{"id":"https://openalex.org/W4405756195","doi":"https://doi.org/10.1109/sc41406.2024.00084","title":"Exploring Efficient Partial Differential Equation Solution Using Speed Galerkin Transformer","display_name":"Exploring Efficient Partial Differential Equation Solution Using Speed Galerkin Transformer","publication_year":2024,"publication_date":"2024-11-17","ids":{"openalex":"https://openalex.org/W4405756195","doi":"https://doi.org/10.1109/sc41406.2024.00084"},"language":"en","primary_location":{"id":"doi:10.1109/sc41406.2024.00084","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sc41406.2024.00084","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SC24: International Conference for High Performance Computing, Networking, Storage and Analysis","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/A5100333854","display_name":"Xun Wang","orcid":"https://orcid.org/0000-0002-2741-433X"},"institutions":[{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Wang","raw_affiliation_strings":["China University of Petroleum (East China),Department of Computer Science and Technology,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Petroleum (East China),Department of Computer Science and Technology,Qingdao,China","institution_ids":["https://openalex.org/I4210162190"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zeyang Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyang Zhu","raw_affiliation_strings":["China University of Petroleum (East China),Department of Computer Science and Technology,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Petroleum (East China),Department of Computer Science and Technology,Qingdao,China","institution_ids":["https://openalex.org/I4210162190"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618126","display_name":"Xiangyu Meng","orcid":"https://orcid.org/0000-0001-7956-8499"},"institutions":[{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Meng","raw_affiliation_strings":["China University of Petroleum (East China),Department of Computer Science and Technology,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Petroleum (East China),Department of Computer Science and Technology,Qingdao,China","institution_ids":["https://openalex.org/I4210162190"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006420025","display_name":"Tao Song","orcid":"https://orcid.org/0000-0002-0130-3340"},"institutions":[{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Song","raw_affiliation_strings":["China University of Petroleum (East China),Department of Computer Science and Technology,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Petroleum (East China),Department of Computer Science and Technology,Qingdao,China","institution_ids":["https://openalex.org/I4210162190"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210162190"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20479062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.7242000102996826,"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"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.7242000102996826,"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"}},{"id":"https://openalex.org/T11263","display_name":"Electromagnetic Simulation and Numerical Methods","score":0.675599992275238,"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/T11205","display_name":"Numerical methods in inverse problems","score":0.6748999953269958,"subfield":{"id":"https://openalex.org/subfields/2610","display_name":"Mathematical Physics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/partial-differential-equation","display_name":"Partial differential equation","score":0.6817948222160339},{"id":"https://openalex.org/keywords/galerkin-method","display_name":"Galerkin method","score":0.5638266801834106},{"id":"https://openalex.org/keywords/first-order-partial-differential-equation","display_name":"First-order partial differential equation","score":0.5318061113357544},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49386316537857056},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4815576374530792},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3788270652294159},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3139626383781433},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.2854398488998413},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.2285155951976776},{"id":"https://openalex.org/keywords/finite-element-method","display_name":"Finite element method","score":0.2197267711162567},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.17824196815490723},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14514636993408203},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.10048717260360718},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08233943581581116}],"concepts":[{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.6817948222160339},{"id":"https://openalex.org/C186899397","wikidata":"https://www.wikidata.org/wiki/Q1491980","display_name":"Galerkin method","level":3,"score":0.5638266801834106},{"id":"https://openalex.org/C64057670","wikidata":"https://www.wikidata.org/wiki/Q4381442","display_name":"First-order partial differential equation","level":3,"score":0.5318061113357544},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49386316537857056},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4815576374530792},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3788270652294159},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3139626383781433},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.2854398488998413},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.2285155951976776},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.2197267711162567},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.17824196815490723},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14514636993408203},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.10048717260360718},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08233943581581116}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sc41406.2024.00084","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sc41406.2024.00084","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SC24: International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2070776117","https://openalex.org/W2082823632","https://openalex.org/W2896457183","https://openalex.org/W2991040477","https://openalex.org/W3042055468","https://openalex.org/W3115761617","https://openalex.org/W3129831491","https://openalex.org/W3138259231","https://openalex.org/W3138516171","https://openalex.org/W3163993681","https://openalex.org/W3171202467","https://openalex.org/W3200336025","https://openalex.org/W3207919916","https://openalex.org/W4205463297","https://openalex.org/W4214612132","https://openalex.org/W4223533630","https://openalex.org/W4224326349","https://openalex.org/W4252104256","https://openalex.org/W4285794944","https://openalex.org/W4313452913","https://openalex.org/W4321636575","https://openalex.org/W4321636820","https://openalex.org/W4322743280","https://openalex.org/W4385194941","https://openalex.org/W4385245566","https://openalex.org/W6778883912","https://openalex.org/W6779821917","https://openalex.org/W6780125659","https://openalex.org/W6784227514","https://openalex.org/W6788811087","https://openalex.org/W6797354866","https://openalex.org/W6799174632","https://openalex.org/W6811250563","https://openalex.org/W6838657745","https://openalex.org/W6850570602","https://openalex.org/W6853070603","https://openalex.org/W6861525120"],"related_works":["https://openalex.org/W2479314534","https://openalex.org/W2359206539","https://openalex.org/W2388355944","https://openalex.org/W2563073486","https://openalex.org/W2485938319","https://openalex.org/W2072438171","https://openalex.org/W1991459776","https://openalex.org/W3021320825","https://openalex.org/W4232257209","https://openalex.org/W4238318050"],"abstract_inverted_index":{"Fourier":[0],"Neural":[1],"Operator":[2],"(FNO)":[3],"has":[4],"been":[5],"proven":[6],"to":[7,44],"be":[8],"a":[9,57],"universal":[10],"and":[11,49,81,84,98,103,112,140],"effective":[12],"deep":[13],"learning":[14],"framework":[15],"capable":[16],"of":[17,32],"achieving":[18],"remarkable":[19],"accuracy":[20],"on":[21,149],"Partial":[22],"Differential":[23],"Equation":[24],"(PDE)":[25],"solution":[26],"problem.":[27],"However,":[28],"certain":[29],"key":[30],"components":[31],"emerging":[33],"FNO-based":[34],"models":[35],"cannot":[36],"leverage":[37],"hardware":[38],"potential,":[39],"which":[40],"makes":[41],"it":[42],"difficult":[43],"apply":[45],"in":[46,100],"high":[47,50,58],"resolution":[48],"realtime":[51],"demand":[52],"scenario.":[53],"This":[54],"paper":[55],"presents":[56],"optimized":[59],"model":[60,133],"called":[61],"Speed":[62,130],"Galerkin":[63,131],"Transformer,":[64],"including":[65],"multilevel":[66],"parallel":[67,147],"SliceK-SplitK-ReduceK":[68],"strategy":[69],"for":[70,78],"batched":[71,92],"skinny":[72],"matrix":[73],"multiplication,":[74],"memory":[75],"layout":[76],"optimization":[77,94],"QKV":[79],"matrices":[80],"positional":[82],"encodings":[83],"multi-head":[85],"layer":[86],"normalization":[87],"fusion,":[88],"as":[89,91],"well":[90],"transposition":[93],"with":[95],"strided":[96],"scattering":[97],"gathering":[99],"2D":[101],"FNO,":[102],"these":[104],"strategies":[105],"can":[106,134],"achieve":[107,135,141],"$10.29":[108],"\\mathrm{x},":[109],"4.41":[110],"\\mathrm{x}$":[111],"2.38":[113],"x":[114,138],"speedup":[115],"respectively":[116],"under":[117],"specific":[118],"configuration.":[119],"When":[120],"solving":[121],"the":[122,129],"Darcy":[123],"Flow":[124],"equation":[125],"at":[126],"512x512":[127],"resolution,":[128],"Transformer":[132],"about":[136],"1.72":[137],"speedup,":[139],"more":[142],"than":[143],"$\\mathbf{9":[144],"0":[145],"\\%}$":[146],"efficiency":[148],"8":[150],"GPUs.":[151]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}