DDC-PIM: Efficient Algorithm/Architecture Co-Design for Doubling Data Capacity of SRAM-Based Processing-in-Memory

Processing-in-memory (PIM), as a novel computing paradigm, provides significant performance benefits from the aspect of effective data movement reduction. SRAM-based PIM has been demonstrated as one of the most promising candidates due to its endurance and compatibility. However, the integration den...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on computer-aided design of integrated circuits and systems Ročník 43; číslo 3; s. 906 - 918
Hlavní autoři:	Duan, Cenlin, Yang, Jianlei, He, Xiaolin, Qi, Yingjie, Wang, Yikun, Wang, Yiou, He, Ziyan, Yan, Bonan, Wang, Xueyan, Jia, Xiaotao, Pan, Weitao, Zhao, Weisheng
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 01.03.2024 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Algorithm/architecture co-design Algorithms Artificial neural networks Co-design Computational modeling Computer architecture Density doubling data capacity In-memory computing Memory architecture Neural networks Parallel processing processing-in-memory (PIM) SRAM cells SRAM-PIM Static random access memory
ISSN:	0278-0070, 1937-4151
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Processing-in-memory (PIM), as a novel computing paradigm, provides significant performance benefits from the aspect of effective data movement reduction. SRAM-based PIM has been demonstrated as one of the most promising candidates due to its endurance and compatibility. However, the integration density of SRAM-based PIM is much lower than other nonvolatile memory-based ones, due to its inherent 6T structure for storing a single bit. Within comparable area constraints, SRAM-based PIM exhibits notably lower capacity. Thus, aiming to unleash its capacity potential, we propose DDC-PIM, an efficient algorithm/architecture co-design methodology that effectively doubles the equivalent data capacity. At the algorithmic level, we propose a filter-wise complementary correlation (FCC) algorithm to obtain a bitwise complementary pair. At the architecture level, we exploit the intrinsic cross-coupled structure of 6T SRAM to store the bitwise complementary pair in their complementary states <inline-formula> <tex-math notation="LaTeX">(Q/\overline {Q}) </tex-math></inline-formula>, thereby maximizing the data capacity of each SRAM cell. The dual-broadcast input structure and reconfigurable unit support both depthwise and pointwise convolution, adhering to the requirements of various neural networks. Evaluation results show that DDC-PIM yields about <inline-formula> <tex-math notation="LaTeX">2.84\times </tex-math></inline-formula> speedup on MobileNetV2 and <inline-formula> <tex-math notation="LaTeX">2.69\times </tex-math></inline-formula> on EfficientNet-B0 with negligible accuracy loss compared with PIM baseline implementation. Compared with state-of-the-art SRAM-based PIM macros, DDC-PIM achieves up to <inline-formula> <tex-math notation="LaTeX">8.41\times </tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">2.75\times </tex-math></inline-formula> improvement in weight density and area efficiency, respectively.
AbstractList	Processing-in-memory (PIM), as a novel computing paradigm, provides significant performance benefits from the aspect of effective data movement reduction. SRAM-based PIM has been demonstrated as one of the most promising candidates due to its endurance and compatibility. However, the integration density of SRAM-based PIM is much lower than other nonvolatile memory-based ones, due to its inherent 6T structure for storing a single bit. Within comparable area constraints, SRAM-based PIM exhibits notably lower capacity. Thus, aiming to unleash its capacity potential, we propose DDC-PIM, an efficient algorithm/architecture co-design methodology that effectively doubles the equivalent data capacity. At the algorithmic level, we propose a filter-wise complementary correlation (FCC) algorithm to obtain a bitwise complementary pair. At the architecture level, we exploit the intrinsic cross-coupled structure of 6T SRAM to store the bitwise complementary pair in their complementary states [Formula Omitted], thereby maximizing the data capacity of each SRAM cell. The dual-broadcast input structure and reconfigurable unit support both depthwise and pointwise convolution, adhering to the requirements of various neural networks. Evaluation results show that DDC-PIM yields about [Formula Omitted] speedup on MobileNetV2 and [Formula Omitted] on EfficientNet-B0 with negligible accuracy loss compared with PIM baseline implementation. Compared with state-of-the-art SRAM-based PIM macros, DDC-PIM achieves up to [Formula Omitted] and [Formula Omitted] improvement in weight density and area efficiency, respectively. Processing-in-memory (PIM), as a novel computing paradigm, provides significant performance benefits from the aspect of effective data movement reduction. SRAM-based PIM has been demonstrated as one of the most promising candidates due to its endurance and compatibility. However, the integration density of SRAM-based PIM is much lower than other nonvolatile memory-based ones, due to its inherent 6T structure for storing a single bit. Within comparable area constraints, SRAM-based PIM exhibits notably lower capacity. Thus, aiming to unleash its capacity potential, we propose DDC-PIM, an efficient algorithm/architecture co-design methodology that effectively doubles the equivalent data capacity. At the algorithmic level, we propose a filter-wise complementary correlation (FCC) algorithm to obtain a bitwise complementary pair. At the architecture level, we exploit the intrinsic cross-coupled structure of 6T SRAM to store the bitwise complementary pair in their complementary states <inline-formula> <tex-math notation="LaTeX">(Q/\overline {Q}) </tex-math></inline-formula>, thereby maximizing the data capacity of each SRAM cell. The dual-broadcast input structure and reconfigurable unit support both depthwise and pointwise convolution, adhering to the requirements of various neural networks. Evaluation results show that DDC-PIM yields about <inline-formula> <tex-math notation="LaTeX">2.84\times </tex-math></inline-formula> speedup on MobileNetV2 and <inline-formula> <tex-math notation="LaTeX">2.69\times </tex-math></inline-formula> on EfficientNet-B0 with negligible accuracy loss compared with PIM baseline implementation. Compared with state-of-the-art SRAM-based PIM macros, DDC-PIM achieves up to <inline-formula> <tex-math notation="LaTeX">8.41\times </tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">2.75\times </tex-math></inline-formula> improvement in weight density and area efficiency, respectively.
Author	He, Xiaolin Wang, Xueyan Jia, Xiaotao Duan, Cenlin Yang, Jianlei Wang, Yiou Zhao, Weisheng Qi, Yingjie Pan, Weitao Wang, Yikun He, Ziyan Yan, Bonan
Author_xml	– sequence: 1 givenname: Cenlin surname: Duan fullname: Duan, Cenlin organization: School of Integrated Circuit Science and Engineering, BDBC, Fert Beijing Research Institute, Beijing, China – sequence: 2 givenname: Jianlei orcidid: 0000-0001-8424-7040 surname: Yang fullname: Yang, Jianlei email: jianlei@buaa.edu.cn organization: School of Computer Science and Engineering, BDBC, Fert Beijing Research Institute, Beijing, China – sequence: 3 givenname: Xiaolin surname: He fullname: He, Xiaolin organization: School of Computer Science and Engineering, BDBC, Fert Beijing Research Institute, Beijing, China – sequence: 4 givenname: Yingjie orcidid: 0009-0009-2785-4480 surname: Qi fullname: Qi, Yingjie organization: Institute of Artificial Intelligence, Peking University, Beijing, China – sequence: 5 givenname: Yikun surname: Wang fullname: Wang, Yikun organization: School of Computer Science and Engineering, BDBC, Fert Beijing Research Institute, Beijing, China – sequence: 6 givenname: Yiou surname: Wang fullname: Wang, Yiou organization: School of Computer Science and Engineering, BDBC, Fert Beijing Research Institute, Beijing, China – sequence: 7 givenname: Ziyan surname: He fullname: He, Ziyan organization: State Key Laboratory of Integrated Service Networks, Xidian University, Xi'an, China – sequence: 8 givenname: Bonan orcidid: 0000-0002-3052-9330 surname: Yan fullname: Yan, Bonan organization: Institute of Artificial Intelligence, Peking University, Beijing, China – sequence: 9 givenname: Xueyan orcidid: 0000-0003-0080-4730 surname: Wang fullname: Wang, Xueyan organization: School of Integrated Circuit Science and Engineering, BDBC, Fert Beijing Research Institute, Beijing, China – sequence: 10 givenname: Xiaotao orcidid: 0000-0003-2207-6092 surname: Jia fullname: Jia, Xiaotao organization: School of Integrated Circuit Science and Engineering, BDBC, Fert Beijing Research Institute, Beijing, China – sequence: 11 givenname: Weitao orcidid: 0000-0002-6388-5008 surname: Pan fullname: Pan, Weitao organization: State Key Laboratory of Integrated Service Networks, Xidian University, Xi'an, China – sequence: 12 givenname: Weisheng orcidid: 0000-0001-8088-0404 surname: Zhao fullname: Zhao, Weisheng email: weisheng.zhao@buaa.edu.cn organization: School of Integrated Circuit Science and Engineering, BDBC, Fert Beijing Research Institute, Beijing, China
BookMark	eNp9kMFuEzEQQC1UJNLCByBxsMTZ6Yztjdfclt0ClRpRQTmvvF47dZWsU9s55O-7UXpAHJAPc3lvRn6X5GKKkyPkI8ISEfT1Q9t0Sw5cLIUQUKN-QxaohWISK7wgC-CqZgAK3pHLnJ8AUFZcL8hz17Xs_nb9hd54H2xwU6HNdhNTKI-76ybZx1CcLYfkaBtZ53LYTNTHRLt4GLZh2tDOFENbszc2lCONnv7-1azZV5PdSO9TtC7nGWNhYmu3i-n4nrz1Zpvdh9d5Rf58u3lof7C7n99v2-aOWa5lYdUAUkoBehiltSNqp-qhNoPQBrRc6VXNFXrJx1GNCHb0tqpBrCrvcSWFQXFFPp_37lN8Prhc-qd4SNN8sud6fpVWHGZKnSmbYs7J-X7-hikhTiWZsO0R-lPf_tS3P_XtX_vOJv5j7lPYmXT8r_Pp7ATn3F-8QBRaiRdSIoZ7
CODEN	ITCSDI
CitedBy_id	crossref_primary_10_1109_TVLSI_2024_3502359 crossref_primary_10_1145_3707205
Cites_doi	10.1109/ISSCC42615.2023.10067285 10.1109/TCSI.2021.3055830 10.1109/ISSCC19947.2020.9062995 10.1109/TC.2021.3087946 10.1109/ISVLSI.2014.94 10.1109/WACV56688.2023.00229 10.1109/ICASSP.2017.7953077 10.5555/3298023.3298188 10.1109/isscc42615.2023.10067842 10.1109/DAC18072.2020.9218660 10.1109/ISSCC.2018.8310398 10.1109/JSSC.2020.3031290 10.1109/JSSC.2022.3213542 10.1109/DAC18072.2020.9218710 10.1145/3299874.3319483 10.1109/ISSCC42615.2023.10067779 10.1109/CVPR.2016.90 10.1109/CVPR52729.2023.01525 10.1145/3065386 10.1109/TCAD.2022.3163628 10.23919/VLSICircuits52068.2021.9492403 10.1109/TC.2022.3155277 10.1109/JETCAS.2022.3170152 10.1038/s41928-023-01010-1 10.1109/CVPR52729.2023.01855 10.1109/JSSC.2017.2782087 10.1109/JPROC.2020.2976475 10.1109/ISSCC42615.2023.10067360 10.1109/ISSCC19947.2020.9062949 10.1038/s41928-021-00676-9 10.1109/JSSC.2017.2776302 10.1109/CVPR52729.2023.01385 10.1109/ISSCC42613.2021.9365766 10.1109/ISSCC42614.2022.9731545 10.1109/TCSI.2022.3185135
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/TCAD.2023.3330819
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Xplore CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1937-4151
EndPage	918
ExternalDocumentID	10_1109_TCAD_2023_3330819 10311397
Genre	orig-research
GrantInformation_xml	– fundername: 111 Talent Program grantid: B16001 – fundername: Fundamental Research Funds for the Central Universities funderid: 10.13039/501100012226 – fundername: National Natural Science Foundation of China grantid: 62072019; 62006011; 62004011 funderid: 10.13039/501100001809
GroupedDBID	--Z -~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFS ACIWK ACNCT AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 IBMZZ ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P PZZ RIA RIE RNS TN5 VH1 VJK AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c294t-5b0444309bd4ccd19e78b8ab39a0946968271f42dd7d10cdfc580365ff1643a13
IEDL.DBID	RIE
ISICitedReferencesCount	4
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001170495100023&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0278-0070
IngestDate	Mon Jun 30 08:24:00 EDT 2025 Sat Nov 29 03:31:52 EST 2025 Tue Nov 18 21:31:46 EST 2025 Wed Aug 27 02:33:11 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	3
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c294t-5b0444309bd4ccd19e78b8ab39a0946968271f42dd7d10cdfc580365ff1643a13
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0009-0009-2785-4480 0000-0003-0080-4730 0000-0002-6388-5008 0000-0002-3052-9330 0000-0001-8088-0404 0000-0003-2207-6092 0000-0001-8424-7040
PQID	2929259720
PQPubID	85470
PageCount	13
ParticipantIDs	crossref_citationtrail_10_1109_TCAD_2023_3330819 proquest_journals_2929259720 ieee_primary_10311397 crossref_primary_10_1109_TCAD_2023_3330819
PublicationCentury	2000
PublicationDate	2024-03-01
PublicationDateYYYYMMDD	2024-03-01
PublicationDate_xml	– month: 03 year: 2024 text: 2024-03-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on computer-aided design of integrated circuits and systems
PublicationTitleAbbrev	TCAD
PublicationYear	2024
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref35 ref12 ref34 ref15 ref37 ref14 ref36 Huang (ref39) 2021 ref31 ref30 ref11 ref33 ref32 ref2 ref1 ref17 ref38 ref19 ref18 ref24 ref23 ref26 ref25 ref20 ref22 ref21 Tan (ref10) ref28 ref27 Howard (ref9) 2017 ref29 ref8 ref7 ref4 ref3 ref6 ref5 Imani (ref16)
References_xml	– ident: ref31 doi: 10.1109/ISSCC42615.2023.10067285 – ident: ref18 doi: 10.1109/TCSI.2021.3055830 – ident: ref24 doi: 10.1109/ISSCC19947.2020.9062995 – ident: ref37 doi: 10.1109/TC.2021.3087946 – ident: ref32 doi: 10.1109/ISVLSI.2014.94 – ident: ref4 doi: 10.1109/WACV56688.2023.00229 – start-page: 802 volume-title: Proc. Int. Symp. Comput. Archit. (ISCA) ident: ref16 article-title: FloatPIM: In-memory acceleration of deep neural network training with high precision – ident: ref5 doi: 10.1109/ICASSP.2017.7953077 – ident: ref2 doi: 10.5555/3298023.3298188 – ident: ref30 doi: 10.1109/isscc42615.2023.10067842 – ident: ref19 doi: 10.1109/DAC18072.2020.9218660 – ident: ref12 doi: 10.1109/ISSCC.2018.8310398 – ident: ref22 doi: 10.1109/JSSC.2020.3031290 – ident: ref27 doi: 10.1109/JSSC.2022.3213542 – ident: ref38 doi: 10.1109/DAC18072.2020.9218710 – ident: ref15 doi: 10.1145/3299874.3319483 – ident: ref28 doi: 10.1109/ISSCC42615.2023.10067779 – ident: ref3 doi: 10.1109/CVPR.2016.90 – year: 2021 ident: ref39 article-title: Accelerating sparse deep neural networks publication-title: arXiv:2104.08378 – ident: ref8 doi: 10.1109/CVPR52729.2023.01525 – ident: ref1 doi: 10.1145/3065386 – ident: ref17 doi: 10.1109/TCAD.2022.3163628 – ident: ref11 doi: 10.23919/VLSICircuits52068.2021.9492403 – ident: ref20 doi: 10.1109/TC.2022.3155277 – ident: ref34 doi: 10.1109/JETCAS.2022.3170152 – ident: ref33 doi: 10.1038/s41928-023-01010-1 – ident: ref7 doi: 10.1109/CVPR52729.2023.01855 – ident: ref21 doi: 10.1109/JSSC.2017.2782087 – ident: ref36 doi: 10.1109/JPROC.2020.2976475 – ident: ref29 doi: 10.1109/ISSCC42615.2023.10067360 – ident: ref13 doi: 10.1109/ISSCC19947.2020.9062949 – ident: ref35 doi: 10.1038/s41928-021-00676-9 – ident: ref23 doi: 10.1109/JSSC.2017.2776302 – year: 2017 ident: ref9 article-title: MobileNets: Efficient convolutional neural networks for mobile vision applications publication-title: arXiv:1704.04861 – ident: ref6 doi: 10.1109/CVPR52729.2023.01385 – ident: ref26 doi: 10.1109/ISSCC42613.2021.9365766 – start-page: 1 volume-title: Proc. Int. Conf. Mach. Learn. (ICML) ident: ref10 article-title: EfficientNet: Rethinking model scaling for convolutional neural networks – ident: ref14 doi: 10.1109/ISSCC42614.2022.9731545 – ident: ref25 doi: 10.1109/TCSI.2022.3185135
SSID	ssj0014529
Score	2.4392455
Snippet	Processing-in-memory (PIM), as a novel computing paradigm, provides significant performance benefits from the aspect of effective data movement reduction....
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	906
SubjectTerms	Algorithm/architecture co-design Algorithms Artificial neural networks Co-design Computational modeling Computer architecture Density doubling data capacity In-memory computing Memory architecture Neural networks Parallel processing processing-in-memory (PIM) SRAM cells SRAM-PIM Static random access memory
Title	DDC-PIM: Efficient Algorithm/Architecture Co-Design for Doubling Data Capacity of SRAM-Based Processing-in-Memory
URI	https://ieeexplore.ieee.org/document/10311397 https://www.proquest.com/docview/2929259720
Volume	43
WOSCitedRecordID	wos001170495100023&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1937-4151 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014529 issn: 0278-0070 databaseCode: RIE dateStart: 19820101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFG6EeNCDPzGiaHrwZFLofnb1hgyjBwhRTLgtW9spCTKFYeJ_b183yBKjibcdumbd1-291_fe9yF05SjJY5BJValwietLRmIqfSJkwnwl_IBJ14hNsOEwmEz4qGxWN70wSilTfKbacGly-TITKzgq64AkAXgsNVRjjBXNWpuUAWQQzYEKUMbqjVymMC3KO2O9qjbohLcdHb4HwKpTMUJGVeXHr9jYl7v9fz7ZAdorHUncLZA_RFtqfoR2K_SCx-gjDHtk9DC4wX1DFKGnwN3ZS7aY5q9vnW4lhYB7GQlNLQfWTizWXnUCbeo4jPMY97Q9FdpZx1mKnx67A3KrLZ_EZYuBHkamczKAit2vBnq-649796SUWCDC5m5OvAT44hzKE-kKIS2uWJAEceJoALkLxDk2s1LXlpJJiwqZCi_QNs9LUx1mObHlnKD6PJurU4QlZ0IENAZBdld4fqDSJFFcz516saROE9H1O49EyT8OMhizyMQhlEcAUwQwRSVMTXS9ueW9IN_4a3ADcKkMLCBpotYa2aj8PpeRrb1CHfgxm579cts52oGFFOVmLVTPFyt1gbbFZz5dLi7N1vsGdQLUkw
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Nj9MwEB1BQQIOfC7aQmF94LSSWydx4phb6YdabVtVUKTeosR2oFK32W1TpP3363HSqtIKJG45OFac52RmPDPvAXwJjJYpyqSaXHHKIy1oynRElc5EZFQUC82d2ISYzeLlUs7rZnXXC2OMccVnpo2XLpevC7XHo7IOShKgx_IYnoSc-17VrnVMGmAO0R2pIGms3cp1EtNjsrOw62qjUng7sAF8jLw6J2bI6ao8-Bk7CzN89Z_P9hpe1q4k6VbYv4FHZvMWXpwQDL6D236_R-fj6VcycFQRdgrSXf8qtqvy93Wne5JEIL2C9l01B7FuLLF-dYaN6qSflinpWYuqrLtOipz8-N6d0m_W9mlSNxnYYXS1oVOs2b07g5_DwaI3orXIAlW-5CUNM2SMC5jMNFdKe9KIOIvTLLAQSo7UOb7wcu5rLbTHlM5VGFurF-a5DbSC1AveQ2NTbMw5EC2FUjFLUZKdqzCKTZ5lRtq58zDVLGgCO7zzRNUM5CiEsU5cJMJkgjAlCFNSw9SEy-MtNxX9xr8GnyEuJwMrSJrQOiCb1F_oLvGtX2hDP-GzD3-57QKejRbTSTIZz64-wnNcVFV81oJGud2bT_BU_SlXu-1ntw3vAa8M19o
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=DDC-PIM%3A+Efficient+Algorithm%2FArchitecture+Co-Design+for+Doubling+Data+Capacity+of+SRAM-Based+Processing-in-Memory&rft.jtitle=IEEE+transactions+on+computer-aided+design+of+integrated+circuits+and+systems&rft.au=Duan%2C+Cenlin&rft.au=Yang%2C+Jianlei&rft.au=He%2C+Xiaolin&rft.au=Qi%2C+Yingjie&rft.date=2024-03-01&rft.issn=0278-0070&rft.eissn=1937-4151&rft.volume=43&rft.issue=3&rft.spage=906&rft.epage=918&rft_id=info:doi/10.1109%2FTCAD.2023.3330819&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TCAD_2023_3330819
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0278-0070&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0278-0070&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0278-0070&client=summon