{"id":"https://openalex.org/W4389476163","doi":"https://doi.org/10.1145/3613424.3623775","title":"RM-STC: Row-Merge Dataflow Inspired GPU Sparse Tensor Core for Energy-Efficient Sparse Acceleration","display_name":"RM-STC: Row-Merge Dataflow Inspired GPU Sparse Tensor Core for Energy-Efficient Sparse Acceleration","publication_year":2023,"publication_date":"2023-10-28","ids":{"openalex":"https://openalex.org/W4389476163","doi":"https://doi.org/10.1145/3613424.3623775"},"language":"en","primary_location":{"id":"doi:10.1145/3613424.3623775","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613424.3623775","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613424.3623775","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"56th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3613424.3623775","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078367183","display_name":"Guyue Huang","orcid":"https://orcid.org/0000-0002-1280-4781"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guyue Huang","raw_affiliation_strings":["UC Santa Barbara, USA"],"raw_orcid":"https://orcid.org/0000-0002-1280-4781","affiliations":[{"raw_affiliation_string":"UC Santa Barbara, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045756072","display_name":"Z. Y. Wang","orcid":"https://orcid.org/0000-0002-9473-0973"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengyang Wang","raw_affiliation_strings":["UC Santa Barbara, USA"],"raw_orcid":"https://orcid.org/0000-0002-9473-0973","affiliations":[{"raw_affiliation_string":"UC Santa Barbara, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080155613","display_name":"Po-An Tsai","orcid":"https://orcid.org/0000-0003-4561-6450"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Po-An Tsai","raw_affiliation_strings":["NVIDIA, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-4561-6450","affiliations":[{"raw_affiliation_string":"NVIDIA, United States of America","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374175","display_name":"Chen Zhang","orcid":"https://orcid.org/0000-0003-2762-2726"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"raw_orcid":"https://orcid.org/0000-0003-2762-2726","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048052285","display_name":"Yufei Ding","orcid":"https://orcid.org/0000-0002-8716-5793"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yufei Ding","raw_affiliation_strings":["UC Santa Barbara, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-8716-5793","affiliations":[{"raw_affiliation_string":"UC Santa Barbara, United States of America","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100385336","display_name":"Yuan Xie","orcid":"https://orcid.org/0000-0003-2093-1788"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Xie","raw_affiliation_strings":["Alibaba Group, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-2093-1788","affiliations":[{"raw_affiliation_string":"Alibaba Group, United States of America","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6983,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.90011881,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"338","last_page":"352"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987999796867371,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.8614800572395325},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.754033088684082},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5870417356491089},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.582434892654419},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.529353678226471},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.48868682980537415},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4569956660270691},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4305740296840668},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.4107442796230316},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34606093168258667},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3317719101905823},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3292158842086792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23192939162254333},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.17408135533332825},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1292419731616974},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0750308632850647}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8614800572395325},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.754033088684082},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5870417356491089},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.582434892654419},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.529353678226471},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48868682980537415},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4569956660270691},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4305740296840668},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.4107442796230316},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34606093168258667},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3317719101905823},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3292158842086792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23192939162254333},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.17408135533332825},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1292419731616974},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0750308632850647},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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":2,"locations":[{"id":"doi:10.1145/3613424.3623775","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613424.3623775","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613424.3623775","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"56th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-136616","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-136616","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.1145/3613424.3623775","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613424.3623775","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613424.3623775","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"56th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8799999952316284,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389476163.pdf","grobid_xml":"https://content.openalex.org/works/W4389476163.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2285660444","https://openalex.org/W2516141709","https://openalex.org/W2585720638","https://openalex.org/W2588191434","https://openalex.org/W2794952988","https://openalex.org/W2809121165","https://openalex.org/W2915106038","https://openalex.org/W2945146780","https://openalex.org/W2963989532","https://openalex.org/W2979310060","https://openalex.org/W2979439447","https://openalex.org/W2980186997","https://openalex.org/W3016542674","https://openalex.org/W3016735325","https://openalex.org/W3016832937","https://openalex.org/W3102510044","https://openalex.org/W3102587717","https://openalex.org/W3103168911","https://openalex.org/W3105802176","https://openalex.org/W3155922894","https://openalex.org/W3158275024","https://openalex.org/W3158831985","https://openalex.org/W3159727696","https://openalex.org/W3159869264","https://openalex.org/W3170778815","https://openalex.org/W3185702163","https://openalex.org/W3187908937","https://openalex.org/W3210117238","https://openalex.org/W4236868170","https://openalex.org/W4286850694","https://openalex.org/W4308083753","https://openalex.org/W4312443924","https://openalex.org/W6803845004"],"related_works":["https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W3167919718","https://openalex.org/W4239447582","https://openalex.org/W2171015181","https://openalex.org/W4225271228","https://openalex.org/W1484403103","https://openalex.org/W2521947294","https://openalex.org/W2907307640","https://openalex.org/W2030992542"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"RM-STC,":[3],"a":[4,44],"novel":[5],"GPU":[6],"tensor":[7,108,113],"core":[8],"architecture":[9],"designed":[10],"for":[11,24,33,64],"sparse":[12,46,66,112],"Deep":[13],"Neural":[14],"Networks":[15],"(DNNs)":[16],"with":[17],"two":[18],"key":[19],"innovations:":[20],"(1)":[21],"native":[22],"support":[23],"both":[25],"training":[26],"and":[27,29,57,82,86,102,110],"inference":[28],"(2)":[30],"high":[31],"efficiency":[32,104],"all":[34,52],"sparsity":[35],"degrees.":[36],"To":[37],"achieve":[38],"the":[39,62,72,79,84,92],"first":[40],"goal,":[41,74],"RM-STC":[42,75,98],"employs":[43],"uniform":[45],"encoding":[47,67],"scheme":[48],"that":[49,97],"natively":[50],"supports":[51],"operations":[53],"holistically":[54],"in":[55,69],"forward":[56],"backward":[58],"passes,":[59],"thereby":[60],"eliminating":[61],"need":[63],"costly":[65],"transformation":[68],"between.":[70],"For":[71],"second":[73],"takes":[76],"inspiration":[77],"from":[78],"row-merge":[80],"dataflow":[81],"combines":[83],"input-gathering":[85],"output-scattering":[87],"hardware":[88],"features":[89],"to":[90],"minimize":[91],"energy":[93,103],"overhead.":[94],"Experiments":[95],"show":[96],"achieves":[99],"significant":[100],"speedups":[101],"improvements":[105],"over":[106],"dense":[107],"cores":[109],"previous":[111],"cores.":[114]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}