{"id":"https://openalex.org/W4401895034","doi":"https://doi.org/10.1145/3688612","title":"Mentor: A Memory-Efficient Sparse-dense Matrix Multiplication Accelerator Based on Column-Wise Product","display_name":"Mentor: A Memory-Efficient Sparse-dense Matrix Multiplication Accelerator Based on Column-Wise Product","publication_year":2024,"publication_date":"2024-08-26","ids":{"openalex":"https://openalex.org/W4401895034","doi":"https://doi.org/10.1145/3688612"},"language":"en","primary_location":{"id":"doi:10.1145/3688612","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3688612","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1145/3688612","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004560818","display_name":"Xiaobo Lu","orcid":"https://orcid.org/0009-0005-2673-8673"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaobo Lu","raw_affiliation_strings":["School of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0005-2673-8673","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083171604","display_name":"Jianbin Fang","orcid":"https://orcid.org/0000-0003-3542-4869"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianbin Fang","raw_affiliation_strings":["School of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-3542-4869","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103142055","display_name":"Peng Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Peng","raw_affiliation_strings":["School of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-6828-3364","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101626850","display_name":"Chun Huang","orcid":"https://orcid.org/0000-0002-0317-8192"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Huang","raw_affiliation_strings":["School of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-0317-8192","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056949827","display_name":"Zidong Du","orcid":"https://orcid.org/0000-0002-7603-4210"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zidong Du","raw_affiliation_strings":["Institute Of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7603-4210","affiliations":[{"raw_affiliation_string":"Institute Of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110580984","display_name":"Yongwei Zhao","orcid":"https://orcid.org/0000-0002-5503-4457"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongwei Zhao","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5503-4457","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030293790","display_name":"Zheng Wang","orcid":"https://orcid.org/0009-0001-7858-6238"},"institutions":[{"id":"https://openalex.org/I37802460","display_name":"Northwest University","ror":"https://ror.org/00z3td547","country_code":"CN","type":"education","lineage":["https://openalex.org/I37802460"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Wang","raw_affiliation_strings":["Northwest University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0001-7858-6238","affiliations":[{"raw_affiliation_string":"Northwest University, Xi'an, China","institution_ids":["https://openalex.org/I37802460"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5004560818"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.9934,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.8006939,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"21","issue":"4","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9973000288009644,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7463950514793396},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.7256711721420288},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6288947463035583},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6235411763191223},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5935199856758118},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5854909420013428},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4999113082885742},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.47597306966781616},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4594806432723999},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3296439051628113},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14776426553726196},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13559871912002563},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.1302875578403473},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.08903199434280396}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7463950514793396},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.7256711721420288},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6288947463035583},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6235411763191223},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5935199856758118},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5854909420013428},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4999113082885742},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.47597306966781616},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4594806432723999},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3296439051628113},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14776426553726196},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13559871912002563},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.1302875578403473},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.08903199434280396},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3688612","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3688612","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3688612","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3688612","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1977661221","https://openalex.org/W1979270822","https://openalex.org/W1992114977","https://openalex.org/W2023930909","https://openalex.org/W2035080386","https://openalex.org/W2285660444","https://openalex.org/W2472334012","https://openalex.org/W2604314403","https://openalex.org/W2794952988","https://openalex.org/W2907492528","https://openalex.org/W2931118404","https://openalex.org/W2941763154","https://openalex.org/W2949674408","https://openalex.org/W2951338975","https://openalex.org/W2962946486","https://openalex.org/W2964337156","https://openalex.org/W2980113464","https://openalex.org/W2985331920","https://openalex.org/W3016542674","https://openalex.org/W3016735325","https://openalex.org/W3016832937","https://openalex.org/W3016904661","https://openalex.org/W3017228913","https://openalex.org/W3034733718","https://openalex.org/W3036955102","https://openalex.org/W3103168911","https://openalex.org/W3105753905","https://openalex.org/W3132695675","https://openalex.org/W3155922894","https://openalex.org/W3157609068","https://openalex.org/W3158831985","https://openalex.org/W3159727696","https://openalex.org/W3173204484","https://openalex.org/W3187481008","https://openalex.org/W3198975860","https://openalex.org/W3205727737","https://openalex.org/W3206453033","https://openalex.org/W3214870808","https://openalex.org/W4200390336","https://openalex.org/W4214686755","https://openalex.org/W4214734582","https://openalex.org/W4226137788","https://openalex.org/W4236868170","https://openalex.org/W4240168186","https://openalex.org/W4289441319","https://openalex.org/W4309620166","https://openalex.org/W4318540786","https://openalex.org/W4320063610","https://openalex.org/W4327930477","https://openalex.org/W4327930517","https://openalex.org/W4360831795","https://openalex.org/W4378804782","https://openalex.org/W4379116149","https://openalex.org/W4380875466","https://openalex.org/W4387323274"],"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":{"Sparse-dense":[0],"matrix":[1,130],"multiplication":[2],"(SpMM)":[3],"is":[4,78,96,159],"the":[5,37,52,116,128,138,149,169,199,220],"performance":[6,172],"bottleneck":[7],"of":[8,32,36,113,151,157,182],"many":[9],"high-performance":[10],"and":[11,39,56,109,173,208],"deep-learning":[12],"applications,":[13],"making":[14],"it":[15,141],"attractive":[16],"to":[17,71,105,126,147,167,196,206,216],"design":[18,146,156],"specialized":[19],"SpMM":[20,73,93],"hardware":[21,25,139,174,222],"accelerators.":[22,74],"Unfortunately,":[23],"existing":[24],"solutions":[26],"do":[27],"not":[28],"take":[29],"full":[30],"advantage":[31],"data":[33,107],"reuse":[34,108],"opportunities":[35],"input":[38,129],"output":[40],"matrices":[41],"or":[42],"suffer":[43],"from":[44],"irregular":[45],"memory":[46,54,111,200],"access":[47,135],"patterns.":[48],"Their":[49],"strategies":[50],"increase":[51],"off-chip":[53],"traffic":[55,201],"bandwidth":[57,210],"pressure,":[58],"leaving":[59],"much":[60],"room":[61],"for":[62,101,131],"improvement.":[63],"We":[64,176],"present":[65],"Mentor":[66,95,119,158,183,189],",":[67],"a":[68,97,121,133,143,162],"new":[69],"approach":[70,100],"designing":[72],"Our":[75],"key":[76],"insight":[77],"that":[79,188],"column-wise":[80,103,152],"dataflow,":[81],"while":[82],"rarely":[83],"exploited":[84],"in":[85,92],"prior":[86],"works,":[87],"can":[88],"address":[89],"these":[90],"issues":[91],"computations.":[94],"software-hardware":[98],"co-design":[99],"leveraging":[102],"dataflow":[104,153],"improve":[106],"regular":[110],"accesses":[112],"SpMM.":[114],"On":[115,137],"software":[117],"level,":[118,140],"incorporates":[120],"novel":[122],"streaming":[123,134],"construction":[124],"scheme":[125],"preprocess":[127],"enabling":[132],"pattern.":[136],"employs":[142],"fully":[144],"pipelined":[145],"unlock":[148],"potential":[150],"further.":[154],"The":[155],"underpinned":[160],"by":[161,192,202,212],"carefully":[163],"designed":[164],"analytical":[165],"model":[166],"find":[168],"tradeoff":[170],"between":[171],"resources.":[175],"have":[177],"implemented":[178],"an":[179],"FPGA":[180],"prototype":[181],".":[184],"Experimental":[185],"results":[186],"show":[187],"achieves":[190],"speedup":[191],"geomean":[193,203,213],"2.05\u00d7":[194],"(up":[195,205,215],"3.98\u00d7),":[197],"reduces":[198],"2.92\u00d7":[204],"4.93\u00d7),":[207],"improves":[209],"utilization":[211],"1.38\u00d7":[214],"2.89\u00d7),":[217],"compared":[218],"with":[219],"state-of-the-art":[221],"solutions.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
