{"id":"https://openalex.org/W3214870808","doi":"https://doi.org/10.1109/iccad51958.2021.9643506","title":"dCSR: A Memory-Efficient Sparse Matrix Representation for Parallel Neural Network Inference","display_name":"dCSR: A Memory-Efficient Sparse Matrix Representation for Parallel Neural Network Inference","publication_year":2021,"publication_date":"2021-11-01","ids":{"openalex":"https://openalex.org/W3214870808","doi":"https://doi.org/10.1109/iccad51958.2021.9643506","mag":"3214870808"},"language":"en","primary_location":{"id":"doi:10.1109/iccad51958.2021.9643506","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad51958.2021.9643506","pdf_url":null,"source":{"id":"https://openalex.org/S4363608354","display_name":"2021 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","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":"2021 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","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/A5021279961","display_name":"Elias Trommer","orcid":"https://orcid.org/0000-0002-5671-3291"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]},{"id":"https://openalex.org/I137594350","display_name":"Infineon Technologies (Germany)","ror":"https://ror.org/005kw6t15","country_code":"DE","type":"company","lineage":["https://openalex.org/I137594350"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Elias Trommer","raw_affiliation_strings":["Infineon Technologies, TU Dresden,Dresden,Germany"],"affiliations":[{"raw_affiliation_string":"Infineon Technologies, TU Dresden,Dresden,Germany","institution_ids":["https://openalex.org/I137594350","https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067647232","display_name":"Bernd Waschneck","orcid":"https://orcid.org/0000-0003-0294-8594"},"institutions":[{"id":"https://openalex.org/I137594350","display_name":"Infineon Technologies (Germany)","ror":"https://ror.org/005kw6t15","country_code":"DE","type":"company","lineage":["https://openalex.org/I137594350"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bernd Waschneck","raw_affiliation_strings":["Infineon Technologies,Dresden,Germany"],"affiliations":[{"raw_affiliation_string":"Infineon Technologies,Dresden,Germany","institution_ids":["https://openalex.org/I137594350"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100755285","display_name":"Akash Kumar","orcid":"https://orcid.org/0000-0001-7125-1737"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Akash Kumar","raw_affiliation_strings":["TU Dresden, Center for advancing electronics (cfaed), Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"TU Dresden, Center for advancing electronics (cfaed), Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021279961"],"corresponding_institution_ids":["https://openalex.org/I137594350","https://openalex.org/I78650965"],"apc_list":null,"apc_paid":null,"fwci":1.1419,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.81974487,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9988999962806702,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9980000257492065,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7984125018119812},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6319037675857544},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.6115113496780396},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5148698091506958},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.508478045463562},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.44909390807151794},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4464890658855438},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4175829589366913},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12275847792625427}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7984125018119812},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6319037675857544},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.6115113496780396},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5148698091506958},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.508478045463562},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.44909390807151794},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4464890658855438},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4175829589366913},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12275847792625427},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccad51958.2021.9643506","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad51958.2021.9643506","pdf_url":null,"source":{"id":"https://openalex.org/S4363608354","display_name":"2021 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","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":"2021 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1743861851","https://openalex.org/W1988311079","https://openalex.org/W1990832096","https://openalex.org/W1999085092","https://openalex.org/W2009654791","https://openalex.org/W2024171325","https://openalex.org/W2034940213","https://openalex.org/W2095705004","https://openalex.org/W2108598243","https://openalex.org/W2112980698","https://openalex.org/W2285660444","https://openalex.org/W2402144811","https://openalex.org/W2565851976","https://openalex.org/W2625457103","https://openalex.org/W2764043458","https://openalex.org/W2769912137","https://openalex.org/W2784372305","https://openalex.org/W2797583228","https://openalex.org/W2799197246","https://openalex.org/W2953384591","https://openalex.org/W2963163009","https://openalex.org/W2963255460","https://openalex.org/W2964299589","https://openalex.org/W2995201943","https://openalex.org/W3034733718","https://openalex.org/W3048107166","https://openalex.org/W3094218199","https://openalex.org/W3118608800","https://openalex.org/W3138781081","https://openalex.org/W4236868170","https://openalex.org/W4240168186","https://openalex.org/W4287639545","https://openalex.org/W6674330103","https://openalex.org/W6713134421","https://openalex.org/W6745148473","https://openalex.org/W6746451879","https://openalex.org/W6747876305","https://openalex.org/W6750665317","https://openalex.org/W6781736146","https://openalex.org/W6784225549"],"related_works":["https://openalex.org/W1560663560","https://openalex.org/W4287593139","https://openalex.org/W3099313426","https://openalex.org/W2136725475","https://openalex.org/W1506547947","https://openalex.org/W2086146848","https://openalex.org/W1993644742","https://openalex.org/W4206811032","https://openalex.org/W2995605830","https://openalex.org/W4239424132"],"abstract_inverted_index":{"Reducing":[0],"the":[1,35,42,145,152],"memory":[2,101,161],"footprint":[3],"of":[4,38,45,100,147],"neural":[5],"networks":[6,40],"is":[7,141],"a":[8,60],"crucial":[9],"prerequisite":[10],"for":[11,41,63,68,125,135],"deploying":[12],"them":[13],"in":[14,151,159],"small":[15],"and":[16,73,103,113,131],"low-cost":[17],"embedded":[18,77],"devices.":[19],"Network":[20],"parameters":[21],"can":[22],"often":[23],"be":[24],"reduced":[25],"significantly":[26],"through":[27,143],"pruning.":[28],"We":[29,83],"discuss":[30],"how":[31],"to":[32,121,156],"best":[33],"represent":[34],"indexing":[36],"overhead":[37,71],"sparse":[39,64,126,136],"coming":[43],"generation":[44,146],"Single":[46],"Instruction,":[47],"Multiple":[48],"Data":[49],"(SIMD)-capable":[50],"microcontrollers.":[51],"From":[52],"this,":[53],"we":[54],"develop":[55],"Delta-Compressed":[56],"Storage":[57],"Row":[58],"(dCSR),":[59],"storage":[61,72],"format":[62],"matrices":[65],"that":[66,106],"allows":[67],"both":[69],"low":[70],"fast":[74],"inference":[75],"on":[76,87],"systems":[78],"with":[79,93],"wide":[80],"SIMD":[81,153],"units.":[82],"demonstrate":[84],"our":[85,107],"method":[86,108],"an":[88,157],"ARM":[89],"Cortex-M55":[90],"MCU":[91],"prototype":[92],"M-Profile":[94],"Vector":[95],"Extension":[96],"(MVE).":[97],"A":[98],"comparison":[99],"consumption":[102],"throughput":[104,115],"shows":[105],"achieves":[109],"competitive":[110],"compression":[111],"ratios":[112],"increases":[114],"over":[116],"dense":[117],"methods":[118],"by":[119],"up":[120],"<tex":[122,132],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[123,133],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$2.9\\times$</tex>":[124],"matrix-vector":[127],"multiplication":[128,138],"(SpMV)-based":[129],"kernels":[130],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$1.06\\times$</tex>":[134],"matrix-matrix":[137],"(SpMM).":[139],"This":[140],"accomplished":[142],"handling":[144],"index":[148],"information":[149],"directly":[150],"unit,":[154],"leading":[155],"increase":[158],"effective":[160],"bandwidth.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}