{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T00:13:54Z","timestamp":1715386434431},"reference-count":35,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"11","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Electron. Express"],"published-print":{"date-parts":[[2023,6,10]]},"DOI":"10.1587\/elex.20.20230152","type":"journal-article","created":{"date-parts":[[2023,4,19]],"date-time":"2023-04-19T22:12:05Z","timestamp":1681942325000},"page":"20230152-20230152","source":"Crossref","is-referenced-by-count":0,"title":["A 6T-3M SOT-MRAM for in-memory computing with reconfigurable arithmetic operations"],"prefix":"10.1587","volume":"20","author":[{"given":"Xing","family":"Jin","sequence":"first","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-sen University"}]},{"given":"Ningyuan","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Microelectronics Science and Technology, Sun Yat-sen University"}]},{"given":"Weichong","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Microelectronics Science and Technology, Sun Yat-sen University"}]},{"given":"Ximing","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-sen University"}]},{"given":"Guihua","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-sen University"}]},{"given":"Zhiyi","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Microelectronics Science and Technology, Sun Yat-sen University"},{"name":"Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems, Sun Yat-sen University"}]}],"member":"532","reference":[{"key":"1","unstructured":"[1] J. Song, <i>et al.<\/i>: \u201cA 28nm 64Kb inference-training two-way transpose multibit 6T SRAM compute-in-memory macro for AI edge chips,\u201d IEEE International Solid-State Circuits Conference-(ISSCC) (2020) 240 (DOI: 10.1109\/ISSCC19947.2020.9062949)."},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] R. Liu, <i>et al.<\/i>: \u201cParallelizing SRAM arrays with customized bit-cell for binary neural networks,\u201d 55th ACM\/ESDA\/IEEE Design Automat. Conf. (DAC) (2018) 1 (DOI: 10.1109\/DAC.2018.8465935).","DOI":"10.1145\/3195970.3196089"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] X. Si, <i>et al.<\/i>: \u201cA dual-split 6T SRAM-based computing-in-memory unit-macro with fully parallel product-sum operation for binarized DNN edge processors,\u201d IEEE Trans. Circuits Syst. I, Reg. Papers <b>66<\/b> (2019) 4172 (DOI: 10.1109\/TCSI.2019.2928043).","DOI":"10.1109\/TCSI.2019.2928043"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] Z. Jiang, <i>et al.<\/i>: \u201cXNOR-SRAM: in-memory computing SRAM macro for binary\/ternary deep neural networks,\u201d IEEE Symposium on VLSI Technology (2018) (DOI: 10.1109\/VLSIT.2018.8510687).","DOI":"10.1109\/VLSIT.2018.8510687"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] V. Sze, <i>et al.<\/i>: \u201cHardware for machine learning: challenges and opportunities,\u201d IEEE Custom Integr. Circuits Conf. (CICC) (2018) 1 (DOI: 10.1109\/CICC.2017.7993626).","DOI":"10.1109\/CICC.2018.8357072"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] X. Si, <i>et al.<\/i>: \u201cA twin-8T SRAM computation-in-memory unit-macro for multibit CNN-based AI edge processors,\u201d IEEE J. Solid-State Circuits <b>55<\/b> (2020) 1189 (DOI: 10.1109\/JSSC.2019.2952773).","DOI":"10.1109\/JSSC.2019.2952773"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] B. Moons and M. Verhelst: \u201cAn energy-efficient precision-scalable ConvNet processor in 40-nm CMOS,\u201d IEEE J. Solid-State Circuits <b>52<\/b> (2017) 903 (DOI: 10.1109\/JSSC.2016.2636225).","DOI":"10.1109\/JSSC.2016.2636225"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] V. Sze: \u201cDesigning hardware for machine learning: The important role played by circuit designers,\u201d IEEE Solid State Circuits Mag. <b>9<\/b> (2017) 46 (DOI: 10.1109\/MSSC.2017.2745798).","DOI":"10.1109\/MSSC.2017.2745798"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] X. Si, <i>et al.<\/i>: \u201cA local computing cell and 6T SRAM-based computing-in-memory macro with 8-b MAC operation for edge AI chips,\u201d IEEE J. Solid-State Circuits <b>56<\/b> (2021) 2817 (DOI: 10.1109\/JSSC.2021.3073254).","DOI":"10.1109\/JSSC.2021.3073254"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] Y. Chen, <i>et al.<\/i>: \u201cReconfigurable 2T2R ReRAM architecture for versatile data storage and computing in-memory,\u201d IEEE Trans. Very Large Scale Integr. (VLSI) Syst. <b>28<\/b> (2020) 2636 (DOI: 10.1109\/TVLSI.2020.3028848).","DOI":"10.1109\/TVLSI.2020.3028848"},{"key":"11","unstructured":"[11] J. Zhang, <i>et al.<\/i>: \u201cA machine-learning classifier implemented in a standard 6T SRAM array,\u201d IEEE Symp. VLSI Circuits (VLSI-Circuits) (2016) 1 (DOI: 10.1109\/VLSIC.2016.7573556)."},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] A. Sebastian, <i>et al.<\/i>: \u201cMemory devices and applications for in-memory computing,\u201d Nat. Nanotechnol. <b>15<\/b> (2020) 529 (DOI: 10.1038\/s41565-020-0655-z).","DOI":"10.1038\/s41565-020-0655-z"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] A. Agrawal, <i>et al.<\/i>: \u201cX-SRAM: enabling in-memory Boolean computations in CMOS static random access memories,\u201d IEEE Trans. Circuits Syst. I, Reg. Papers <b>65<\/b> (2018) 4219 (DOI: 10.1109\/TCSI.2018.2848999).","DOI":"10.1109\/TCSI.2018.2848999"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] Y.-C. Chiu, <i>et al.<\/i>: \u201cA 4-Kb 1-to-8-bit configurable 6T SRAM-based computation-in-memory unit-macro for CNN-based AI edge processors,\u201d IEEE J. Solid-State Circuits <b>55<\/b> (2020) 2790 (DOI: 10.1109\/JSSC.2020.3005754).","DOI":"10.1109\/JSSC.2020.3005754"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] S.K. Gonugondla, <i>et al.<\/i>: \u201cA 42pJ\/decision 3.12TOPS\/W robust in-memory machine learning classifier with on-chip training,\u201d IEEE International Solid-State Circuits Conference-(ISSCC) (2018) 490 (DOI: 10.1109\/ISSCC.2018.8310398).","DOI":"10.1109\/ISSCC.2018.8310398"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] A. Jaiswal, <i>et al.<\/i>: \u201cI-SRAM: Interleaved wordlines for vector Boolean operations using SRAMs,\u201d IEEE Trans. Circuits Syst. I, Reg. Papers <b>67<\/b> (2020) 1 (DOI: 10.1109\/TCSI.2020.3005783).","DOI":"10.1109\/TCSI.2020.3005783"},{"key":"17","unstructured":"[17] J.-W. Su, <i>et al.<\/i>: \u201cA 28nm 384kb 6T-SRAM computation-in-memory macro with 8b precision for AI edge chips,\u201d IEEE International Solid-State Circuits Conference-(ISSCC) (2021) 250 (DOI: 10.1109\/ISSCC42613.2021.9365984)."},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] S.K. Gonugondla, <i>et al.<\/i>: \u201cA variation-tolerant in-memory machine learning classifier via on-chip training,\u201d IEEE J Solid-State Circuits <b>53<\/b> (2018) 3163 (DOI: 10.1109\/JSSC.2018.2867275).","DOI":"10.1109\/JSSC.2018.2867275"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] X. Yang, <i>et al.<\/i>: \u201cAn in-memory-computing charge-domain ternary CNN classifier,\u201d IEEE Custom Integr. Circuits Conf. (CICC) (2021) 1 (DOI: 10.1109\/CICC51472.2021.9431398).","DOI":"10.1109\/CICC51472.2021.9431398"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] J. Zhang, <i>et al.<\/i>: \u201cAn 8T SRAM array with configurable word lines for in-memory computing operation,\u201d Electron. <b>10<\/b> (2021) 300 (DOI: 10.3390\/electronics10030300).","DOI":"10.3390\/electronics10030300"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] P. Huang and W. Hwang: \u201cA 65nm 0.165fJ\/bit\/search 256\u00d7144 TCAM macro design for IPv6 lookup tables,\u201d IEEE J. Solid-State Circuits <b>46<\/b> (2011) 507 (DOI: 10.1109\/JSSC.2010.2082270).","DOI":"10.1109\/JSSC.2010.2082270"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] S. Jeloka, <i>et al.<\/i>: \u201cA 28nm configurable memory (TCAM\/BCAM\/SRAM) using push-rule 6T bit cell enabling logic-in-memory,\u201d IEEE J. Solid-State Circuits <b>51<\/b> (2016) 1009 (DOI: 10.1109\/JSSC.2016.2515510).","DOI":"10.1109\/JSSC.2016.2515510"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] W.A. Simon, <i>et al.<\/i>: \u201cBLADE: an in-cache computing architecture for edge devices,\u201d IEEE Trans. Comput. <b>69<\/b> (2020) 1349 (DOI: 10.1109\/TC.2020.2972528).","DOI":"10.1109\/TC.2020.2972528"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] M.E. Sinangil, <i>et al.<\/i>: \u201cA 7-nm compute-in-memory SRAM macro supporting multi-bit input, weight and output and achieving 351TOPS\/W and 372.4GOPS,\u201d IEEE Trans. Circuits Syst. I, Reg. Papers <b>56<\/b> (2021) 188 (DOI: 10.1109\/JSSC.2020.3031290).","DOI":"10.1109\/JSSC.2020.3031290"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] Y. Zhang, <i>et al.<\/i>: \u201cTime-domain computing in memory using spintronics for energy-efficient convolutional neural network,\u201d IEEE Trans. Circuits Syst. I, Reg. Papers <b>68<\/b> (2021) 1193 (DOI: 10.1109\/TCSI.2021.3055830).","DOI":"10.1109\/TCSI.2021.3055830"},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] J. Wang, <i>et al.<\/i>: \u201cA 28-nm compute SRAM with bit-serial logic\/arithmetic operations for programmable in-memory vector computing,\u201d IEEE J. Solid-State Circuits <b>55<\/b> (2020) 76 (DOI: 10.1109\/JSSC.2019.2939682).","DOI":"10.1109\/JSSC.2019.2939682"},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] Q. Dong, <i>et al.<\/i>: \u201cA 4 + 2T SRAM for searching and in-memory computing with 0.3-V V<sub>DDmin<\/sub>,\u201d IEEE J. Solid-State Circuits <b>53<\/b> (2018) 1006 (DOI: 10.1109\/JSSC.2017.2776309).","DOI":"10.1109\/JSSC.2017.2776309"},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] R. Bishnoi, <i>et al.<\/i>: \u201cSelf-timed read and write operations in STT-MRAM,\u201d IEEE Trans. Very Large Scale Integr. (VLSI) Syst. <b>24<\/b> (2016) 1783 (DOI: 10.1109\/TVLSI.2015.2496363).","DOI":"10.1109\/TVLSI.2015.2496363"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] J. Doevenspeck, <i>et al.<\/i>: \u201cSOT-MRAM based analog in-memory computing for DNN inference,\u201d 2020 IEEE Symposium on VLSI Technology (2020) 1 (DOI: 10.1109\/VLSITechnology18217.2020.9265099).","DOI":"10.1109\/VLSITechnology18217.2020.9265099"},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] X. Jin, <i>et al.<\/i>: \u201cHigh-reliability, reconfigurable, and fully non-volatile full-adder based on SOT-MTJ for image processing applications,\u201d IEEE Trans. Circuits Syst. II, Exp. Briefs <b>70<\/b> (2022) 781 (DOI: 10.1109\/TCSII.2022.3213747).","DOI":"10.1109\/TCSII.2022.3213747"},{"key":"31","doi-asserted-by":"crossref","unstructured":"[31] M. Natsui, <i>et al.<\/i>: \u201cDual-port SOT-MRAM achieving 90-MHz read and 60-MHz write operations under field-assistance-free condition,\u201d IEEE J. Solid-State Circuits <b>56<\/b> (2020) 1116 (DOI: 10.1109\/JSSC.2020.30398009).","DOI":"10.1109\/JSSC.2020.3039800"},{"key":"32","doi-asserted-by":"crossref","unstructured":"[32] A. Sengupta, <i>et al.<\/i>: \u201cStochastic inference and learning enabled by magnetic tunnel junctions,\u201d IEEE International Electron Devices Meeting (IEDM) (2018) 15.6.1 (DOI: 10.1109\/IEDM.2018.8614616).","DOI":"10.1109\/IEDM.2018.8614616"},{"key":"33","doi-asserted-by":"crossref","unstructured":"[33] S. Dhull, <i>et al.<\/i>: \u201cArea efficient computing-in-memory architecture using STT\/SOT hybrid three level cell,\u201d IEEE Open J. Nanotechnol. <b>3<\/b> (2022) 45 (DOI: 10.1109\/OJNANO.2022.3166959).","DOI":"10.1109\/OJNANO.2022.3166959"},{"key":"34","doi-asserted-by":"crossref","unstructured":"[34] S. Shreya, <i>et al.<\/i>: \u201cComputing-in-memory architecture using energy-efficient multilevel voltage-controlled spin-orbit torque device,\u201d IEEE Trans. Electron Devices <b>67<\/b> (2020) 1972 (DOI: 10.1109\/TED.2020.2978085).","DOI":"10.1109\/TED.2020.2978085"},{"key":"35","doi-asserted-by":"crossref","unstructured":"[35] M. Zabihi, <i>et al.<\/i>: \u201cIn-memory processing on the spin-tronic CRAM: From hardware design to application mapping,\u201d IEEE Trans. Comput. <b>68<\/b> (2019) 1159 (DOI: 10.1109\/TC.2018.2858251).","DOI":"10.1109\/TC.2018.2858251"}],"container-title":["IEICE Electronics Express"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/elex\/20\/11\/20_20.20230152\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,10]],"date-time":"2024-05-10T04:28:41Z","timestamp":1715315321000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/elex\/20\/11\/20_20.20230152\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,10]]},"references-count":35,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2023]]}},"URL":"https:\/\/doi.org\/10.1587\/elex.20.20230152","relation":{},"ISSN":["1349-2543"],"issn-type":[{"value":"1349-2543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,10]]},"article-number":"20.20230152"}}