{"id":"https://openalex.org/W2984035546","doi":"https://doi.org/10.1145/3295500.3356169","title":"BSTC","display_name":"BSTC","publication_year":2019,"publication_date":"2019-11-07","ids":{"openalex":"https://openalex.org/W2984035546","doi":"https://doi.org/10.1145/3295500.3356169","mag":"2984035546"},"language":"en","primary_location":{"id":"doi:10.1145/3295500.3356169","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3295500.3356169","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3295500.3356169","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3295500.3356169","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100413657","display_name":"Ang Li","orcid":"https://orcid.org/0000-0003-3734-9137"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ang Li","raw_affiliation_strings":["Pacific Northwest National Lab"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Lab","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078443672","display_name":"Tong Geng","orcid":"https://orcid.org/0000-0002-3644-2922"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tong Geng","raw_affiliation_strings":["Boston University"],"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100734913","display_name":"Tianqi Wang","orcid":"https://orcid.org/0000-0002-5921-6565"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianqi Wang","raw_affiliation_strings":["Boston University"],"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021051610","display_name":"Martin Herbordt","orcid":"https://orcid.org/0000-0002-3443-9113"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Herbordt","raw_affiliation_strings":["Boston University"],"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043209884","display_name":"Shuaiwen Leon Song","orcid":"https://orcid.org/0000-0002-8402-1436"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuaiwen Leon Song","raw_affiliation_strings":["Pacific Northwest National Lab"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Lab","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038062469","display_name":"Kevin Barker","orcid":"https://orcid.org/0000-0003-4947-0559"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Barker","raw_affiliation_strings":["Pacific Northwest National Lab"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Lab","institution_ids":["https://openalex.org/I142606810"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100413657"],"corresponding_institution_ids":["https://openalex.org/I142606810"],"apc_list":null,"apc_paid":null,"fwci":2.8606,"has_fulltext":true,"cited_by_count":42,"citation_normalized_percentile":{"value":0.92994625,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"30"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9973000288009644,"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/T12676","display_name":"Machine Learning and ELM","score":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8593604564666748},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.633446991443634},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6198973655700684},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5891910791397095},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.5746521353721619},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.5371869802474976},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5203285217285156},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.47327136993408203},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.38534826040267944},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.24992695450782776},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18118256330490112}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8593604564666748},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.633446991443634},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6198973655700684},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5891910791397095},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.5746521353721619},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.5371869802474976},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5203285217285156},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.47327136993408203},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.38534826040267944},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.24992695450782776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18118256330490112},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3295500.3356169","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3295500.3356169","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3295500.3356169","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3295500.3356169","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3295500.3356169","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3295500.3356169","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4000000059604645,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1184536953","display_name":null,"funder_award_id":"HPDA-SBLAS","funder_id":"https://openalex.org/F4320338354","funder_display_name":"Pacific Northwest National Laboratory"},{"id":"https://openalex.org/G5271250179","display_name":null,"funder_award_id":"90001-N90615","funder_id":"https://openalex.org/F4320337547","funder_display_name":"Laboratory Directed Research and Development"},{"id":"https://openalex.org/G5600677258","display_name":null,"funder_award_id":"U.S. DOE","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6769186712","display_name":null,"funder_award_id":"66150-Center for Advanced Technology Evaluation (CENATE)","funder_id":"https://openalex.org/F4320337506","funder_display_name":"Advanced Scientific Computing Research"},{"id":"https://openalex.org/G8170416923","display_name":null,"funder_award_id":"66150","funder_id":"https://openalex.org/F4320337506","funder_display_name":"Advanced Scientific Computing Research"},{"id":"https://openalex.org/G8679700530","display_name":null,"funder_award_id":"66150","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"},{"id":"https://openalex.org/F4320337547","display_name":"Laboratory Directed Research and Development","ror":"https://ror.org/01e41cf67"},{"id":"https://openalex.org/F4320338354","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2984035546.pdf","grobid_xml":"https://content.openalex.org/works/W2984035546.grobid-xml"},"referenced_works_count":73,"referenced_works":["https://openalex.org/W1483793973","https://openalex.org/W1530262073","https://openalex.org/W1661801558","https://openalex.org/W1667072054","https://openalex.org/W1667652561","https://openalex.org/W1902934009","https://openalex.org/W1967701350","https://openalex.org/W1974239281","https://openalex.org/W1976641468","https://openalex.org/W2013812309","https://openalex.org/W2023770077","https://openalex.org/W2027016096","https://openalex.org/W2041356909","https://openalex.org/W2047213715","https://openalex.org/W2057126609","https://openalex.org/W2091599698","https://openalex.org/W2094269606","https://openalex.org/W2098274770","https://openalex.org/W2108598243","https://openalex.org/W2109197177","https://openalex.org/W2140483504","https://openalex.org/W2142801765","https://openalex.org/W2155893237","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2267635276","https://openalex.org/W2300242332","https://openalex.org/W2319920447","https://openalex.org/W2345717615","https://openalex.org/W2415973476","https://openalex.org/W2469490737","https://openalex.org/W2483772785","https://openalex.org/W2512971201","https://openalex.org/W2553427643","https://openalex.org/W2565125333","https://openalex.org/W2585560244","https://openalex.org/W2591922920","https://openalex.org/W2604700561","https://openalex.org/W2605251767","https://openalex.org/W2605350416","https://openalex.org/W2623173292","https://openalex.org/W2623381305","https://openalex.org/W2710900611","https://openalex.org/W2725001169","https://openalex.org/W2747853580","https://openalex.org/W2753301142","https://openalex.org/W2757956526","https://openalex.org/W2765235648","https://openalex.org/W2788645721","https://openalex.org/W2804224090","https://openalex.org/W2808541151","https://openalex.org/W2812373594","https://openalex.org/W2852179785","https://openalex.org/W2886991855","https://openalex.org/W2891890103","https://openalex.org/W2903631665","https://openalex.org/W2903901007","https://openalex.org/W2908314593","https://openalex.org/W2914381000","https://openalex.org/W2926767350","https://openalex.org/W2928897890","https://openalex.org/W2949117887","https://openalex.org/W2949744956","https://openalex.org/W2962938696","https://openalex.org/W2963427045","https://openalex.org/W2964064024","https://openalex.org/W2971542763","https://openalex.org/W2990714382","https://openalex.org/W3102169921","https://openalex.org/W3103589224","https://openalex.org/W3106144922","https://openalex.org/W4206174637","https://openalex.org/W4229654654"],"related_works":["https://openalex.org/W2475524688","https://openalex.org/W2739740241","https://openalex.org/W947442053","https://openalex.org/W2085105049","https://openalex.org/W2592417500","https://openalex.org/W1974923383","https://openalex.org/W2526069705","https://openalex.org/W2024016913","https://openalex.org/W2019153376","https://openalex.org/W2796552083"],"abstract_inverted_index":{"Binarized":[0],"neural":[1],"networks":[2],"(or":[3],"BNNs)":[4],"promise":[5],"tremendous":[6],"performance":[7,55,109],"improvement":[8],"over":[9,186,193],"traditional":[10],"DNNs":[11],"through":[12],"simplified":[13],"bit-level":[14],"computation":[15],"and":[16,30,38,48,78,102,105,118,136,148,167,175,208,219],"significantly":[17],"reduced":[18],"memory":[19],"access/storage":[20],"cost.":[21],"In":[22],"addition,":[23],"it":[24],"has":[25,60],"advantages":[26],"of":[27,57,76,172,213],"low-cost,":[28],"low-energy,":[29],"high-robustness,":[31],"showing":[32],"great":[33],"potential":[34],"in":[35],"resources-constrained,":[36],"volatile,":[37],"latency-critical":[39],"applications,":[40],"which":[41],"are":[42],"critical":[43],"for":[44,133,189,199],"future":[45],"HPC,":[46],"cloud,":[47],"edge":[49],"applications.":[50],"However,":[51],"the":[52,74,88,94,154,170,194,211],"promised":[53],"significant":[54],"gain":[56],"BNN":[58,100,112,156,197],"inference":[59,157,191,198],"never":[61],"been":[62],"fully":[63],"demonstrated":[64],"on":[65,69,201],"general-purpose":[66],"processors,":[67],"particularly":[68],"GPUs,":[70],"due":[71],"to:":[72],"(i)":[73,117],"challenge":[75],"extracting":[77],"leveraging":[79],"sufficient":[80],"finegrained":[81],"bit-level-parallelism":[82,140],"to":[83,111,129],"saturate":[84],"GPU":[85,165],"cores":[86],"when":[87],"batch":[89],"size":[90],"is":[91,217],"small;":[92],"(ii)":[93],"fundamental":[95],"design":[96,183],"conflict":[97],"between":[98],"bit-based":[99],"algorithm":[101],"word-based":[103],"architecture;":[104],"(iii)":[106],"architecture":[107],"&":[108],"unfriendly":[110],"network":[113],"design.":[114,215],"To":[115,142],"address":[116],"(ii),":[119],"we":[120,145],"propose":[121,146],"a":[122,125,163],"binarized-soft-tensor-core":[123],"as":[124],"software-hardware":[126],"codesign":[127],"approach":[128],"construct":[130],"bit-manipulation":[131],"capability":[132],"modern":[134],"GPUs":[135],"thereby":[137],"effectively":[138],"harvest":[139],"(BLP).":[141],"tackle":[143],"(iii),":[144],"intra-":[147],"inter-layer":[149],"fusion":[150],"techniques":[151],"so":[152,168],"that":[153,179],"entire":[155],"execution":[158],"can":[159,184],"be":[160],"packed":[161],"into":[162],"single":[164],"kernel,":[166],"avoid":[169],"high-cost":[171],"frequent":[173],"launching":[174],"releasing.":[176],"Experiments":[177],"show":[178],"our":[180,214],"Singular-Binarized-Neural-Network":[181],"(SBNN)":[182],"achieve":[185],"1000X":[187],"speedup":[188],"raw":[190],"latency":[192],"state-of-the-art":[195],"full-precision":[196],"AlexNet":[200],"GPUs.":[202],"Comparisons":[203],"with":[204],"CPU,":[205],"GPU,":[206],"FPGA":[207],"Xeon-Phi":[209],"demonstrate":[210],"effectiveness":[212],"SBNN":[216],"opensourced":[218],"available":[220],"at":[221],"https://github.com/uuudown/SBNN.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2019-11-22T00:00:00"}