{"id":"https://openalex.org/W4200369086","doi":"https://doi.org/10.1109/hpec49654.2021.9622804","title":"Sparse Deep Neural Network Acceleration on HBM-Enabled FPGA Platform","display_name":"Sparse Deep Neural Network Acceleration on HBM-Enabled FPGA Platform","publication_year":2021,"publication_date":"2021-09-20","ids":{"openalex":"https://openalex.org/W4200369086","doi":"https://doi.org/10.1109/hpec49654.2021.9622804"},"language":"en","primary_location":{"id":"doi:10.1109/hpec49654.2021.9622804","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec49654.2021.9622804","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5076243389","display_name":"Abhishek Kumar Jain","orcid":"https://orcid.org/0000-0003-3797-029X"},"institutions":[{"id":"https://openalex.org/I32923980","display_name":"Xilinx (United States)","ror":"https://ror.org/01rb7bk56","country_code":"US","type":"company","lineage":["https://openalex.org/I32923980"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Abhishek Kumar Jain","raw_affiliation_strings":["Xilinx Inc., San Jose, CA, United States"],"affiliations":[{"raw_affiliation_string":"Xilinx Inc., San Jose, CA, United States","institution_ids":["https://openalex.org/I32923980"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049575446","display_name":"Sharan Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I32923980","display_name":"Xilinx (United States)","ror":"https://ror.org/01rb7bk56","country_code":"US","type":"company","lineage":["https://openalex.org/I32923980"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sharan Kumar","raw_affiliation_strings":["Xilinx Inc., San Jose, CA, United States"],"affiliations":[{"raw_affiliation_string":"Xilinx Inc., San Jose, CA, United States","institution_ids":["https://openalex.org/I32923980"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081030795","display_name":"Aashish Tripathi","orcid":null},"institutions":[{"id":"https://openalex.org/I32923980","display_name":"Xilinx (United States)","ror":"https://ror.org/01rb7bk56","country_code":"US","type":"company","lineage":["https://openalex.org/I32923980"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aashish Tripathi","raw_affiliation_strings":["Xilinx Inc., San Jose, CA, United States"],"affiliations":[{"raw_affiliation_string":"Xilinx Inc., San Jose, CA, United States","institution_ids":["https://openalex.org/I32923980"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074585636","display_name":"Dinesh Gaitonde","orcid":null},"institutions":[{"id":"https://openalex.org/I32923980","display_name":"Xilinx (United States)","ror":"https://ror.org/01rb7bk56","country_code":"US","type":"company","lineage":["https://openalex.org/I32923980"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinesh Gaitonde","raw_affiliation_strings":["Xilinx Inc., San Jose, CA, United States"],"affiliations":[{"raw_affiliation_string":"Xilinx Inc., San Jose, CA, United States","institution_ids":["https://openalex.org/I32923980"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5076243389"],"corresponding_institution_ids":["https://openalex.org/I32923980"],"apc_list":null,"apc_paid":null,"fwci":0.4803,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.66138889,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9976000189781189,"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":0.9976000189781189,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9961000084877014,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9944999814033508,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.788749635219574},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7468256950378418},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6760596036911011},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5438554286956787},{"id":"https://openalex.org/keywords/inference-engine","display_name":"Inference engine","score":0.5183983445167542},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.48567473888397217},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46741294860839844},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4646811783313751},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.45787355303764343},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.45459723472595215},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4235481321811676},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4169897735118866},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4077782928943634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32420825958251953},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1097554862499237}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.788749635219574},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7468256950378418},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6760596036911011},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5438554286956787},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.5183983445167542},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.48567473888397217},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46741294860839844},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4646811783313751},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.45787355303764343},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.45459723472595215},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4235481321811676},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4169897735118866},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4077782928943634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32420825958251953},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1097554862499237},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec49654.2021.9622804","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec49654.2021.9622804","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1937292006","https://openalex.org/W2133563079","https://openalex.org/W2284169075","https://openalex.org/W2888727064","https://openalex.org/W2915106038","https://openalex.org/W2941763154","https://openalex.org/W2973134322","https://openalex.org/W2973152414","https://openalex.org/W2990185852","https://openalex.org/W3016542674","https://openalex.org/W3093571597","https://openalex.org/W3100839241","https://openalex.org/W3161204726","https://openalex.org/W4240168186","https://openalex.org/W4240983278","https://openalex.org/W4245683599","https://openalex.org/W6656609317"],"related_works":["https://openalex.org/W1556451512","https://openalex.org/W1555349535","https://openalex.org/W2384475851","https://openalex.org/W4234091740","https://openalex.org/W4319952061","https://openalex.org/W4280636456","https://openalex.org/W4388913998","https://openalex.org/W4310584535","https://openalex.org/W4295935044","https://openalex.org/W3159906349"],"abstract_inverted_index":{"Domain-specific":[0],"architectures":[1],"(DSAs)":[2],"for":[3,80,108,131],"deep":[4],"neural":[5],"networks":[6],"(DNNs)":[7],"are":[8,76],"becoming":[9],"mainstream":[10],"because":[11],"of":[12,19,51,71,116,124],"high":[13,33,49],"energy-efficiency":[14],"and":[15,30,36,54,69,141],"performance.":[16],"Currently,":[17],"most":[18],"these":[20],"DSAs":[21,46,75],"perform":[22],"dense":[23],"linear":[24],"algebra":[25],"efficiently":[26],"by":[27,120],"exploiting":[28],"temporal":[29],"spatial":[31],"locality,":[32],"data":[34],"reuse":[35],"regular":[37],"memory":[38,55],"access":[39],"patterns.":[40],"However,":[41],"state-of-the-art":[42],"DNN":[43,60,89,127],"models":[44,123],"require":[45],"with":[47],"very":[48],"amount":[50],"compute,":[52],"interconnect":[53],"resources.":[56],"Since":[57],"sparsity":[58,81],"in":[59],"parameters":[61],"can":[62],"be":[63],"exploited":[64],"to":[65,150],"reduce":[66],"the":[67,72,114,125,132,137],"resources":[68],"complexity":[70],"DSAs,":[73],"emerging":[74],"adding":[77],"native":[78,106],"support":[79,107],"[1],":[82],"[2].":[83],"This":[84],"paper":[85],"presents":[86],"a":[87],"sparse":[88],"inference":[90,118,122,139,156],"engine":[91,119,140],"on":[92,144],"HBM-enabled":[93,145],"Alveo":[94,146],"U280":[95,147],"platform,":[96],"built":[97],"around":[98],"FPGA-optimized":[99],"DSA":[100,103],"blocks.":[101],"The":[102],"blocks":[104],"have":[105],"completely":[109],"unstructured":[110],"sparsity.":[111],"We":[112],"demonstrate":[113],"effectiveness":[115],"proposed":[117,138],"running":[121],"Sparse":[126],"Challenge":[128],"[3].":[129],"Results":[130],"challenge":[133],"benchmarks":[134],"show":[135],"that":[136],"multi-DSA":[142],"parallelization":[143],"achieve":[148],"up":[149],"3.7":[151],"billion":[152],"edges":[153],"per":[154],"second":[155],"throughput.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}