{"id":"https://openalex.org/W4321222463","doi":"https://doi.org/10.1145/3584373","title":"A Heterogeneous Parallel Computing Approach Optimizing SpTTM on CPU-GPU via GCN","display_name":"A Heterogeneous Parallel Computing Approach Optimizing SpTTM on CPU-GPU via GCN","publication_year":2023,"publication_date":"2023-02-17","ids":{"openalex":"https://openalex.org/W4321222463","doi":"https://doi.org/10.1145/3584373"},"language":"en","primary_location":{"id":"doi:10.1145/3584373","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3584373","pdf_url":null,"source":{"id":"https://openalex.org/S2483380313","display_name":"ACM Transactions on Parallel Computing","issn_l":"2329-4949","issn":["2329-4949","2329-4957"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Parallel Computing","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/A5100383993","display_name":"Haotian Wang","orcid":"https://orcid.org/0000-0002-0086-6301"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haotian Wang","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, China"],"raw_orcid":"https://orcid.org/0000-0002-0086-6301","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016247312","display_name":"Wangdong Yang","orcid":"https://orcid.org/0000-0003-2681-7898"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangdong Yang","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, China"],"raw_orcid":"https://orcid.org/0000-0003-2681-7898","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047441166","display_name":"Renqiu Ouyang","orcid":"https://orcid.org/0000-0002-8712-4561"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renqiu Ouyang","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, China"],"raw_orcid":"https://orcid.org/0000-0002-8712-4561","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066849666","display_name":"\u6804\u5fb3 \u5b8d\u6238","orcid":"https://orcid.org/0000-0003-4174-1326"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Hu","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, China"],"raw_orcid":"https://orcid.org/0000-0003-4174-1326","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078793726","display_name":"Kenli Li","orcid":"https://orcid.org/0000-0002-2635-7716"},"institutions":[{"id":"https://openalex.org/I1327163397","display_name":"State University of New York","ror":"https://ror.org/01q1z8k08","country_code":"US","type":"education","lineage":["https://openalex.org/I1327163397"]},{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Kenli Li","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, China","Department of Computer Science, State University of New York, USA and College of Computer Science and Electronic Engineering, Hunan University, China"],"raw_orcid":"https://orcid.org/0000-0002-2635-7716","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"Department of Computer Science, State University of New York, USA and College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I1327163397","https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087894632","display_name":"Keqin Li","orcid":"https://orcid.org/0000-0001-5224-4048"},"institutions":[{"id":"https://openalex.org/I1327163397","display_name":"State University of New York","ror":"https://ror.org/01q1z8k08","country_code":"US","type":"education","lineage":["https://openalex.org/I1327163397"]},{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Keqin Li","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, China","Department of Computer Science, State University of New York, USA and College of Computer Science and Electronic Engineering, Hunan University, China"],"raw_orcid":"https://orcid.org/0000-0001-5224-4048","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"Department of Computer Science, State University of New York, USA and College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I1327163397","https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9679,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.68261563,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"10","issue":"2","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9933000206947327,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9599000215530396,"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":0.8422904014587402},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6928676962852478},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6818310022354126},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.5981301665306091},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5840362310409546},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5499444007873535},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.53776615858078},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5229045748710632},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.46513858437538147},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4024207890033722},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3565586805343628},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.11282268166542053},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09314721822738647}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8422904014587402},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6928676962852478},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6818310022354126},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.5981301665306091},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5840362310409546},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5499444007873535},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.53776615858078},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5229045748710632},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.46513858437538147},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4024207890033722},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3565586805343628},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.11282268166542053},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09314721822738647},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3584373","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3584373","pdf_url":null,"source":{"id":"https://openalex.org/S2483380313","display_name":"ACM Transactions on Parallel Computing","issn_l":"2329-4949","issn":["2329-4949","2329-4957"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Parallel Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1166995285","display_name":null,"funder_award_id":"61872127 and 61751204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8332549413","display_name":null,"funder_award_id":"2020YFB2104000","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W182691100","https://openalex.org/W1511885491","https://openalex.org/W1825959699","https://openalex.org/W2004642969","https://openalex.org/W2006973305","https://openalex.org/W2024165284","https://openalex.org/W2040836065","https://openalex.org/W2046808168","https://openalex.org/W2082238959","https://openalex.org/W2091883426","https://openalex.org/W2105724942","https://openalex.org/W2108138101","https://openalex.org/W2116721352","https://openalex.org/W2135496322","https://openalex.org/W2245094585","https://openalex.org/W2521497392","https://openalex.org/W2523567745","https://openalex.org/W2616934551","https://openalex.org/W2788264912","https://openalex.org/W2885436857","https://openalex.org/W2886162485","https://openalex.org/W2886632348","https://openalex.org/W2914086833","https://openalex.org/W2924444427","https://openalex.org/W2951178714","https://openalex.org/W2952598959","https://openalex.org/W2971508019","https://openalex.org/W2986686333","https://openalex.org/W3003516456","https://openalex.org/W3020586295","https://openalex.org/W3022703302","https://openalex.org/W3033688252","https://openalex.org/W3094435130","https://openalex.org/W3099762987","https://openalex.org/W3129727110","https://openalex.org/W3173953560","https://openalex.org/W3174469048","https://openalex.org/W3175189837","https://openalex.org/W3177185021","https://openalex.org/W3183647566","https://openalex.org/W3200803154","https://openalex.org/W4206958722","https://openalex.org/W4223467872","https://openalex.org/W4241741271","https://openalex.org/W4287542618","https://openalex.org/W4293024985","https://openalex.org/W4312191310","https://openalex.org/W4387839549","https://openalex.org/W6690272936","https://openalex.org/W6712694631","https://openalex.org/W6810139970"],"related_works":["https://openalex.org/W2983282793","https://openalex.org/W3012895752","https://openalex.org/W3000570965","https://openalex.org/W2052993554","https://openalex.org/W2046125858","https://openalex.org/W2473478803","https://openalex.org/W2030992542","https://openalex.org/W2003735","https://openalex.org/W2729363167","https://openalex.org/W2060611139"],"abstract_inverted_index":{"Sparse":[0],"Tensor-Times-Matrix":[1],"(SpTTM)":[2],"is":[3],"the":[4,54,60,66,70,73,76,116],"core":[5],"calculation":[6],"in":[7,48],"tensor":[8,85,103],"analysis.":[9],"The":[10,126],"sparse":[11,50,86,104],"distributions":[12],"of":[13,62,75,120,140],"different":[14,49],"tensors":[15],"vary":[16],"greatly,":[17],"which":[18],"poses":[19],"a":[20,42,81,93,101,148],"big":[21],"challenge":[22],"to":[23,64,83,99,114,144],"designing":[24],"efficient":[25],"and":[26,40,58,72,91,118],"general":[27],"SpTTM.":[28,125],"In":[29],"this":[30],"paper,":[31],"we":[32,107],"describe":[33,84],"SpTTM":[34,47,134],"on":[35,147],"CPU-GPU":[36,149],"heterogeneous":[37,77,150],"hybrid":[38],"systems":[39],"give":[41],"parallel":[43],"execution":[44],"strategy":[45],"for":[46],"formats.":[51],"We":[52,79],"analyze":[53],"theoretical":[55],"computer":[56],"powers":[57],"estimate":[59],"number":[61],"tasks":[63],"achieve":[65,136],"load":[67],"balancing":[68],"between":[69],"CPU":[71],"GPU":[74],"systems.":[78],"discuss":[80],"method":[82],"structure":[87,90],"by":[88],"graph":[89,95],"design":[92],"new":[94],"neural":[96],"network":[97],"SPT-GCN":[98],"select":[100],"suitable":[102],"format.":[105],"Furthermore,":[106],"perform":[108],"extensive":[109],"experiments":[110],"using":[111],"real":[112],"datasets":[113],"demonstrate":[115],"advantages":[117],"efficiency":[119],"our":[121,131],"proposed":[122],"input-aware":[123,132],"slice-wise":[124,133],"experimental":[127],"results":[128],"show":[129],"that":[130],"can":[135],"an":[137],"average":[138],"speedup":[139],"1.310":[141],"\u00d7":[142],"compared":[143],"ParTI!":[145],"library":[146],"system.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}