{"id":"https://openalex.org/W4390189010","doi":"https://doi.org/10.1109/hpec58863.2023.10363578","title":"GLARE: Accelerating Sparse DNN Inference Kernels with Global Memory Access Reduction","display_name":"GLARE: Accelerating Sparse DNN Inference Kernels with Global Memory Access Reduction","publication_year":2023,"publication_date":"2023-09-25","ids":{"openalex":"https://openalex.org/W4390189010","doi":"https://doi.org/10.1109/hpec58863.2023.10363578"},"language":"en","primary_location":{"id":"doi:10.1109/hpec58863.2023.10363578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec58863.2023.10363578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5103137666","display_name":"Shui Jiang","orcid":"https://orcid.org/0000-0003-0718-1003"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shui Jiang","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong","The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088685794","display_name":"Tsung\u2010Wei Huang","orcid":"https://orcid.org/0000-0001-9768-3378"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tsung-Wei Huang","raw_affiliation_strings":["The University of Wisconsin at Madison,Wisconsin,USA","The University of Wisconsin at Madison, Wisconsin, USA"],"affiliations":[{"raw_affiliation_string":"The University of Wisconsin at Madison,Wisconsin,USA","institution_ids":["https://openalex.org/I135310074"]},{"raw_affiliation_string":"The University of Wisconsin at Madison, Wisconsin, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062800747","display_name":"Tsung-Yi Ho","orcid":"https://orcid.org/0000-0001-7348-5625"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tsung-Yi Ho","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong","The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103137666"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.1113,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.80609499,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"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":0.9962000250816345,"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":0.9962000250816345,"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":0.9891999959945679,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7846044301986694},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7563097476959229},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5356912612915039},{"id":"https://openalex.org/keywords/inference-engine","display_name":"Inference engine","score":0.5035557150840759},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.4914811849594116},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.48657047748565674},{"id":"https://openalex.org/keywords/dense-graph","display_name":"Dense graph","score":0.4783998429775238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41788890957832336},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.41595888137817383},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.41411909461021423},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.3749457895755768},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36278751492500305},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.35461682081222534},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.34382912516593933},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2640828788280487},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.11523130536079407}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7846044301986694},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7563097476959229},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5356912612915039},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.5035557150840759},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.4914811849594116},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.48657047748565674},{"id":"https://openalex.org/C13251829","wikidata":"https://www.wikidata.org/wiki/Q3085841","display_name":"Dense graph","level":5,"score":0.4783998429775238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41788890957832336},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.41595888137817383},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.41411909461021423},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3749457895755768},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36278751492500305},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.35461682081222534},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.34382912516593933},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2640828788280487},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.11523130536079407},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C203776342","wikidata":"https://www.wikidata.org/wiki/Q1378376","display_name":"Line graph","level":3,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C102192266","wikidata":"https://www.wikidata.org/wiki/Q4545823","display_name":"1-planar graph","level":4,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec58863.2023.10363578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec58863.2023.10363578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W192356505","https://openalex.org/W1992851788","https://openalex.org/W2148869717","https://openalex.org/W2153667821","https://openalex.org/W2194775991","https://openalex.org/W2303605678","https://openalex.org/W2725179571","https://openalex.org/W2896457183","https://openalex.org/W2914631005","https://openalex.org/W2963163009","https://openalex.org/W2973134322","https://openalex.org/W2982022996","https://openalex.org/W2990514424","https://openalex.org/W3041526861","https://openalex.org/W3088721995","https://openalex.org/W3091980371","https://openalex.org/W3100839241","https://openalex.org/W3111098492","https://openalex.org/W3113443077","https://openalex.org/W3134181251","https://openalex.org/W3165412222","https://openalex.org/W3188917597","https://openalex.org/W3197809542","https://openalex.org/W3198396679","https://openalex.org/W3211750799","https://openalex.org/W3212679119","https://openalex.org/W4200090124","https://openalex.org/W4200128939","https://openalex.org/W4200319213","https://openalex.org/W4252769808","https://openalex.org/W4283390926","https://openalex.org/W4293025123","https://openalex.org/W4308090217","https://openalex.org/W4308090426","https://openalex.org/W4308090451","https://openalex.org/W4308090748","https://openalex.org/W4320067872","https://openalex.org/W4379115843","https://openalex.org/W4379115887","https://openalex.org/W4380607252","https://openalex.org/W4384705351","https://openalex.org/W4385585512","https://openalex.org/W4386709670","https://openalex.org/W4386763846","https://openalex.org/W6666676899","https://openalex.org/W6755207826","https://openalex.org/W6762718338","https://openalex.org/W6846571505"],"related_works":["https://openalex.org/W2483318309","https://openalex.org/W2323703259","https://openalex.org/W1566229417","https://openalex.org/W4316252382","https://openalex.org/W1893178273","https://openalex.org/W2542063421","https://openalex.org/W4299546378","https://openalex.org/W3138826529","https://openalex.org/W4320554512","https://openalex.org/W2539871928"],"abstract_inverted_index":{"Sparse":[0,41],"deep":[1],"neural":[2],"networks":[3],"(DNNs)":[4],"leverage":[5],"sparse":[6,18,64,96,117,138],"representations":[7],"to":[8,79,110,144],"achieve":[9],"faster":[10],"inference":[11,97,118,139],"and":[12,114,132],"lower":[13],"memory":[14,26,75,104],"footprint.":[15],"However,":[16,67],"deploying":[17],"DNNs":[19],"comes":[20],"with":[21],"challenges,":[22,35],"such":[23],"as":[24],"irregular":[25],"access":[27,76],"patterns,":[28],"workload":[29],"imbalance,":[30],"etc.":[31],"To":[32,83],"address":[33],"these":[34],"IEEE":[36],"HPEC":[37],"has":[38,58],"organized":[39],"the":[40,50,127,151],"DNN":[42,65],"Graph":[43],"Challenge":[44],"(SDGC),":[45],"seeking":[46],"new":[47],"methods":[48],"from":[49],"high-performance":[51],"computing":[52],"community.":[53],"For":[54],"many":[55],"years,":[56],"SDGC":[57,112,123,153],"yielded":[59],"innovative":[60],"works":[61],"on":[62,122],"accelerating":[63,136],"inference.":[66],"none":[68],"of":[69,130,150],"them":[70],"have":[71,107],"identified":[72],"redundant":[73,102],"global":[74,103],"that":[77,92],"contributes":[78],"significant":[80],"runtime":[81],"overhead.":[82],"overcome":[84],"this":[85],"challenge,":[86],"we":[87,125],"propose":[88],"GLARE,":[89],"a":[90,115],"framework":[91],"can":[93],"assist":[94],"existing":[95,137],"kernels":[98],"in":[99,135],"effectively":[100],"reducing":[101],"access.":[105],"We":[106],"applied":[108],"GLARE":[109,131],"previous":[111,152],"champions":[113],"recent":[116],"engine":[119],"SNICIT.":[120],"Evaluated":[121],"benchmarks,":[124],"demonstrate":[126],"promising":[128],"performance":[129],"its":[133],"generalizability":[134],"kernels,":[140],"for":[141],"instance,":[142],"up":[143],"31.56":[145],"x":[146],"speed-up":[147],"over":[148],"one":[149],"champions.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}