W4250589301","https://openalex.org/W4285060868","https://openalex.org/W4285503968","https://openalex.org/W4297097426","https://openalex.org/W4318603197","https://openalex.org/W4376562663","https://openalex.org/W4380874786","https://openalex.org/W4381050415","https://openalex.org/W4385245566","https://openalex.org/W4386076236","https://openalex.org/W4386859300","https://openalex.org/W4390872931","https://openalex.org/W4400413567","https://openalex.org/W6858757186","https://openalex.org/W6863992277"],"related_works":["https://openalex.org/W3041640200","https://openalex.org/W2372015887","https://openalex.org/W2063667507","https://openalex.org/W2239322103","https://openalex.org/W4384824515","https://openalex.org/W1931693251","https://openalex.org/W2382515793","https://openalex.org/W2016198829","https://openalex.org/W2022586207","https://openalex.org/W2977611547"],"abstract_inverted_index":{"Taylor":[0,59,74,115,127],"expansion,":[1],"a":[2,123],"mature":[3],"method":[4],"for":[5,73,129],"function":[6,22],"evaluations":[7],"used":[8],"in":[9,141],"Artificial":[10],"Intelligence":[11],"(AI)":[12],"applications,":[13],"approximates":[14],"functions":[15,131],"with":[16,36,42,159,163],"polynomials.":[17],"In":[18,80],"addition":[19],"to":[20,32,86],"the":[21,43,47,51,57,70,87,94,103,107,111,137],"evaluations,":[23],"AI":[24,34,52,112],"applications":[25],"require":[26],"massive":[27],"matrix":[28,37,91,142,147],"multiplications,":[29],"inspiring":[30],"manufacturers":[31],"propose":[33],"processors":[35,53],"multiplier-accumulators":[38],"(MACs).":[39],"However,":[40],"compared":[41,158],"powerful":[44],"Matrix":[45,71,88,108,133],"MACs,":[46],"vectorized":[48,160,168],"units":[49],"of":[50,62,126],"cannot":[54],"efficiently":[55],"carry":[56],"existing":[58],"expansion":[60,75,116,128],"implementation":[61],"Single":[63],"Instruction":[64],"Multiple":[65],"Data":[66],"(SIMD)":[67],"parallelism.":[68],"Leveraging":[69],"MACs":[72,89,109],"becomes":[76],"an":[77],"ideal":[78],"direction.":[79],"previous":[81],"studies,":[82],"migrating":[83],"optimized":[84],"algorithms":[85],"requires":[90],"generation":[92,97],"during":[93],"runtime.":[95],"The":[96],"is":[98],"expensive":[99],"and":[100,139],"even":[101],"cancels":[102],"accelerations":[104],"brought":[105],"by":[106],"on":[110],"processors,":[113,152],"which":[114],"also":[117],"suffers.":[118],"This":[119],"article":[120],"presents":[121],"Cube-fx,":[122],"mapping":[124],"algorithm":[125],"multiple":[130],"onto":[132],"MACs.":[134],"Cube-fx":[135,153],"expresses":[136],"building":[138],"computation":[140],"multiplications":[143],"without":[144],"inefficient":[145],"dynamic":[146],"generation.":[148],"On":[149],"Huawei":[150],"Ascend":[151],"averagely":[154],"achieves":[155],"1.64\u00d7":[156],"speedups":[157],"Horner's":[161],"Method":[162],"56.38<inline-formula":[164],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[165],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[166],"notation=\"LaTeX\">$\\%$</tex-math></inline-formula>":[167],"operations":[169],"reduced.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}