{"id":"https://openalex.org/W4310614714","doi":"https://doi.org/10.1109/icta56932.2022.9963119","title":"SAUST: A Scheme for Acceleration of Unstructured Sparse Transformer","display_name":"SAUST: A Scheme for Acceleration of Unstructured Sparse Transformer","publication_year":2022,"publication_date":"2022-10-28","ids":{"openalex":"https://openalex.org/W4310614714","doi":"https://doi.org/10.1109/icta56932.2022.9963119"},"language":"en","primary_location":{"id":"doi:10.1109/icta56932.2022.9963119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icta56932.2022.9963119","pdf_url":null,"source":{"id":"https://openalex.org/S4363608577","display_name":"2022 IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA)","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/A5057522443","display_name":"Yifan Song","orcid":"https://orcid.org/0000-0001-5553-4833"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yifan Song","raw_affiliation_strings":["University of Science and Technology of China,China","University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061765919","display_name":"Shunpeng Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shunpeng Zhao","raw_affiliation_strings":["University of Science and Technology of China,China","University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100423614","display_name":"Song Chen","orcid":"https://orcid.org/0000-0003-0341-3428"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Chen","raw_affiliation_strings":["University of Science and Technology of China,China","University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033886915","display_name":"Yi Kang","orcid":"https://orcid.org/0009-0004-3092-5626"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Kang","raw_affiliation_strings":["University of Science and Technology of China,China","University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5057522443"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.2996,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.63995437,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"56","last_page":"57"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.9876999855041504,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9876999855041504,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9825999736785889,"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/T10468","display_name":"Photovoltaic System Optimization Techniques","score":0.9818999767303467,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8552740216255188},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8127631545066833},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.7311254739761353},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7255041003227234},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.646574854850769},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6266535520553589},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6036409139633179},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5515560507774353},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5511044859886169},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.5414485931396484},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.49013814330101013},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4421810507774353},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4290599822998047},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.42562878131866455},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3357657194137573},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.25373169779777527},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09571269154548645}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8552740216255188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8127631545066833},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.7311254739761353},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7255041003227234},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.646574854850769},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6266535520553589},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6036409139633179},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5515560507774353},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5511044859886169},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.5414485931396484},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.49013814330101013},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4421810507774353},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4290599822998047},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.42562878131866455},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3357657194137573},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.25373169779777527},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09571269154548645},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icta56932.2022.9963119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icta56932.2022.9963119","pdf_url":null,"source":{"id":"https://openalex.org/S4363608577","display_name":"2022 IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.44999998807907104,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G4027129818","display_name":null,"funder_award_id":"2019YFB2204800","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2910396952","https://openalex.org/W3162542754","https://openalex.org/W3170233084","https://openalex.org/W3176468986","https://openalex.org/W3206837665","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6788001715"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W2532502681","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":{"Transformer":[0],"achieves":[1],"impressive":[2],"results":[3],"on":[4,117],"many":[5],"AI":[6],"tasks.":[7],"However,":[8,52],"it":[9],"also":[10],"introduces":[11],"a":[12,19,65,76],"huge":[13],"amount":[14],"of":[15,84],"computation.":[16],"Pruning":[17],"is":[18],"promising":[20],"method":[21],"to":[22,113],"reduce":[23],"the":[24,70,80,89],"computation":[25],"load":[26,34,90],"by":[27,37],"generating":[28],"sparse":[29],"transformer":[30],"models.":[31],"To":[32],"avoid":[33],"imbalance":[35,91],"caused":[36],"computing":[38],"involved":[39],"in":[40,55,69],"zero":[41],"elements,":[42],"previous":[43],"works":[44],"explore":[45],"structured":[46,56],"pruning":[47,57,86],"combined":[48],"with":[49],"hardware":[50,95,118],"acceleration.":[51],"tight":[53],"constraints":[54],"usually":[58],"make":[59],"training":[60],"much":[61],"harder":[62],"and":[63,87,96,107],"reach":[64],"lower":[66],"sparsity":[67,82],"level":[68,83],"end.":[71],"This":[72],"paper":[73],"proposes":[74],"SAUST,":[75],"scheme":[77],"that":[78,102],"exploits":[79],"high":[81],"unstructured":[85],"addresses":[88],"problem":[92],"using":[93],"both":[94],"software":[97],"methods.":[98],"FPGA":[99],"implementation":[100],"shows":[101],"SAUST":[103],"can":[104],"achieve":[105],"3.35x":[106],"2.76x":[108],"execution":[109],"time":[110],"speedup":[111],"compared":[112],"two":[114],"state-of-the-art":[115],"references":[116],"accelerators.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
