{"id":"https://openalex.org/W4405440253","doi":"https://doi.org/10.1109/tc.2024.3517745","title":"A Context-Awareness and Hardware-Friendly Sparse Matrix Multiplication Kernel for CNN Inference Acceleration","display_name":"A Context-Awareness and Hardware-Friendly Sparse Matrix Multiplication Kernel for CNN Inference Acceleration","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4405440253","doi":"https://doi.org/10.1109/tc.2024.3517745"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2024.3517745","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2024.3517745","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-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/A5100383993","display_name":"Haotian Wang","orcid":"https://orcid.org/0000-0002-0086-6301"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haotian Wang","raw_affiliation_strings":["College of Information Science and Engineering, Hunan University, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101867190","display_name":"Yan Ding","orcid":"https://orcid.org/0000-0001-6956-9260"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Ding","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, Chinad"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, Chinad","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100637930","display_name":"Yumeng Liu","orcid":"https://orcid.org/0000-0003-0927-9039"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yumeng Liu","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038598144","display_name":"Weichen Liu","orcid":"https://orcid.org/0000-0001-9348-4662"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Weichen Liu","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Singapore","College of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"College of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006345319","display_name":"Chubo Liu","orcid":"https://orcid.org/0000-0002-2372-6715"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chubo Liu","raw_affiliation_strings":["College of Information Science and Engineering, Hunan University, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016247312","display_name":"Wangdong Yang","orcid":"https://orcid.org/0000-0003-2681-7898"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangdong Yang","raw_affiliation_strings":["College of Information Science and Engineering, Hunan University, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078793726","display_name":"Kenli Li","orcid":"https://orcid.org/0000-0002-2635-7716"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kenli Li","raw_affiliation_strings":["College of Information Science and Engineering, Hunan University, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100383993"],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":0.2495,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59670872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"74","issue":"4","first_page":"1182","last_page":"1195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9890000224113464,"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"}},"topics":[{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9890000224113464,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9666000008583069,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9538000226020813,"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":0.70383220911026},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6402488946914673},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6371326446533203},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6122528314590454},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5964455604553223},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5710825324058533},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.5600477457046509},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.4759865999221802},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4619346857070923},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.42620429396629333},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.41405338048934937},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.3929090201854706},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3509833812713623},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3288082480430603},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3083116412162781},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.21450382471084595},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.175807923078537}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.70383220911026},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6402488946914673},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6371326446533203},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6122528314590454},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5964455604553223},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5710825324058533},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.5600477457046509},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.4759865999221802},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4619346857070923},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.42620429396629333},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.41405338048934937},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.3929090201854706},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3509833812713623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3288082480430603},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3083116412162781},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.21450382471084595},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.175807923078537},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tc.2024.3517745","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2024.3517745","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/210680","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/210680","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1839773802","https://openalex.org/W2117539524","https://openalex.org/W2791673912","https://openalex.org/W2899244816","https://openalex.org/W3009472344","https://openalex.org/W3101151845","https://openalex.org/W3163329758","https://openalex.org/W3180562345","https://openalex.org/W3185702163","https://openalex.org/W4200300432","https://openalex.org/W4205231989","https://openalex.org/W4283368428","https://openalex.org/W4293023340","https://openalex.org/W4308090748","https://openalex.org/W4320036900","https://openalex.org/W4320063610","https://openalex.org/W4360831840","https://openalex.org/W4361019735","https://openalex.org/W4381748048","https://openalex.org/W4388667495","https://openalex.org/W4400668557","https://openalex.org/W6637151318","https://openalex.org/W6770258539","https://openalex.org/W6775374646","https://openalex.org/W6779726710","https://openalex.org/W6786262024","https://openalex.org/W6794457956","https://openalex.org/W6803607599","https://openalex.org/W6803712692","https://openalex.org/W6811466168","https://openalex.org/W6841430910","https://openalex.org/W6845974107","https://openalex.org/W6848451824","https://openalex.org/W6850052537","https://openalex.org/W6853583351","https://openalex.org/W6854171083"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W2995605830","https://openalex.org/W4206811032","https://openalex.org/W2086123442","https://openalex.org/W2596457687","https://openalex.org/W3212757063","https://openalex.org/W2093666864"],"abstract_inverted_index":{"Sparsification":[0],"technology":[1],"is":[2,18],"crucial":[3],"for":[4,32,42],"deploying":[5],"convolutional":[6,91],"neural":[7,92],"networks":[8],"in":[9,25,35],"resource-constrained":[10],"environments.":[11],"However,":[12],"the":[13,165],"efficiency":[14],"of":[15,111],"sparse":[16,26,36,45,54,74,81,125,131,166,180],"models":[17],"hampered":[19],"by":[20],"irregular":[21],"memory":[22],"access":[23],"patterns":[24],"matrix":[27,46,75,82,100,146],"multiplication":[28,47,76,83,147],"kernels.":[29,48],"Hardware-level":[30],"support":[31],"2:4":[33,71,130],"granularity":[34],"tensor":[37,167],"cores":[38],"presents":[39],"an":[40,171],"opportunity":[41],"designing":[43],"efficient":[44,145],"Existing":[49],"approaches":[50],"often":[51],"involve":[52],"adjusting":[53],"structures":[55],"or":[56],"secondary":[57],"sparsification,":[58],"introducing":[59],"additional":[60],"computational":[61],"errors.":[62],"To":[63],"tackle":[64],"this":[65],"challenge,":[66],"we":[67,95,121,143],"introduce":[68],"a":[69,79,97,109,123,184],"flexible":[70],"structured":[72],"adaptive":[73],"(FS-AMM)":[77],"method,":[78],"hardware-friendly":[80,124],"kernel":[84,168],"that":[85,103,128,160],"leverages":[86],"model":[87,98],"context":[88],"to":[89,107,114,149,178],"accelerate":[90],"networks.":[93],"First,":[94],"propose":[96],"context-aware":[99],"pre-processing":[101],"method":[102,162],"employs":[104],"heuristic":[105],"algorithms":[106],"estimate":[108],"loss":[110],"accuracy":[112],"due":[113],"weight":[115],"sparsity":[116,139],"at":[117],"each":[118],"layer.":[119],"Second,":[120],"design":[122],"storage":[126,134],"format":[127],"combines":[129],"and":[132,169],"dense":[133],"formats,":[135],"enabling":[136],"more":[137],"versatile":[138],"ratio":[140,176],"selection.":[141],"Third,":[142],"implement":[144],"kernels":[148],"optimize":[150],"GPU":[151],"utilization.":[152],"Finally,":[153],"experimental":[154],"results":[155],"on":[156],"A100":[157],"GPUs":[158],"show":[159],"our":[161],"effectively":[163],"utilizes":[164],"obtains":[170],"average":[172],"3.09":[173],"times":[174],"speedup":[175],"compared":[177],"other":[179],"methods":[181],"while":[182],"maintaining":[183],"high":[185],"accuracy.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-26T15:22:09.906841","created_date":"2025-10-10T00:00:00"}