{"id":"https://openalex.org/W4319870574","doi":"https://doi.org/10.1145/3543622.3573160","title":"LAWS: Large-Scale Accelerated Wave Simulations on FPGAs","display_name":"LAWS: Large-Scale Accelerated Wave Simulations on FPGAs","publication_year":2023,"publication_date":"2023-02-10","ids":{"openalex":"https://openalex.org/W4319870574","doi":"https://doi.org/10.1145/3543622.3573160"},"language":"en","primary_location":{"id":"doi:10.1145/3543622.3573160","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543622.3573160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"},"type":"conference-abstract","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/A5062029228","display_name":"Dimitrios Gourounas","orcid":"https://orcid.org/0000-0002-5011-9646"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimitrios Gourounas","raw_affiliation_strings":["The University of Texas at Austin, Austin, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-5011-9646","affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019583227","display_name":"Bagus Hanindhito","orcid":"https://orcid.org/0000-0002-8485-581X"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bagus Hanindhito","raw_affiliation_strings":["The University of Texas at Austin, Austin, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-8485-581X","affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015516733","display_name":"Arash Fathi","orcid":"https://orcid.org/0000-0002-6809-9815"},"institutions":[{"id":"https://openalex.org/I923382979","display_name":"ExxonMobil (United States)","ror":"https://ror.org/01xcepn55","country_code":"US","type":"company","lineage":["https://openalex.org/I923382979"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arash Fathi","raw_affiliation_strings":["ExxonMobil Technology and Engineering, Irving, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-6809-9815","affiliations":[{"raw_affiliation_string":"ExxonMobil Technology and Engineering, Irving, TX, USA","institution_ids":["https://openalex.org/I923382979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048990981","display_name":"Dimitar Trenev","orcid":"https://orcid.org/0000-0001-6131-8467"},"institutions":[{"id":"https://openalex.org/I923382979","display_name":"ExxonMobil (United States)","ror":"https://ror.org/01xcepn55","country_code":"US","type":"company","lineage":["https://openalex.org/I923382979"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimitar Trenev","raw_affiliation_strings":["ExxonMobil Technology and Engineering, Irving, TX, USA"],"raw_orcid":"https://orcid.org/0000-0001-6131-8467","affiliations":[{"raw_affiliation_string":"ExxonMobil Technology and Engineering, Irving, TX, USA","institution_ids":["https://openalex.org/I923382979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068885069","display_name":"Lizy K. John","orcid":"https://orcid.org/0000-0002-8747-5214"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lizy John","raw_affiliation_strings":["The University of Texas at Austin, Austin, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-8747-5214","affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046024226","display_name":"Andreas Gerstlauer","orcid":"https://orcid.org/0000-0002-6748-2054"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Gerstlauer","raw_affiliation_strings":["The University of Texas at Austin, Austin, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-6748-2054","affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"230","last_page":"230"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9851999878883362,"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":0.9851999878883362,"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/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.9739999771118164,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9567999839782715,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7569887638092041},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.7020638585090637},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.6935625672340393},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6876230239868164},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.6548082828521729},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6228070855140686},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5497817993164062},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5180864334106445},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.4899961054325104},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4528059959411621},{"id":"https://openalex.org/keywords/reconfigurable-computing","display_name":"Reconfigurable computing","score":0.4104488790035248},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3737351894378662},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.22438639402389526},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.19813096523284912},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0854668915271759}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7569887638092041},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.7020638585090637},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.6935625672340393},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6876230239868164},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.6548082828521729},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6228070855140686},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5497817993164062},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5180864334106445},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.4899961054325104},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4528059959411621},{"id":"https://openalex.org/C142962650","wikidata":"https://www.wikidata.org/wiki/Q240838","display_name":"Reconfigurable computing","level":3,"score":0.4104488790035248},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3737351894378662},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.22438639402389526},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.19813096523284912},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0854668915271759},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3543622.3573160","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543622.3573160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8999999761581421,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3172353879","https://openalex.org/W2904665340","https://openalex.org/W2887282140","https://openalex.org/W4239672454","https://openalex.org/W4388580994","https://openalex.org/W2030340070","https://openalex.org/W4386875296","https://openalex.org/W2808629603","https://openalex.org/W2953279884","https://openalex.org/W3101533771"],"abstract_inverted_index":{"Computing":[0],"numerical":[1],"solution":[2],"to":[3,27,46,85,143,209],"large-scale":[4,106],"scientific":[5],"computing":[6],"problems":[7,91,110],"described":[8],"by":[9],"partial":[10],"differential":[11],"equations":[12],"is":[13,25,33,83,219],"a":[14,34,58,100,124,184],"common":[15],"task":[16],"in":[17],"high-performance":[18],"computing.":[19,29],"Improving":[20],"their":[21],"performance":[22,159,191],"and":[23,102,120,130,139,147,168,221,228,235],"efficiency":[24],"critical":[26],"exa-scale":[28],"Application-specific":[30],"hardware":[31],"design":[32],"well-known":[35],"solution,":[36],"but":[37],"the":[38,175,210],"wide":[39],"range":[40],"of":[41,77,115,127,177],"kernels":[42,88],"makes":[43,55],"it":[44],"infeasible":[45],"provision":[47],"supercomputers":[48],"with":[49,156,196,233],"accelerators":[50],"for":[51,105,163],"all":[52],"applications.":[53,78],"This":[54],"reconfigurable":[56],"platforms":[57],"promising":[59],"direction.":[60],"In":[61],"this":[62],"work,":[63],"we":[64],"focus":[65],"on":[66,112,174],"wave":[67,108,179],"simulations":[68],"using":[69,81,123],"discontinuous":[70],"Galerkin":[71],"solvers,":[72],"as":[73],"an":[74,157,217,229],"important":[75],"class":[76],"Existing":[79],"work":[80],"FPGAs":[82,113],"limited":[84],"accelerating":[86],"specific":[87],"or":[89],"small":[90],"that":[92,161,183,216],"fit":[93],"into":[94],"FPGA":[95,186,218],"BRAM.":[96],"We":[97,152,171],"present":[98],"LAWS,":[99],"generic":[101],"configurable":[103],"architecture":[104,169],"accelerated":[107],"simulation":[109,176],"running":[111],"out":[114],"DRAM.":[116],"LAWS":[117,155,173],"exploits":[118],"fine-":[119],"coarse-grain":[121],"parallelism":[122],"scalable":[125],"array":[126],"application-specific":[128],"cores,":[129],"incorporates":[131],"novel":[132],"dataflow":[133],"optimizations,":[134],"including":[135],"prefetching,":[136],"kernel":[137],"fusion,":[138],"memory":[140],"layout":[141],"optimizations":[142],"minimize":[144],"data":[145],"transfers":[146],"maximize":[148],"DRAM":[149,206,213],"bandwidth":[150,214],"utilization.":[151],"further":[153],"accompany":[154],"analytical":[158],"model":[160],"allows":[162],"scaling":[164],"across":[165],"technology":[166],"trends":[167],"configurations.":[170],"demonstrate":[172],"elastic":[178],"equations.":[180],"Results":[181],"show":[182],"single":[185],"core":[187],"achieves":[188],"69%":[189],"higher":[190],"than":[192,224],"24":[193,225],"Xeon":[194],"cores":[195,227],"13.27x":[197],"better":[198,237],"energy":[199],"efficiency,":[200,238],"when":[201],"given":[202],"1.94x":[203],"less":[204],"peak":[205,212],"bandwidth.":[207],"Scaling":[208],"same":[211],"shows":[215],"3.27x":[220],"1.5x":[222],"faster":[223],"CPU":[226],"Nvidia":[230],"P100":[231],"GPU,":[232],"22.3x":[234],"4.53x":[236],"respectively.":[239]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}