{"id":"https://openalex.org/W3196932171","doi":"https://doi.org/10.1145/3462676.3462680","title":"Accelerating Matrix Power Operations with GPUs","display_name":"Accelerating Matrix Power Operations with GPUs","publication_year":2021,"publication_date":"2021-04-09","ids":{"openalex":"https://openalex.org/W3196932171","doi":"https://doi.org/10.1145/3462676.3462680","mag":"3196932171"},"language":"en","primary_location":{"id":"doi:10.1145/3462676.3462680","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3462676.3462680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 4th International Conference on Electronics, Communications and Control Engineering","raw_type":"proceedings-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/A5074858946","display_name":"Lezhou Wu","orcid":"https://orcid.org/0000-0002-9432-9573"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lezhou Wu","raw_affiliation_strings":["College of Information Science and Engineering, Northeastern University, Shenyang, Liaoning Province, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Northeastern University, Shenyang, Liaoning Province, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5074858946"],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14751507,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9961000084877014,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9961000084877014,"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":0.9915000200271606,"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":0.9722999930381775,"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/cuda","display_name":"CUDA","score":0.9481607675552368},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8147026896476746},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8016680479049683},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7743774652481079},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6143531203269958},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.49823713302612305},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.45371660590171814},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4107828140258789},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.41004878282546997},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3749518394470215},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19333800673484802},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.16945326328277588},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.10889831185340881}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.9481607675552368},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8147026896476746},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8016680479049683},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7743774652481079},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6143531203269958},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.49823713302612305},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.45371660590171814},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4107828140258789},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.41004878282546997},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3749518394470215},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19333800673484802},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.16945326328277588},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.10889831185340881},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3462676.3462680","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3462676.3462680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 4th International Conference on Electronics, Communications and Control Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2086105136","https://openalex.org/W2087507944","https://openalex.org/W2144511445","https://openalex.org/W2769151032"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"Many-core":[0],"framework,":[1],"represented":[2],"by":[3,176],"Graphic":[4],"Processing":[5],"Unit":[6],"(GPU),":[7],"has":[8],"been":[9],"becoming":[10],"more":[11,33],"popular":[12],"in":[13,52,72,134,210],"scientific":[14],"computing":[15],"and":[16,19,48,57,76,89,110,124,132,150,213],"data":[17,211],"analysis,":[18],"Compute":[20],"Unified":[21],"Device":[22],"Architecture":[23],"(CUDA)":[24],"allows":[25],"developers":[26],"to":[27,98],"carry":[28],"out":[29,118],"computation":[30,47],"on":[31,63,119],"GPUs":[32,88],"conveniently.":[34],"Matrix":[35],"operation":[36,67],"is":[37,85,130,143,148,154,185],"one":[38],"of":[39,45,83,166,183,192,197,204],"the":[40,81,101,139,145,151,160,171,181,190,195,205],"most":[41],"important":[42],"application":[43],"scenarios":[44],"GPU":[46,140,214],"CUDA,":[49],"widely":[50],"appearing":[51],"domains":[53],"like":[54],"graph":[55],"applications":[56],"artificial":[58],"intelligence.":[59],"This":[60],"paper":[61],"focuses":[62],"accelerating":[64],"matrix":[65,104,107],"power":[66,193],"(MPO)":[68],"process,":[69],"which":[70],"appears":[71],"many":[73],"engineering":[74],"problems":[75],"may":[77],"be":[78,200],"time-consuming":[79],"when":[80],"scale":[82],"matrixes":[84],"large,":[86],"with":[87,170,189],"CUDA.":[90],"In":[91],"this":[92],"paper,":[93],"three":[94,158],"techniques":[95],"are":[96],"used":[97],"speed":[99],"up":[100],"MPO":[102,161],"process:":[103],"parallel":[105,108],"reduction,":[106],"multiplication":[109,173],"CUDA":[111,146],"dynamic":[112],"parallelism.":[113],"The":[114,128],"experiments":[115],"were":[116],"carried":[117],"NVIDIA":[120],"RTX":[121],"2080":[122],"Super":[123],"Intel(R)":[125],"Core(TM)":[126],"i7-10750H.":[127],"code":[129,182],"compiled":[131],"executed":[133,175],"Visual":[135],"Studio":[136],"2019":[137],"community,":[138],"driver":[141],"version":[142,147,153],"461.40,":[144],"11.1,":[149],"NVCC":[152],"11.1.74.":[155],"With":[156],"all":[157],"techniques,":[159],"process":[162,174],"can":[163,199],"get":[164],"hundreds":[165],"times":[167],"speedup":[168],"compared":[169],"sequential":[172],"Eigen":[177],"library,":[178],"even":[179,201],"though":[180],"algorithm":[184,198],"hardly":[186],"optimized.":[187],"Moreover,":[188],"number":[191],"increasing,":[194],"efficiency":[196],"higher":[202],"because":[203],"relatively":[206],"fixed":[207],"time":[208],"consumed":[209],"transmission":[212],"memory":[215],"allocation.":[216]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}