{"id":"https://openalex.org/W4361732751","doi":"https://doi.org/10.1109/hpcc-dss-smartcity-dependsys57074.2022.00050","title":"MZ Core: An Enhanced Matrix Acceleration Engine for HPC/ AI Applications","display_name":"MZ Core: An Enhanced Matrix Acceleration Engine for HPC/ AI Applications","publication_year":2022,"publication_date":"2022-12-01","ids":{"openalex":"https://openalex.org/W4361732751","doi":"https://doi.org/10.1109/hpcc-dss-smartcity-dependsys57074.2022.00050"},"language":"en","primary_location":{"id":"doi:10.1109/hpcc-dss-smartcity-dependsys57074.2022.00050","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/hpcc-dss-smartcity-dependsys57074.2022.00050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 24th Int Conf on High Performance Computing &amp; Communications; 8th Int Conf on Data Science &amp; Systems; 20th Int Conf on Smart City; 8th Int Conf on Dependability in Sensor, Cloud &amp; Big Data Systems &amp; Application (HPCC/DSS/SmartCity/DependSys)","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/A5057268141","display_name":"Yasong Cao","orcid":"https://orcid.org/0009-0003-7683-989X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yasong Cao","raw_affiliation_strings":["College of Computer, National University of Defense Technology,Changsha,China","College of Computer, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101937502","display_name":"Mei Wen","orcid":"https://orcid.org/0000-0002-5875-3297"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mei Wen","raw_affiliation_strings":["College of Computer, National University of Defense Technology,Changsha,China","College of Computer, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037428152","display_name":"Junzhong Shen","orcid":"https://orcid.org/0000-0001-6233-6800"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junzhong Shen","raw_affiliation_strings":["College of Computer, National University of Defense Technology,Changsha,China","College of Computer, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320010","display_name":"Sheng Liu","orcid":"https://orcid.org/0000-0003-2731-9591"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Liu","raw_affiliation_strings":["College of Computer, National University of Defense Technology,Changsha,China","College of Computer, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076598663","display_name":"Zhi Wang","orcid":"https://orcid.org/0000-0003-0743-5544"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Wang","raw_affiliation_strings":["College of Computer, National University of Defense Technology,Changsha,China","College of Computer, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072361503","display_name":"Minjin Tang","orcid":"https://orcid.org/0009-0000-2254-4912"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minjin Tang","raw_affiliation_strings":["College of Computer, National University of Defense Technology,Changsha,China","College of Computer, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041134555","display_name":"Yahao Fang","orcid":"https://orcid.org/0000-0002-3234-5367"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yahao Fang","raw_affiliation_strings":["College of Computer, National University of Defense Technology,Changsha,China","College of Computer, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianchao Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianchao Yang","raw_affiliation_strings":["College of Computer, National University of Defense Technology,Changsha,China","College of Computer, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050796169","display_name":"Renyu Yang","orcid":"https://orcid.org/0000-0001-6334-4925"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renyu Yang","raw_affiliation_strings":["College of Computer, National University of Defense Technology,Changsha,China","College of Computer, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046780670","display_name":"Yuhan Kang","orcid":"https://orcid.org/0000-0001-5197-5025"},"institutions":[{"id":"https://openalex.org/I173759888","display_name":"Hunan Normal University","ror":"https://ror.org/053w1zy07","country_code":"CN","type":"education","lineage":["https://openalex.org/I173759888"]},{"id":"https://openalex.org/I3130607311","display_name":"Changsha Normal University","ror":"https://ror.org/02sqk3z62","country_code":"CN","type":"education","lineage":["https://openalex.org/I3130607311"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhan Kang","raw_affiliation_strings":["Hunan Normal University,Software Engineering,Changsha,China","Software Engineering, Hunan Normal University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan Normal University,Software Engineering,Changsha,China","institution_ids":["https://openalex.org/I173759888","https://openalex.org/I3130607311"]},{"raw_affiliation_string":"Software Engineering, Hunan Normal University, Changsha, China","institution_ids":["https://openalex.org/I173759888"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014208203","display_name":"Jiawei Fei","orcid":"https://orcid.org/0000-0001-9325-0516"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Fei","raw_affiliation_strings":["College of Computer, National University of Defense Technology,Changsha,China","College of Computer, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6877,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66081001,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"126","last_page":"134"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9988999962806702,"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":0.9988999962806702,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9973999857902527,"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/T11321","display_name":"Error Correcting Code Techniques","score":0.9943000078201294,"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/supercomputer","display_name":"Supercomputer","score":0.7318917512893677},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7235021591186523},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7216079235076904},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5152661800384521},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.4715464413166046},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.463382363319397},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4444194734096527},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4444190263748169},{"id":"https://openalex.org/keywords/systolic-array","display_name":"Systolic array","score":0.4328402876853943},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4240071475505829},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23126831650733948},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.17773476243019104},{"id":"https://openalex.org/keywords/very-large-scale-integration","display_name":"Very-large-scale integration","score":0.1324610710144043}],"concepts":[{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.7318917512893677},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7235021591186523},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7216079235076904},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5152661800384521},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.4715464413166046},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.463382363319397},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4444194734096527},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4444190263748169},{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.4328402876853943},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4240071475505829},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23126831650733948},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.17773476243019104},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.1324610710144043},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpcc-dss-smartcity-dependsys57074.2022.00050","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/hpcc-dss-smartcity-dependsys57074.2022.00050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 24th Int Conf on High Performance Computing &amp; Communications; 8th Int Conf on Data Science &amp; Systems; 20th Int Conf on Smart City; 8th Int Conf on Dependability in Sensor, Cloud &amp; Big Data Systems &amp; Application (HPCC/DSS/SmartCity/DependSys)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2017369466","https://openalex.org/W2067523571","https://openalex.org/W2346205343","https://openalex.org/W2589518372","https://openalex.org/W2763421725","https://openalex.org/W2765439756","https://openalex.org/W2945146780","https://openalex.org/W2953212265","https://openalex.org/W2977634443","https://openalex.org/W3023895731","https://openalex.org/W3212852614","https://openalex.org/W3213528054","https://openalex.org/W3217237164","https://openalex.org/W4281390154"],"related_works":["https://openalex.org/W2022229285","https://openalex.org/W46448156","https://openalex.org/W2283084692","https://openalex.org/W2130878144","https://openalex.org/W1582436825","https://openalex.org/W3172158163","https://openalex.org/W2150609674","https://openalex.org/W2138404091","https://openalex.org/W3034729708","https://openalex.org/W1996803181"],"abstract_inverted_index":{"The":[0,181],"convergence":[1],"of":[2,21,102,112,129,169,183],"High-Performance":[3],"Computing":[4],"(HPC)":[5],"and":[6,23,60,73,93,109,126,139,144,164,174],"Artificial":[7],"Intelligence":[8],"(AI)":[9],"has":[10],"become":[11],"a":[12,65,74],"promising":[13],"trend.":[14],"Due":[15],"to":[16,28,33,68,78],"the":[17,100,113,130,157,170,175],"different":[18],"computation":[19],"patterns":[20],"HPC":[22,59,92,131,158,171],"AI":[24,61,94],"applications,":[25],"it's":[26],"challenging":[27],"design":[29],"an":[30,45],"appropriate":[31],"architecture":[32],"balance":[34],"their":[35],"demand.":[36],"To":[37],"address":[38],"this,":[39],"we":[40],"propose":[41],"Matrix":[42,54],"Zone":[43],"(MZ),":[44],"enhanced":[46],"Systolic":[47],"Array-based":[48],"matrix":[49],"engine":[50],"that":[51,86,168],"accelerates":[52],"General":[53],"Multiplication":[55],"(GEMM)":[56],"for":[57,90],"both":[58,91],"applications.":[62],"We":[63,84],"develop":[64],"semi-memory":[66],"hierarchy":[67],"reduce":[69],"on-chip":[70],"area":[71,182],"consumption":[72],"data":[75],"stitching":[76],"method":[77],"support":[79],"multi-precision":[80],"floating-point":[81],"processing":[82],"efficiently.":[83],"demonstrate":[85],"MZ":[87,103,161,176,184],"improves":[88],"performance":[89,101,120],"applications":[95],"significantly.":[96],"For":[97,154],"AI-GEMM":[98],"tasks,":[99,156],"is":[104,121,141,162,185],"1.80X":[105],"(FP32),":[106],"15.11X":[107],"(FPI6),":[108],"3.48X":[110],"(FPI6-FP32)":[111],"TPU-like":[114],"model":[115],"on":[116,137,152,178],"average,":[117,138,179],"respectively.":[118,180],"MZ's":[119],"more":[122],"than":[123,167],"10.29X":[124],"(FP32)":[125,143],"26.37X":[127],"(FPI6)":[128,146],"core":[132,159,172],"in":[133,147],"Convolutional":[134],"(CONV)":[135],"layers":[136,151],"it":[140],"4.66X":[142],"20.75X":[145],"Fully":[148],"Connected":[149],"(FC)":[150],"average.":[153],"HPC-GEMM":[155],"+":[160],"6.28X":[163],"1.15X":[165],"faster":[166],"only":[173,177],"2.052":[186],"square":[187],"millimeters.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
