{"id":"https://openalex.org/W4416873842","doi":"https://doi.org/10.1109/sbac-padw69789.2025.00014","title":"Efficient SIMD and Shared-Memory Parallelization of 3D Acoustic Wave Propagation Simulation","display_name":"Efficient SIMD and Shared-Memory Parallelization of 3D Acoustic Wave Propagation Simulation","publication_year":2025,"publication_date":"2025-10-28","ids":{"openalex":"https://openalex.org/W4416873842","doi":"https://doi.org/10.1109/sbac-padw69789.2025.00014"},"language":"en","primary_location":{"id":"doi:10.1109/sbac-padw69789.2025.00014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sbac-padw69789.2025.00014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/SBC 37th International Symposium on Computer Architecture and High Performance Computing Workshops (SBAC-PADW)","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/A5120531939","display_name":"Chahin\u00e8ze Ztoti","orcid":null},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Chahin\u00e8ze Ztoti","raw_affiliation_strings":["Universit&#x00E9; Paris-Saclay,Saclay,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E9; Paris-Saclay,Saclay,France","institution_ids":["https://openalex.org/I277688954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057912061","display_name":"Claude Tadonki","orcid":"https://orcid.org/0000-0003-1194-6400"},"institutions":[{"id":"https://openalex.org/I4210115519","display_name":"Centre de Recherche en Informatique","ror":"https://ror.org/020cdve92","country_code":"FR","type":"facility","lineage":["https://openalex.org/I190752583","https://openalex.org/I2746051580","https://openalex.org/I4210091621","https://openalex.org/I4210115519","https://openalex.org/I70768539"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Claude Tadonki","raw_affiliation_strings":["Mines Paris - PSL,Centre de Recherche en Informatique (CRI),Fontainebleau,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mines Paris - PSL,Centre de Recherche en Informatique (CRI),Fontainebleau,France","institution_ids":["https://openalex.org/I4210115519"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092356330","display_name":"Roblex Nana Tchakoute","orcid":"https://orcid.org/0009-0009-8636-8466"},"institutions":[{"id":"https://openalex.org/I4210115519","display_name":"Centre de Recherche en Informatique","ror":"https://ror.org/020cdve92","country_code":"FR","type":"facility","lineage":["https://openalex.org/I190752583","https://openalex.org/I2746051580","https://openalex.org/I4210091621","https://openalex.org/I4210115519","https://openalex.org/I70768539"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Roblex Nana Tchakoute","raw_affiliation_strings":["Mines Paris - PSL,Centre de Recherche en Informatique (CRI),Fontainebleau,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mines Paris - PSL,Centre de Recherche en Informatique (CRI),Fontainebleau,France","institution_ids":["https://openalex.org/I4210115519"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004580808","display_name":"Herv\u00e9 Chauris","orcid":"https://orcid.org/0000-0001-6652-0381"},"institutions":[{"id":"https://openalex.org/I4210148040","display_name":"Centre de G\u00e9osciences","ror":"https://ror.org/03kc13263","country_code":"FR","type":"facility","lineage":["https://openalex.org/I190752583","https://openalex.org/I2746051580","https://openalex.org/I4210091621","https://openalex.org/I4210148040","https://openalex.org/I70768539"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Herv\u00e9 Chauris","raw_affiliation_strings":["Mines Paris - PSL,Geosciences,Fontainebleau,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mines Paris - PSL,Geosciences,Fontainebleau,France","institution_ids":["https://openalex.org/I4210148040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32144225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"33","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11263","display_name":"Electromagnetic Simulation and Numerical Methods","score":0.15700000524520874,"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"}},"topics":[{"id":"https://openalex.org/T11263","display_name":"Electromagnetic Simulation and Numerical Methods","score":0.15700000524520874,"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/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.11349999904632568,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.10249999910593033,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/domain-decomposition-methods","display_name":"Domain decomposition methods","score":0.5778999924659729},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5778999924659729},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5320000052452087},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.5239999890327454},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.5080000162124634},{"id":"https://openalex.org/keywords/code-refactoring","display_name":"Code refactoring","score":0.5026000142097473},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4945000112056732},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4790000021457672},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.44749999046325684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.830299973487854},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7102000117301941},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5778999924659729},{"id":"https://openalex.org/C198880260","wikidata":"https://www.wikidata.org/wiki/Q5289813","display_name":"Domain decomposition methods","level":3,"score":0.5778999924659729},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5320000052452087},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.5239999890327454},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.5080000162124634},{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.5026000142097473},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4945000112056732},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4790000021457672},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44749999046325684},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4122999906539917},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.3919000029563904},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.31540000438690186},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2969000041484833},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C43173174","wikidata":"https://www.wikidata.org/wiki/Q2646942","display_name":"Regular grid","level":3,"score":0.2888000011444092},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.28060001134872437},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C164833996","wikidata":"https://www.wikidata.org/wiki/Q2323839","display_name":"Automatic parallelization","level":3,"score":0.2757999897003174},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.26969999074935913},{"id":"https://openalex.org/C31487907","wikidata":"https://www.wikidata.org/wiki/Q1154597","display_name":"Polygon mesh","level":2,"score":0.26440000534057617}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/sbac-padw69789.2025.00014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sbac-padw69789.2025.00014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/SBC 37th International Symposium on Computer Architecture and High Performance Computing Workshops (SBAC-PADW)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-05393904v1","is_oa":false,"landing_page_url":"https://minesparis-psl.hal.science/hal-05393904","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2025 IEEE/SBC 37th International Symposium on Computer Architecture and High Performance Computing Workshops (SBAC-PADW), Oct 2025, Bonito, Brazil. pp.33-40, &#x27E8;10.1109/SBAC-PADW69789.2025.00014&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W562359334","https://openalex.org/W1986778827","https://openalex.org/W2003519051","https://openalex.org/W2053748859","https://openalex.org/W2075626677","https://openalex.org/W2078465958","https://openalex.org/W2100245965","https://openalex.org/W2108113382","https://openalex.org/W2113190809","https://openalex.org/W2154078685","https://openalex.org/W2187442180","https://openalex.org/W2220375742","https://openalex.org/W2317439899","https://openalex.org/W2617091226","https://openalex.org/W2621264743","https://openalex.org/W2625171569","https://openalex.org/W2735310121","https://openalex.org/W2788818070","https://openalex.org/W2899293960","https://openalex.org/W2912052494","https://openalex.org/W2939971271","https://openalex.org/W2968094316","https://openalex.org/W3010498773","https://openalex.org/W3029772794","https://openalex.org/W3104055803","https://openalex.org/W3125050592","https://openalex.org/W3144543762","https://openalex.org/W3164435152","https://openalex.org/W3210300097","https://openalex.org/W4247867768","https://openalex.org/W4286715397","https://openalex.org/W4360613267","https://openalex.org/W4391594491","https://openalex.org/W4412071373","https://openalex.org/W4413340926"],"related_works":[],"abstract_inverted_index":{"We":[0,101],"are":[1],"interested":[2],"in":[3,84],"the":[4,30,43,80,85,103,113,117,134,152,171,175,185],"implementation":[5,188],"of":[6,14,71,87,98,106,116,130,136,174,189],"a":[7,11,19,25,34,50,56,68,90,96,137,165],"mesh-based":[8],"modeling":[9],"for":[10,181],"numerical":[12],"simulation":[13],"acoustic":[15],"wave":[16],"propagation.":[17],"Considering":[18],"2D":[20],"validated":[21],"version,":[22],"we":[23,126],"derive":[24],"3D":[26],"design":[27,186],"by":[28,55],"extending":[29],"spatial":[31,44],"domain":[32,81,195],"with":[33,67,148],"third":[35],"dimension.":[36],"The":[37],"dimension":[38],"n":[39],"here":[40],"refers":[41],"to":[42,154,170],"domain,":[45],"which":[46,74],"is":[47,184],"modeled":[48],"as":[49],"n-dimensional":[51],"mesh":[52],"grid":[53],"augmented":[54],"time":[57],"axis.":[58],"With":[59],"this":[60,182],"4D":[61],"model,":[62],"considering":[63,112],"large-scale":[64],"scenarios":[65,150],"goes":[66],"significant":[69],"demand":[70],"memory":[72,92,107,191],"space,":[73],"can":[75],"therefore":[76],"justify":[77],"delving":[78],"into":[79],"decomposition":[82],"strategy":[83],"perspective":[86],"running":[88],"on":[89,164],"distributed":[91,190],"parallel":[93,192],"machine":[94],"or":[95],"cluster":[97],"standard":[99],"processors.":[100],"investigate":[102],"required":[104],"volume":[105],"and":[108,124,144,158,187,197],"make":[109],"it":[110],"minimal":[111],"specific":[114,166],"rules":[115],"simulation.":[118],"Next,":[119],"beside":[120],"ordinary":[121],"code":[122],"refactoring":[123],"optimization,":[125],"explore":[127],"all":[128],"levers":[129],"computing":[131],"power":[132],"at":[133],"level":[135],"single":[138],"processor,":[139],"more":[140],"precisely":[141],"multi-thread":[142],"parallelism":[143],"SIMD.":[145],"Experimental":[146],"results":[147],"various":[149],"illustrate":[151],"possibility":[153],"handle":[155],"bigger":[156],"instances":[157],"an":[159],"impressive":[160],"global":[161],"speedup":[162],"(\u00d720":[163],"execution":[167],"scenario)":[168],"compared":[169],"original":[172],"version":[173,193],"code.":[176],"A":[177],"natural":[178],"step":[179],"further":[180],"work":[183],"through":[194],"decomposition,":[196],"GPU":[198],"acceleration.":[199]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-01T00:00:00"}
