{"id":"https://openalex.org/W4389166651","doi":"https://doi.org/10.1109/iccad57390.2023.10323650","title":"INR-Arch: A Dataflow Architecture and Compiler for Arbitrary-Order Gradient Computations in Implicit Neural Representation Processing","display_name":"INR-Arch: A Dataflow Architecture and Compiler for Arbitrary-Order Gradient Computations in Implicit Neural Representation Processing","publication_year":2023,"publication_date":"2023-10-28","ids":{"openalex":"https://openalex.org/W4389166651","doi":"https://doi.org/10.1109/iccad57390.2023.10323650"},"language":"en","primary_location":{"id":"doi:10.1109/iccad57390.2023.10323650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad57390.2023.10323650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5076244218","display_name":"Stefan Abi-Karam","orcid":"https://orcid.org/0000-0002-6697-8517"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I4388482740","display_name":"Georgia Tech Research Institute","ror":"https://ror.org/04qfrh333","country_code":null,"type":"facility","lineage":["https://openalex.org/I130701444","https://openalex.org/I4388482740"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefan Abi-Karam","raw_affiliation_strings":["Georgia Institute of Technology","Georgia Tech Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Tech Research Institute","institution_ids":["https://openalex.org/I130701444","https://openalex.org/I4388482740"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032302447","display_name":"Rishov Sarkar","orcid":"https://orcid.org/0000-0002-9168-0392"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rishov Sarkar","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084521327","display_name":"Dejia Xu","orcid":"https://orcid.org/0000-0001-8474-3095"},"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":"Dejia Xu","raw_affiliation_strings":["University of Texas,Austin","University of Texas, Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas,Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas, Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101178345","display_name":"Zhiwen Fan","orcid":"https://orcid.org/0000-0002-8302-7465"},"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":"Zhiwen Fan","raw_affiliation_strings":["University of Texas,Austin","University of Texas, Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas,Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas, Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048522863","display_name":"Zhangyang Wang","orcid":"https://orcid.org/0000-0002-2050-5693"},"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":"Zhangyang Wang","raw_affiliation_strings":["University of Texas,Austin","University of Texas, Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas,Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas, Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074300487","display_name":"Cong Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cong Hao","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9987000226974487,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/dataflow","display_name":"Dataflow","score":0.8879272937774658},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.869648814201355},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7784554362297058},{"id":"https://openalex.org/keywords/dataflow-architecture","display_name":"Dataflow architecture","score":0.7061797380447388},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6408051252365112},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.582953691482544},{"id":"https://openalex.org/keywords/stratix","display_name":"Stratix","score":0.5424613952636719},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5399617552757263},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream processing","score":0.44262051582336426},{"id":"https://openalex.org/keywords/out-of-order-execution","display_name":"Out-of-order execution","score":0.44003379344940186},{"id":"https://openalex.org/keywords/compile-time","display_name":"Compile time","score":0.4132750332355499},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.4066958427429199},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3386935591697693},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2852901220321655},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.19534602761268616},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1249571144580841}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8879272937774658},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.869648814201355},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7784554362297058},{"id":"https://openalex.org/C176727019","wikidata":"https://www.wikidata.org/wiki/Q1172415","display_name":"Dataflow architecture","level":3,"score":0.7061797380447388},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6408051252365112},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.582953691482544},{"id":"https://openalex.org/C2776277307","wikidata":"https://www.wikidata.org/wiki/Q22074755","display_name":"Stratix","level":3,"score":0.5424613952636719},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5399617552757263},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.44262051582336426},{"id":"https://openalex.org/C1793878","wikidata":"https://www.wikidata.org/wiki/Q1153762","display_name":"Out-of-order execution","level":2,"score":0.44003379344940186},{"id":"https://openalex.org/C200833197","wikidata":"https://www.wikidata.org/wiki/Q333707","display_name":"Compile time","level":3,"score":0.4132750332355499},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.4066958427429199},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3386935591697693},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2852901220321655},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.19534602761268616},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1249571144580841}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccad57390.2023.10323650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad57390.2023.10323650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W1868018859","https://openalex.org/W2604763608","https://openalex.org/W2962727772","https://openalex.org/W3037265641","https://openalex.org/W4200150166","https://openalex.org/W4287887519","https://openalex.org/W4306802143","https://openalex.org/W4312626952","https://openalex.org/W4312933730","https://openalex.org/W4320169939","https://openalex.org/W4383749334","https://openalex.org/W6638908295","https://openalex.org/W6779753539","https://openalex.org/W6791346067","https://openalex.org/W6846141923","https://openalex.org/W6849683939","https://openalex.org/W6850224944"],"related_works":["https://openalex.org/W2077180914","https://openalex.org/W2032571270","https://openalex.org/W4256562996","https://openalex.org/W1989140795","https://openalex.org/W2008321029","https://openalex.org/W1997547023","https://openalex.org/W4388501905","https://openalex.org/W2018965686","https://openalex.org/W2615505563","https://openalex.org/W2248318825"],"abstract_inverted_index":{"An":[0],"increasing":[1],"number":[2],"of":[3,16,37,115],"researchers":[4],"are":[5],"finding":[6],"use":[7],"for":[8,12,84,99,188],"nth-order":[9,77,117],"gradient":[10,36,78,118],"computations":[11],"a":[13,57,62,66,96,108,120,134,157],"wide":[14],"variety":[15],"applications,":[17],"including":[18],"graphics,":[19],"meta-learning":[20],"(MAML),":[21],"scientific":[22],"computing,":[23],"and":[24,87,141,151,161,172,182,203,209,217,222,224,235],"most":[25],"recently,":[26],"implicit":[27],"neural":[28],"representations":[29],"(INRs).":[30],"Recent":[31],"work":[32],"shows":[33],"that":[34,110,137,159,200],"the":[35,45,81,112],"an":[38,116,142],"INR":[39,193],"can":[40],"be":[41,232],"used":[42],"to":[43,52,56,80,175,207],"edit":[44],"data":[46,91],"it":[47,54,95],"represents":[48],"directly":[49],"without":[50],"needing":[51],"convert":[53],"back":[55],"discrete":[58],"representation.":[59],"However,":[60],"given":[61],"function":[63],"represented":[64],"as":[65,170,195],"computation":[67,113,144,163],"graph,":[68],"traditional":[69],"architectures":[70],"face":[71],"challenges":[72],"in":[73,90,128],"efficiently":[74],"computing":[75,85],"its":[76],"due":[79],"higher":[82,88],"demand":[83],"power":[86],"complexity":[89],"movement.":[92],"This":[93],"makes":[94],"promising":[97],"target":[98],"FPGA":[100,189],"acceleration.":[101],"In":[102],"this":[103,126],"work,":[104],"we":[105,132,155,214],"introduce":[106],"INR-Arch,":[107],"framework":[109,230],"transforms":[111],"graph":[114],"into":[119],"hardware-optimized":[121],"dataflow":[122,135],"architecture.":[123],"We":[124,191],"address":[125],"problem":[127],"two":[129],"phases.":[130],"First,":[131],"design":[133],"architecture":[136],"uses":[138],"FIFO":[139],"streams":[140],"optimized":[143],"kernel":[145],"library,":[146],"ensuring":[147,179],"high":[148],"memory":[149,220],"efficiency":[150],"parallel":[152],"computation.":[153],"Second,":[154],"propose":[156],"compiler":[158],"extracts":[160],"optimizes":[162],"graphs,":[164],"automatically":[165],"configures":[166],"hardware":[167],"parameters":[168],"such":[169],"latency":[171],"stream":[173],"depths":[174],"optimize":[176],"throughput,":[177],"while":[178],"deadlock-free":[180],"operation,":[181],"outputs":[183],"High-Level":[184],"Synthesis":[185],"(HLS)":[186],"code":[187],"implementation.":[190],"utilize":[192],"editing":[194],"our":[196],"benchmark,":[197],"presenting":[198],"results":[199],"demonstrate":[201],"1.8-4.8x":[202],"1.5-3.6x":[204],"speedup":[205],"compared":[206],"CPU":[208],"GPU":[210],"baselines":[211],"respectively.":[212],"Furthermore,":[213],"obtain":[215],"3.1-8.9x":[216],"1.7-4.3x":[218],"lower":[219,226],"usage,":[221],"1.7-11.3x":[223],"5.5-32.8x":[225],"energy-delay":[227],"product.":[228],"Our":[229],"will":[231],"made":[233],"open-source":[234],"available":[236],"on":[237],"GitHub.****https://github.com/sharc-lab/inr-arch":[238]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}