{"id":"https://openalex.org/W7225178563","doi":"https://doi.org/10.3390/electronics15215092","title":"Optimizing LSTM-Based AI Workloads on High-Performance Computing Systems: A Scalability and Performance Evaluation","display_name":"Optimizing LSTM-Based AI Workloads on High-Performance Computing Systems: A Scalability and Performance Evaluation","publication_year":2026,"publication_date":"2026-11-03","ids":{"openalex":"https://openalex.org/W7225178563","doi":"https://doi.org/10.3390/electronics15215092"},"language":"en","primary_location":{"id":"doi:10.3390/electronics15215092","doi":"https://doi.org/10.3390/electronics15215092","is_oa":true,"landing_page_url":"https://doi.org/10.3390/electronics15215092","pdf_url":null,"source":{"id":"https://openalex.org/S4210202905","display_name":"Electronics","issn_l":"2079-9292","issn":["2079-9292"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronics","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/electronics15215092","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099119764","display_name":"Tania Tanzin Hoque","orcid":"https://orcid.org/0000-0002-2004-5199","observed_orcids":["https://orcid.org/0000-0002-2004-5199"]},"institutions":[{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Tania Tanzin Hoque","raw_affiliation_strings":["INESC TEC\u2014Institute for Systems and Computer Engineering, Technology and Science, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal"],"raw_orcid":"https://orcid.org/0000-0002-2004-5199","affiliations":[{"raw_affiliation_string":"INESC TEC\u2014Institute for Systems and Computer Engineering, Technology and Science, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal","institution_ids":["https://openalex.org/I4210166615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049184710","display_name":"C\u00e1tia Silva","orcid":"https://orcid.org/0000-0001-8306-4568","observed_orcids":["https://orcid.org/0000-0001-8306-4568"]},"institutions":[{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"C\u00e1tia Silva","raw_affiliation_strings":["INESC TEC\u2014Institute for Systems and Computer Engineering, Technology and Science, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal"],"raw_orcid":"https://orcid.org/0000-0001-8306-4568","affiliations":[{"raw_affiliation_string":"INESC TEC\u2014Institute for Systems and Computer Engineering, Technology and Science, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal","institution_ids":["https://openalex.org/I4210166615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006485479","display_name":"Md. Tofael Ahmed","orcid":"https://orcid.org/0000-0003-3591-5844","observed_orcids":["https://orcid.org/0000-0003-3591-5844"]},"institutions":[{"id":"https://openalex.org/I21803372","display_name":"University of \u00c9vora","ror":"https://ror.org/02gyps716","country_code":"PT","type":"education","lineage":["https://openalex.org/I21803372"]},{"id":"https://openalex.org/I4405259988","display_name":"Center for Sci-Tech Research in EArth sysTem and Energy","ror":"https://ror.org/031e44z20","country_code":"PT","type":"education","lineage":["https://openalex.org/I4405259988"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Md Tofael Ahmed","raw_affiliation_strings":["Instrumentation & Control Laboratory, LAICA, Center for Sci-Tech Research in Earth System and Energy\u2014CREATE, University of Evora, 7000-671 Evora, Portugal"],"raw_orcid":"https://orcid.org/0000-0003-3591-5844","affiliations":[{"raw_affiliation_string":"Instrumentation & Control Laboratory, LAICA, Center for Sci-Tech Research in Earth System and Energy\u2014CREATE, University of Evora, 7000-671 Evora, Portugal","institution_ids":["https://openalex.org/I21803372","https://openalex.org/I4405259988"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160452042","display_name":"Tiago Pinto","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Tiago Pinto","raw_affiliation_strings":["INESC TEC\u2014Institute for Systems and Computer Engineering, Technology and Science, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INESC TEC\u2014Institute for Systems and Computer Engineering, Technology and Science, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal","institution_ids":["https://openalex.org/I4210166615"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006485479"],"corresponding_institution_ids":["https://openalex.org/I21803372","https://openalex.org/I4405259988"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2896},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2896},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.88237391,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":"21","first_page":"5092","last_page":"5092"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":9.999999747378752e-05,"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/T10101","display_name":"Cloud Computing and Resource Management","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/lstm-networks","display_name":"LSTM networks","score":0.7429999709129333},{"id":"https://openalex.org/keywords/time-series-forecasting","display_name":"time series forecasting","score":0.5429999828338623},{"id":"https://openalex.org/keywords/gpu-acceleration","display_name":"GPU acceleration","score":0.8090000152587891},{"id":"https://openalex.org/keywords/cpu-vs-gpu-performance-comparison","display_name":"CPU vs GPU performance comparison","score":0.7459999918937683},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"task parallelism","score":0.843999981880188},{"id":"https://openalex.org/keywords/heterogeneous-computing","display_name":"heterogeneous computing","score":0.6200000047683716},{"id":"https://openalex.org/keywords/high-performance-computing","display_name":"high-performance computing","score":0.7699999809265137},{"id":"https://openalex.org/keywords/synthetic-time-series-data","display_name":"synthetic time-series data","score":0.609000027179718},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.3840000033378601}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8770999908447266},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7515000104904175},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6680999994277954},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.6096000075340271},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.5550000071525574},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.49900001287460327},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4803999960422516},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45170000195503235},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4447999894618988},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.41269999742507935},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3928000032901764},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.3804999887943268},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35830000042915344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35530000925064087},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.30550000071525574},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.29649999737739563},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C2776834041","wikidata":"https://www.wikidata.org/wiki/Q25346349","display_name":"Execution model","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.25110000371932983},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3390/electronics15215092","doi":"https://doi.org/10.3390/electronics15215092","is_oa":true,"landing_page_url":"https://doi.org/10.3390/electronics15215092","pdf_url":null,"source":{"id":"https://openalex.org/S4210202905","display_name":"Electronics","issn_l":"2079-9292","issn":["2079-9292"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3390/electronics15215092","doi":"https://doi.org/10.3390/electronics15215092","is_oa":true,"landing_page_url":"https://doi.org/10.3390/electronics15215092","pdf_url":null,"source":{"id":"https://openalex.org/S4210202905","display_name":"Electronics","issn_l":"2079-9292","issn":["2079-9292"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronics","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1986303814","https://openalex.org/W2064675550","https://openalex.org/W2105524676","https://openalex.org/W2144499799","https://openalex.org/W2955325220","https://openalex.org/W3004140385","https://openalex.org/W3022643593","https://openalex.org/W3093933627","https://openalex.org/W3162956350","https://openalex.org/W4392365743","https://openalex.org/W4399564009","https://openalex.org/W4403963066","https://openalex.org/W4407276595","https://openalex.org/W4407596632","https://openalex.org/W4409797218","https://openalex.org/W4413283156","https://openalex.org/W4414055379","https://openalex.org/W7134181632"],"related_works":["https://openalex.org/W4395689810","https://openalex.org/W4229068602","https://openalex.org/W4399564009","https://openalex.org/W3110236750","https://openalex.org/W4412451596","https://openalex.org/W7124944680","https://openalex.org/W2964688222","https://openalex.org/W2922207751","https://openalex.org/W2951584298","https://openalex.org/W7167250661"],"abstract_inverted_index":{"Deep":[0],"learning":[1,169],"models":[2,60],"are":[3,27],"increasingly":[4],"used":[5,29],"for":[6,166],"time-series":[7],"applications;":[8],"however,":[9],"they":[10,35],"introduce":[11],"significant":[12],"computational":[13,107,179],"challenges,":[14],"particularly":[15],"when":[16],"handling":[17],"the":[18,56,67,126,136,140,148,152,159],"largest":[19],"workload":[20],"datasets.":[21],"Long":[22],"Short-Term":[23],"Memory":[24],"(LSTM)":[25],"networks":[26],"widely":[28],"in":[30,151,171],"time-":[31],"series":[32,173],"applications":[33],"because":[34],"can":[36],"learn":[37],"sequential":[38,70],"patterns":[39],"and":[40,51,71,87,163,187],"time-dependent":[41],"relationships":[42],"within":[43],"data.":[44],"Nevertheless,":[45],"LSTM":[46,59],"training":[47],"is":[48,181],"computationally":[49],"expensive":[50],"time-consuming.":[52],"This":[53],"work":[54],"investigates":[55],"performance":[57,131,180],"of":[58,69,161],"across":[61,125,135,194],"heterogeneous":[62,195],"computing":[63,165],"environments,":[64],"focusing":[65],"on":[66,78,184],"impact":[68],"parallel":[72,119,164],"execution":[73,120,123,145,188],"strategies.":[74],"Experiments":[75],"were":[76],"conducted":[77],"multiple":[79],"platforms":[80],"with":[81],"different":[82],"Central":[83],"Processing":[84,89],"Unit":[85,90],"(CPU)":[86],"Graphics":[88],"(GPU)":[91],"hardware":[92,185],"using":[93],"a":[94],"13-year":[95],"(4748":[96],"observations)":[97],"original":[98],"dataset":[99],"synthetically":[100],"expanded":[101],"to":[102,105],"47,480":[103],"observations":[104],"evaluate":[106],"workloads":[108],"rather":[109],"than":[110,147],"additional":[111],"real-world":[112],"observations.":[113],"The":[114,175],"results":[115],"show":[116],"that":[117,178],"task-level":[118],"reduces":[121],"wall-clock":[122],"time":[124,172],"tested":[127,137,153],"systems,":[128],"while":[129],"predictive":[130],"remains":[132,192],"broadly":[133],"comparable":[134],"configurations.":[138,154],"Furthermore,":[139],"GPU-based":[141],"implementation":[142,150],"achieved":[143],"lower":[144],"times":[146],"CPU-based":[149],"Overall,":[155],"this":[156],"study":[157],"highlights":[158],"importance":[160],"HPC":[162],"accelerating":[167],"deep":[168],"workflows":[170],"applications.":[174],"findings":[176],"confirm":[177],"highly":[182],"dependent":[183],"capabilities":[186],"strategies,":[189],"although":[190],"accuracy":[191],"stable":[193],"platforms.":[196]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-04T00:00:00"}