{"id":"https://openalex.org/W4414198387","doi":"https://doi.org/10.1109/dac63849.2025.11133288","title":"CIM-BLAS: Computing-in-Memory Accelerator for BLAS","display_name":"CIM-BLAS: Computing-in-Memory Accelerator for BLAS","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4414198387","doi":"https://doi.org/10.1109/dac63849.2025.11133288"},"language":"en","primary_location":{"id":"doi:10.1109/dac63849.2025.11133288","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11133288","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100448519","display_name":"Rui Liu","orcid":"https://orcid.org/0000-0002-6515-652X"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Liu","raw_affiliation_strings":["Institute of Computing Technology,Chinese Academy of Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology,Chinese Academy of Science","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069146197","display_name":"Zerun Li","orcid":"https://orcid.org/0000-0002-7672-0667"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zerun Li","raw_affiliation_strings":["Institute of Computing Technology,Chinese Academy of Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology,Chinese Academy of Science","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115596181","display_name":"Xiaoyu Zhang","orcid":"https://orcid.org/0000-0002-1752-5482"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Zhang","raw_affiliation_strings":["Institute of Computing Technology,Chinese Academy of Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology,Chinese Academy of Science","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoming Chen","orcid":null},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoming Chen","raw_affiliation_strings":["Institute of Computing Technology,Chinese Academy of Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology,Chinese Academy of Science","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016864694","display_name":"Yinhe Han","orcid":"https://orcid.org/0000-0003-0904-6681"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinhe Han","raw_affiliation_strings":["Institute of Computing Technology,Chinese Academy of Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology,Chinese Academy of Science","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101884040","display_name":"Minghua Tang","orcid":"https://orcid.org/0000-0002-0369-9166"},"institutions":[{"id":"https://openalex.org/I4610292","display_name":"Xiangtan University","ror":"https://ror.org/00xsfaz62","country_code":"CN","type":"education","lineage":["https://openalex.org/I4610292"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghua Tang","raw_affiliation_strings":["Xiangtan University,School of Materials Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiangtan University,School of Materials Science and Engineering","institution_ids":["https://openalex.org/I4610292"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27839685,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9797999858856201,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9797999858856201,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.929099977016449,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9136000275611877,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/bottleneck","display_name":"Bottleneck","score":0.7035999894142151},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6829000115394592},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6079999804496765},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.47519999742507935},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4636000096797943},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4375999867916107},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.37059998512268066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8195000290870667},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7035999894142151},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6829000115394592},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6079999804496765},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5575000047683716},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.48890000581741333},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.47519999742507935},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4636000096797943},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4375999867916107},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.362199991941452},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.32659998536109924},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2529999911785126},{"id":"https://openalex.org/C2982832238","wikidata":"https://www.wikidata.org/wiki/Q5531640","display_name":"General purpose","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac63849.2025.11133288","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11133288","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324780","display_name":"Xiangtan University","ror":"https://ror.org/00xsfaz62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W36826159","https://openalex.org/W1839773802","https://openalex.org/W1988425770","https://openalex.org/W2002257715","https://openalex.org/W2006384005","https://openalex.org/W2038469228","https://openalex.org/W2069345435","https://openalex.org/W2116513702","https://openalex.org/W2155589054","https://openalex.org/W2208150243","https://openalex.org/W2508602506","https://openalex.org/W2891550056","https://openalex.org/W2972686555","https://openalex.org/W2982974103","https://openalex.org/W3033443178","https://openalex.org/W3209041109","https://openalex.org/W3212662098","https://openalex.org/W4206625779","https://openalex.org/W4213334477","https://openalex.org/W4213366639","https://openalex.org/W4213444069","https://openalex.org/W4243519499","https://openalex.org/W4292121737","https://openalex.org/W4313476549","https://openalex.org/W4392897316"],"related_works":[],"abstract_inverted_index":{"Basic":[0],"Linear":[1],"Algebra":[2],"Subprograms":[3],"(BLAS)":[4],"is":[5,15,64,101],"a":[6,88],"foundational":[7],"software":[8],"library":[9],"for":[10,67,79,128,145,172],"linear":[11],"algebra":[12],"kernels,":[13],"which":[14],"widely":[16],"used":[17],"in":[18,34],"scientific":[19],"and":[20,30,50,63,124,131,135],"engineering":[21],"computing.":[22],"Existing":[23],"BLAS":[24,35,111,133,148],"accelerations":[25],"mainly":[26],"rely":[27],"on":[28,83],"CPUs":[29,49],"GPUs.":[31,51],"Many":[32],"operations":[33],"are":[36,41],"data":[37,106],"intensive,":[38],"so":[39],"they":[40],"constrained":[42],"by":[43,103],"the":[44,59,75,99,154,157,168],"limited":[45],"memory":[46,60],"bandwidth":[47],"of":[48,98,121,142,156,162,170],"The":[52,150],"computing-in-memory":[53],"(CIM)":[54],"technology":[55],"can":[56,136],"effectively":[57],"alleviate":[58],"wall":[61],"bottleneck":[62],"particularly":[65],"suitable":[66],"accelerating":[68,173],"BLAS.":[69,174],"In":[70],"this":[71],"paper,":[72],"we":[73],"propose":[74],"first":[76],"CIM":[77,171],"accelerator":[78,100],"BLAS,":[80],"CIM-BLAS,":[81],"based":[82],"non-volatile":[84],"memory.":[85],"CIM-BLAS":[86],"includes":[87],"unified":[89],"floating-point":[90],"pipeline":[91],"to":[92,108],"support":[93,109],"high-precision":[94],"arithmetics.":[95],"High":[96],"efficiency":[97,126,140],"achieved":[102],"developing":[104],"configurable":[105],"flows":[107],"various":[110],"functions.":[112,149],"Compared":[113],"with":[114,153],"GPU":[115],"implementations,":[116],"CIMBLAS":[117],"demonstrates":[118],"several":[119],"orders":[120],"magnitude":[122],"performance":[123],"energy":[125,139],"improvements":[127],"executing":[129,146],"level-1":[130],"level-2":[132],"functions,":[134],"achieve":[137],"an":[138],"improvement":[141,151],"2.6-24.1":[143],"$\\times$":[144],"level-3":[147],"increases":[152],"size":[155],"matrix,":[158],"indicating":[159],"excellent":[160],"scalability":[161],"CIM-BLAS.":[163],"Application-level":[164],"evaluations":[165],"also":[166],"demonstrate":[167],"potential":[169]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}