{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T22:06:55Z","timestamp":1783634815525,"version":"3.55.0"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T00:00:00Z","timestamp":1619481600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T00:00:00Z","timestamp":1619481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1007\/s11432-020-3227-1","type":"journal-article","created":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T04:09:00Z","timestamp":1620101340000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":279,"title":["Breaking the von Neumann bottleneck: architecture-level processing-in-memory technology"],"prefix":"10.1007","volume":"64","author":[{"given":"Xingqi","family":"Zou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoming","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinhe","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,4,27]]},"reference":[{"key":"3227_CR1","doi-asserted-by":"publisher","first-page":"75","DOI":"10.3390\/make1010005","volume":"1","author":"S Mittal","year":"2018","unstructured":"Mittal S. A survey of ReRAM-based architectures for processing-in-memory and neural networks. Mach Learn Knowl Extr, 2018, 1: 75\u2013114","journal-title":"Mach Learn Knowl Extr"},{"key":"3227_CR2","doi-asserted-by":"crossref","unstructured":"Chen L R, Li J W, Chen Y R, et al. Accelerator-friendly neural-network training: learning variations and defects in RRAM crossbar. In: Proceedings of Design, Automation & Test in Europe Conference & Exhibition (DATE), Lausanne, 2017. 19\u201324","DOI":"10.23919\/DATE.2017.7926952"},{"key":"3227_CR3","doi-asserted-by":"crossref","unstructured":"Chen W H, Li K X, Lin W Y, et al. A 65 nm 1 Mb nonvolatile computing-in-memory ReRAM macro with sub-16 ns multiply-and-accumulate for binary DNN AI edge processors. In: Proceedings of IEEE International Solid-State Circuits Conference, San Francisco, 2018. 494\u2013496","DOI":"10.1109\/ISSCC.2018.8310400"},{"key":"3227_CR4","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1038\/s41928-019-0270-x","volume":"2","author":"F Cai","year":"2019","unstructured":"Cai F, Correll J M, Lee S H, et al. A fully integrated reprogrammable memristor-CMOS system for efficient multiply-accumulate operations. Nat Electron, 2019, 2: 290\u2013299","journal-title":"Nat Electron"},{"key":"3227_CR5","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1038\/s41586-020-1942-4","volume":"577","author":"P Yao","year":"2020","unstructured":"Yao P, Wu H, Gao B, et al. Fully hardware-implemented memristor convolutional neural network. Nature, 2020, 577: 641\u2013646","journal-title":"Nature"},{"key":"3227_CR6","doi-asserted-by":"crossref","unstructured":"Burr G W, Shelby R M, Sidler S, et al. Experimental demonstration and tolerancing of a large-scale neural network (165000 synapses) using phase-change memory as the synaptic weight element. In: Proceedings of IEEE International Electron Devices Meeting, 2015. 3498\u20133507","DOI":"10.1109\/TED.2015.2439635"},{"key":"3227_CR7","doi-asserted-by":"crossref","unstructured":"Guo X, Bayat F M, Bavandpour M, et al. Fast, energy-efficient, robust, and reproducible mixed-signal neuromorphic classifier based on embedded NOR flash memory technology. In: Proceedings of IEEE International Electron Devices Meeting (IEDM), San Francisco, 2017. 1\u20134","DOI":"10.1109\/IEDM.2017.8268341"},{"key":"3227_CR8","doi-asserted-by":"crossref","unstructured":"Jiang Z, Yin S, Seo J S, et al. XNOR-SRAM: in-bitcell computing SRAM Macro based on resistive computing mechanism. In: Proceedings of the 2019 on Great Lakes Symposium on VLSI, 2019. 417\u2013422","DOI":"10.1145\/3299874.3319458"},{"key":"3227_CR9","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1109\/JSSC.2019.2899730","volume":"54","author":"H Valavi","year":"2019","unstructured":"Valavi H, Ramadge P J, Nestler E, et al. A 64-Tile 2.4-Mb in-memory-computing CNN accelerator employing charge-domain compute. IEEE J Solid-State Circ, 2019, 54: 1789\u20131799","journal-title":"IEEE J Solid-State Circ"},{"key":"3227_CR10","doi-asserted-by":"crossref","unstructured":"Seshadri V, Lee D, Mullins T, et al. Ambit: in-memory accelerator for bulk bitwise operations using commodity DRAM technology. In: Proceedings of the 50th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO), Boston, 2017. 273\u2013287","DOI":"10.1145\/3123939.3124544"},{"key":"3227_CR11","doi-asserted-by":"crossref","unstructured":"Li S, Niu D, Malladi K T, et al. DRISA: a DRAM-based reconfigurable in-situ accelerator. In: Proceedings of the 50th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO), Boston, 2017. 288\u2013301","DOI":"10.1145\/3123939.3123977"},{"key":"3227_CR12","doi-asserted-by":"crossref","unstructured":"Angizi S, Fan D. ReDRAM: a reconfigurable processing-in-DRAM platform for accelerating bulk bit-wise operations. In: Proceedings of IEEE\/ACM International Conference on Computer-Aided Design (ICCAD), Westminster, 2019. 1\u20138","DOI":"10.1109\/ICCAD45719.2019.8942101"},{"key":"3227_CR13","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1109\/T-C.1969.222754","volume":"18","author":"W H Kautz","year":"1969","unstructured":"Kautz W H. Cellular logic-in-memory arrays. IEEE Trans Comput, 1969, 18: 719\u2013727","journal-title":"IEEE Trans Comput"},{"key":"3227_CR14","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1109\/TC.1970.5008902","volume":"19","author":"H S Stone","year":"1970","unstructured":"Stone H S. A logic-in-memory computer. IEEE Trans Comput, 1970, 19: 73\u201378","journal-title":"IEEE Trans Comput"},{"key":"3227_CR15","doi-asserted-by":"publisher","first-page":"102868","DOI":"10.1016\/j.micpro.2019.102868","volume":"71","author":"G Singh","year":"2019","unstructured":"Singh G, Chelini L, Corda S, et al. Near-memory computing: past, present, and future. Microprocessors Microsyst, 2019, 71: 102868","journal-title":"Microprocessors Microsyst"},{"key":"3227_CR16","doi-asserted-by":"crossref","unstructured":"Jeddeloh J, Keeth B. Hybrid memory cube new DRAM architecture increases density and performance. In: Proceedings of Symposium on VLSI Technology (VLSIT), 2012","DOI":"10.1109\/VLSIT.2012.6242474"},{"key":"3227_CR17","unstructured":"Dong U L, Kyung W K, Kwan W K, et al. 25.2 A 1.2 V 8 Gb 8-channel 128 GB\/s high-bandwidth memory (HBM) stacked DRAM with effective microbump I\/O test methods using 29 nm process and TSV. In: Proceedings of IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC), San Francisco, 2014. 432\u2013433"},{"key":"3227_CR18","doi-asserted-by":"crossref","unstructured":"Devaux F. The true processing in memory accelerator. In: Proceedings of IEEE Hot Chips 31 Symposium (HCS), Cupertino, 2019. 1\u201324","DOI":"10.1109\/HOTCHIPS.2019.8875680"},{"key":"3227_CR19","unstructured":"Consortium. Hybrid memory cube specification 2.1, 2015"},{"key":"3227_CR20","doi-asserted-by":"crossref","unstructured":"Zhuo Y, Wang C, Zhang M, et al. GraphQ: scalable PIM-based graph processing. In: Proceedings of the 52nd Annual IEEE\/ACM International Symposium, 2019. 712\u2013725","DOI":"10.1145\/3352460.3358256"},{"key":"3227_CR21","doi-asserted-by":"crossref","unstructured":"He M, Song C, Kim I, et al. Newton: a DRAM-maker\u2019s accelerator-in-memory (AiM) architecture for machine learning. In: Proceedings of the 53rd Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO), Athens, 2020. 372\u2013385","DOI":"10.1109\/MICRO50266.2020.00040"},{"key":"3227_CR22","doi-asserted-by":"crossref","unstructured":"Boroumand A, Zheng H, Mutlu O, et al. CoNDA: efficient cache coherence support for near-data accelerators. In: Proceedings of ACM\/IEEE 46th Annual International Symposium on Computer Architecture (ISCA), Phoenix, 2019. 629\u2013642","DOI":"10.1145\/3307650.3322266"},{"key":"3227_CR23","doi-asserted-by":"crossref","unstructured":"Ahn J, Yoo S, Mutlu O, et al. PIM-enabled instructions: a low-overhead, locality-aware processing-in-memory architecture. In: Proceedings of ACM\/IEEE 42nd Annual International Symposium on Computer Architecture (ISCA), Portland, 2015. 336\u2013348","DOI":"10.1145\/2749469.2750385"},{"key":"3227_CR24","doi-asserted-by":"crossref","unstructured":"Cheng L, Muralimanohar N, Ramani K, et al. Interconnect-aware coherence protocols for chip multiprocessors. In: Proceedings of the 33rd International Symposium on Computer Architecture (ISCA), Boston, 2006. 339\u2013351","DOI":"10.1145\/1150019.1136515"},{"key":"3227_CR25","doi-asserted-by":"crossref","unstructured":"Baer J L, Wang W H. On the inclusion properties for multi-level cache hierarchies. In: Proceedings of the 15th Annual International Symposium on Computer Architecture, Honolulu, 1988. 73\u201380","DOI":"10.1145\/633625.52409"},{"key":"3227_CR26","doi-asserted-by":"crossref","unstructured":"Imani M, Gupta S, Rosing T. Ultra-efficient processing in-memory for data intensive applications. In: Proceedings of the 54th ACM\/EDAC\/IEEE Design Automation Conference (DAC), Austin, 2017. 1\u20136","DOI":"10.1145\/3061639.3062337"},{"key":"3227_CR27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-30695-7_2","volume-title":"Design and evaluation of a processing-in-memory architecture for the smart memory cube","author":"E Azarkhish","year":"2016","unstructured":"Azarkhish E, Rossi D, Loi I, et al. Design and evaluation of a processing-in-memory architecture for the smart memory cube. In: Proceedings of International Conference on Architecture of Computing Systems. Berlin: Springer, 2016"},{"key":"3227_CR28","doi-asserted-by":"crossref","unstructured":"Farmahini-Farahani A, Ahn J H, Morrow K, et al. NDA: near-DRAM acceleration architecture leveraging commodity DRAM devices and standard memory modules. In: Proceedings of IEEE 21st International Symposium on High Performance Computer Architecture (HPCA), Burlingame, 2015. 283\u2013295","DOI":"10.1109\/HPCA.2015.7056040"},{"key":"3227_CR29","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1109\/LCA.2016.2577557","volume":"16","author":"A Boroumand","year":"2017","unstructured":"Boroumand A, Ghose S, Patel M, et al. LazyPIM: an efficient cache coherence mechanism for processing-in-memory. IEEE Comput Arch Lett, 2017, 16: 46\u201350","journal-title":"IEEE Comput Arch Lett"},{"key":"3227_CR30","first-page":"140","volume-title":"CuckooPIM: an efficient and less-blocking coherence mechanism for processing-in-memory systems","author":"S Xu","year":"2019","unstructured":"Xu S, Chen X, Wang Y, et al. CuckooPIM: an efficient and less-blocking coherence mechanism for processing-in-memory systems. In: Proceedings of the 24th Asia and South Pacific Design Automation Conference (ASPDAC\u201919). New York: Association for Computing Machinery, 2019. 140\u2013145"},{"key":"3227_CR31","doi-asserted-by":"crossref","unstructured":"Xu S, Wang Y, Han Y, et al. PIMCH: cooperative memory prefetching in processing-in-memory architecture. In: Proceedings of the 23rd Asia and South Pacific Design Automation Conference (ASP-DAC), Jeju, 2018. 209\u2013214","DOI":"10.1109\/ASPDAC.2018.8297307"},{"key":"3227_CR32","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1109\/MM.2005.6","volume":"25","author":"K J Nesbit","year":"2005","unstructured":"Nesbit K J, Smith J E. Data cache prefetching using a global history buffer. IEEE Micro, 2005, 25: 90\u201397","journal-title":"IEEE Micro"},{"key":"3227_CR33","first-page":"499","volume":"13","author":"Y Ishii","year":"2011","unstructured":"Ishii Y, Inaba M, Hiraki K. Access map pattern matching for high performance data cache prefetch. J Instruction-Level Parallelism, 2011, 13: 499\u2013500","journal-title":"J Instruction-Level Parallelism"},{"key":"3227_CR34","doi-asserted-by":"crossref","unstructured":"Ahn J, Hong S, Yoo S, et al. A scalable processing-in-memory accelerator for parallel graph processing. In: Proceedings of 2015 ACM\/IEEE 42nd Annual International Symposium on Computer Architecture (ISCA), Portland, 2015. 105\u2013117","DOI":"10.1145\/2749469.2750386"},{"key":"3227_CR35","doi-asserted-by":"crossref","unstructured":"Xu S, Chen X, Han Y, et al. TUPIM: a transparent and universal processing-in-memory architecture for unmodified binaries. In: Proceedings of the 2020 on Great Lakes Symposium on VLSI (GLSVLSI\u201920). New York: Association for Computing Machinery, 2020. 199\u2013204","DOI":"10.1145\/3386263.3406896"},{"key":"3227_CR36","doi-asserted-by":"crossref","unstructured":"Oliveira G F, Santos P C, Alves M A Z, et al. A generic processing in memory cycle accurate simulator under hybrid memory cube architecture. In: Proceedings of 2017 International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation (SAMOS), Pythagorion, 2017. 54\u201361","DOI":"10.1109\/SAMOS.2017.8344611"},{"key":"3227_CR37","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1109\/LCA.2015.2414456","volume":"15","author":"Y Kim","year":"2016","unstructured":"Kim Y, Yang W, Mutlu O. Ramulator: a fast and extensible DRAM simulator. IEEE Comput Arch Lett, 2016, 15: 45\u201349","journal-title":"IEEE Comput Arch Lett"},{"key":"3227_CR38","doi-asserted-by":"crossref","unstructured":"Singh G, Gomez-Luna J, Mariani G, et al. NAPEL: near-memory computing application performance prediction via ensemble learning. In: Proceedings of the 56th ACM\/IEEE Design Automation Conference (DAC), Las Vegas, 2019. 1\u20136","DOI":"10.1145\/3316781.3317867"},{"key":"3227_CR39","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1109\/LCA.2018.2885752","volume":"18","author":"S Xu","year":"2019","unstructured":"Xu S, Chen X, Wang Y, et al. PIMSim: a flexible and detailed processing-in-memory simulator. IEEE Comput Arch Lett, 2019, 18: 6\u20139","journal-title":"IEEE Comput Arch Lett"},{"key":"3227_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2024716.2024718","volume":"39","author":"N Binkert","year":"2011","unstructured":"Binkert N, Beckmann B, Black G, et al. The GEM5 simulator. SIGARCH Comput Archit News, 2011, 39: 1\u20137","journal-title":"SIGARCH Comput Archit News"},{"key":"3227_CR41","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1145\/2508148.2485963","volume":"41","author":"D Sanchez","year":"2013","unstructured":"Sanchez D, Kozyrakis C. ZSim: fast and accurate microarchitectural simulation of thousand-core systems. SIGARCH Comput Archit News, 2013, 41: 475\u2013486","journal-title":"SIGARCH Comput Archit News"},{"key":"3227_CR42","doi-asserted-by":"crossref","unstructured":"Coudrain P, Charbonnier J, Garnier A, et al. Active interposer technology for chiplet-based advanced 3D system architectures. In: Proceedings of 2019 IEEE 69th Electronic Components and Technology Conference (ECTC), Las Vegas, 2019. 569\u2013578","DOI":"10.1109\/ECTC.2019.00092"},{"key":"3227_CR43","doi-asserted-by":"publisher","first-page":"1021","DOI":"10.1109\/JEDS.2020.3024235","volume":"8","author":"X Shen","year":"2020","unstructured":"Shen X, Xia Z, Yang T, et al. Hydrogen source and diffusion path for Poly-Si channel passivation in Xtacking 3D NAND flash memory. IEEE J Electron Dev Soc, 2020, 8: 1021\u20131024","journal-title":"IEEE J Electron Dev Soc"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-020-3227-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-020-3227-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-020-3227-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,20]],"date-time":"2022-07-20T20:10:20Z","timestamp":1658347820000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-020-3227-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,27]]},"references-count":43,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,6]]}},"alternative-id":["3227"],"URL":"https:\/\/doi.org\/10.1007\/s11432-020-3227-1","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,27]]},"assertion":[{"value":"31 December 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 March 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 March 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 April 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"160404"}}