Junwei Zeng
Abstract
Traditional CMOS-based von-Neumann computer architecture faces the issue of memory wall that the limitation of bus-bandwidth and the speed mismatch between processor and memory restrict the efficiency of data processing along with an irreducible energy consumption conducted by data movement, especially in some data-intensive applications. Recently, some novel in-memory computing (IMC) paradigms developed by utilizing the characteristics of different non-volatile memories provide promising ways to overcome the bottleneck of memory wall. Here, we propose a new IMC unit based on a memory array with the core element of magnetoelectric spin-orbit logic (MESO) device (AIMCU-MESO), in which the characteristics of the MESO device are exploited to achieve several in-memory logic operations with the functions of NAND, NOR, and XOR in the MESO-based memory array. With the aid of some transistor-based switches, these logic operations can be achieved between any two MESOs in the array. Furthermore, the computing process of a 1-bit full adder (FA) is achieved in AIMCU-MESO by the in-memory logic manner to demonstrate the ability of logic cascading. The result of SPICE simulation for achieving the 1-bit FA using MESO devices is demonstrated, and the performances are compared with other designs of spintronics-based devices. Compared to multilevel voltage-controlled spin-orbit torque–based magnetic memory, the proposed design demonstrates 71.4% and 49.2% reductions in terms of storage delay and logic delay, respectively.
- [1] . 2015. Full-adder circuit design based on all-spin logic device. In Proceedings of the IEEE/ACM International Symposium on Nanoscale Architectures (NANOARCH’15). 163–168. Google Scholar
Cross Ref
- [2] . 2019. GraphS: A graph processing accelerator leveraging SOT-MRAM. In Proceedings of the Design, Automation Test in Europe Conference Exhibition (DATE’19). 378–383. Google ScholarCross Ref
- [3] . 2021. Spintronic devices: A promising alternative to CMOS devices. J. Comput. Electr. 20 (2021), 805–837. Google ScholarDigital Library
- [4] . 2010. Proposal for an all-spin logic device with built-in memory. Nat. Nanotechnol. 5 (
02 2010), 266–70. Google ScholarCross Ref - [5] . 2020. Magnetic racetrack memory: From physics to the cusp of applications within a decade. Proc. IEEE 108, 8 (2020), 1303–1321. Google ScholarCross Ref
- [6] . 2016. PRIME: A novel processing-in-memory architecture for neural network computation in ReRAM-based main memory. In Proceedings of the ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA’16). 27–39. Google ScholarDigital Library
- [7] . 2013. Low power magnetic full-adder based on spin transfer torque MRAM. IEEE Trans. Magn. 49 (
09 2013), 4982–4987. Google ScholarCross Ref - [8] . 2021. The promise of spintronics for unconventional computing. J. Magn. Magn. Mater. 521 (
03 2021), 167506. Google ScholarCross Ref - [9] . 2021. Spintronics for energy- efficient computing: An overview and outlook. Proc. IEEE 109, 8 (2021), 1398–1417. Google ScholarCross Ref
- [10] . 2021. Efficient and optimized methods for alleviating the impacts of IR-Drop and fault in RRAM based neural computing systems. IEEE J. Electr. Dev. Soc. 9 (2021), 645–652. Google ScholarCross Ref
- [11] . 2011. Neuromorphic silicon neuron circuits. Front. Neurosci. 5 (2011), 73. Google ScholarCross Ref
- [12] . 2014. Compact modeling of a magnetic tunnel junction based on spin orbit torque. IEEE Trans. Magn. 50, 7 (2014), 1–8. Google ScholarCross Ref
- [13] . 2017. Computing in memory with spin-transfer torque magnetic RAM. In IEEE Transactions on Very Large Scale Integration (VLSI) Systems. 26, 3 (2018), 470-483.
DOI: Google ScholarDigital Library - [14] . 2018. Computing in memory with spin-transfer torque magnetic RAM. IEEE Trans. VLSI Syst. 26, 3 (2018), 470–483. Google ScholarDigital Library
- [15] S. Jain, S. Sapatnekar, J.-P. Wang, K. Roy, and A. Raghunathan. 2018. Computing-in-memory with spintronics. In Design, Automation & Test in Europe Conference & Exhibition (DATE). 1640–1645.
DOI: Google ScholarCross Ref - [16] . 2015. Multilevel spin-orbit torque MRAMs. IEEE Trans. Electr. Dev. 62, 2 (2015), 561–568. Google ScholarCross Ref
- [17] . 2016. Highly efficient and tunable spin-to-charge conversion through Rashba coupling at oxide interfaces. Nat. Mater. 15 (
08 2016). Google ScholarCross Ref - [18] . 2010. Design paradigm for robust spin-torque transfer magnetic RAM (STT MRAM) from circuit/architecture perspective. IEEE Trans. VLSI Syst. 18, 12 (2010), 1710–1723. Google ScholarDigital Library
- [19] C.-C. Lin et al. 2019. Experimental demonstration of integrated magneto-electric and spin-orbit building blocks implementing energy-efficient logic. IEEE International Electron Devices Meeting (IEDM). Vol. 2019, 37.3.1–37.3.4.
DOI: Google ScholarCross Ref - [20] . 2019. Synchronous circuit design with beyond-CMOS magnetoelectric spin-orbit devices toward 100-mV logic. IEEE J. Explor. Solid-State Comput. Dev. Circ. 5 (
12 2019), 74–74. Google ScholarCross Ref - [21] . 2020. Current-driven magnetic domain-wall logic. Nature 579 (
03 2020), 214–218. Google ScholarCross Ref - [22] . 2019. Scalable energy-efficient magnetoelectric spin–orbit logic. Nature 565 (
01 2019), 35–42. Google ScholarCross Ref - [23] . 2018. Voltage control of uni-directional anisotropy in ferromagnet-multiferroic system. Sci. Adv. 4 (
01 2018). Google ScholarCross Ref - [24] . 2015. Spin-orbit torque induced magnetization switching in nano-scale Ta/CoFeB/MgO. Appl. Phys. Lett. 107, 1 (
7 2015). Google ScholarCross Ref - [25] . 2019. Modulation of heavy metal/ferromagnetic metal interface for High\( ^{} \) spintronic devices. Adv. Electr. Mater. 5 (
06 2019). Google ScholarCross Ref - [26] . 2016. Single event multiple upset-tolerant SRAM cell designs for nano-scale CMOS technology. Turk. J. Electr. Eng. Comput. Sci. 25 (
03 2016). Google ScholarCross Ref - [27] . 2016. Comment on “Spin-orbit logic with magnetoelectric nodes: A scalable charge mediated nonvolatile spintronic logic.” arXiv:1512.05428). Retrieved from https://arxiv.org/abs/1512.05428.Google Scholar
- [28] . 2020. Computing-in-memory architecture using energy-efficient multilevel voltage-controlled spin-orbit torque Device. IEEE Trans. Electr. Dev. 67, 5 (2020), 1972–1979. Google ScholarCross Ref
- [29] Tankwal, Piyush Nehra, Vikas Prajapati, Sanjay Kaushik, and Brajesh Kumar. 2019. Performance analysis of differential spin hall effect (DSHE)-MRAM-based logic gates. Circuit World. 45 (2019), 300–310.
DOI: Google ScholarCross Ref - [30] . 2013. Spin-Hall-assisted magnetic random access memory. Appl. Phys. Lett. 104 (
12 2013). Google ScholarCross Ref - [31] . 2019. Proposal of toggle spin torques magnetic RAM for ultrafast computing. IEEE Electr. Dev. Lett. 40, 5 (2019), 726–729. Google ScholarCross Ref
- [32] . 2019. Time-efficient stateful dual-bit-memristor logic. Phys. Status Solidi Rapid Res. Lett. 13 (
02 2019), 1900033. Google ScholarCross Ref - [33] . 2019. A stateful logic family based on a new logic primitive circuit composed of two antiparallel bipolar memristors. Adv. Intell. Syst. 2 (
11 2019). Google ScholarCross Ref - [34] . 2021. In-memory stateful logic computing using memristors: gate, calculation, and application. Phys. Status Solidi C Rapid Res. Lett. 15, 9 (2021), 2100208. Google ScholarCross Ref
- [35] . 2019. Fully functional logic-in-memory operations based on a reconfigurable finite-state machine using a single memristor. Adv. Electr. Mater. 5 (
01 2019), 1800775. Google ScholarCross Ref - [36] S. Yu, X. Sun, X. Peng, and S. Huang. 2020. Compute-in-memory With Emerging Nonvolatile-memories: Challenges and Prospects. In IEEE Custom Integrated Circuits Conference (CICC). 1–4.
DOI: Google ScholarCross Ref - [37] . 2019. Using spin-hall MTJs to build an energy-efficient in-memory computation platform. In Proceedings of the 20th International Symposium on Quality Electronic Design (ISQED’19). 52–57. Google ScholarCross Ref
- [38] . 2021. MESO-ADC: The ADC design using MESO device. Microelectr. J. 116 (
08 2021), 105235. Google ScholarDigital Library - [39] . 2012. Compact modeling of perpendicular-anisotropy CoFeB/MgO magnetic tunnel junctions. IEEE Trans. Electr. Dev. 59 (
03 2012). Google ScholarCross Ref - [40] . 2020. 3D ferrimagnetic device for multi-bit storage and efficient in-memory computing. IEEE Electr. Dev. Lett. PP (
12 2020), 1–1. Google ScholarCross Ref - [41] . 2016. Failure analysis in magnetic tunnel junction nanopillar with interfacial perpendicular magnetic anisotropy. Materials 9, 1 (2016). Google ScholarCross Ref
Index Terms
- AIMCU-MESO: An In-Memory Computing Unit Constructed by MESO Device
Recommendations
Spin-transfer torque magnetic random access memory (STT-MRAM)
Special issue on memory technologiesSpin-transfer torque magnetic random access memory (STT-MRAM) is a novel, magnetic memory technology that leverages the base platform established by an existing 100+nm node memory product called MRAM to enable a scalable nonvolatile memory solution for ...
Evaluation of Hybrid Memory Technologies Using SOT-MRAM for On-Chip Cache Hierarchy
Magnetic Random Access Memory (MRAM) is a very promising emerging memory technology because of its various advantages such as nonvolatility, high density and scalability. In particular, Spin Orbit Torque (SOT) MRAM is gaining interest as it comes along ...
In-Memory Computing: The Next-Generation AI Computing Paradigm
GLSVLSI '20: Proceedings of the 2020 on Great Lakes Symposium on VLSITo overcome the memory bottleneck of von-Neuman architecture, various memory-centric computing techniques are emerging to reduce the latency and energy consumption caused by data communication. The great success of artificial intelligence (AI) ...
Comments