journal article·2023-02-01Open access

Time-domain computing for Boolean logic using STT-MRAM

Rong Zhou, Hao Cai

AIP Advances· Volume 13· Issue 2

Abstract

With the development of artificial intelligence, the separation of memory and processor in the traditional von-Neumann architecture has led to the bottleneck of data transmission hindering the development of energy efficient computing. The computing-in-memory (CIM) paradigm is expected to solve the problems of memory wall and power wall. In this work, we propose a time-domain (TD) computing scheme based on the spin transfer torque magnetic random access memory (STT-MRAM). Basic Boolean logic operations, such as AND/OR/Full-adder (FA), are implemented through converting the bit-line voltage to time delay and time-to-digital converter (TDC). The proposal is simulated using the 28 nm CMOS process and 40 nm MTJ compact model. Monte-Carlo simulations show that 94.2% to 100% computation accuracy can be obtained and the delay of AND/OR and FA is 2.5 ns and 3.5 ns. The energy consumption of AND/OR and FA achieve 59.43 fJ and 97.56 fJ, respectively.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Magnetic properties of thin films · Advanced Memory and Neural Computing · Neural Networks and Reservoir Computing

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

School of Electronic Science and Engineering, Southeast University , Nanjing 210000, China

Funding

National Natural Science Foundation of China

References (14)

Show source-provided references
1. An in-memory VLSI architecture for convolutional neural networks10.1109/jetcas.2018.2829522 ↗
2. Challenges and trends of SRAM-based computing-in-memory for AI edge devices10.1109/tcsi.2021.3064189 ↗
3. CONV-RAM: An energy-efficient SRAM with embedded convolution computation for low-power CNN-based machine learning applications
4. 24.5 A Twin-8T SRAM computation-in-memory macro for multiple-bit CNN-based machine learning
5. In-memory computation of a machine-learning classifier in a standard 6T SRAM array10.1109/jssc.2016.2642198 ↗
6. Large magnetoresistance and 15 Boolean logic functions based on a ZNCOO film and diode combined device10.1002/aelm.201800812 ↗
7. Efficient time-domain in-memory computing based on TST-MRAM
8. Time-domain computing in memory using spintronics for energy-efficient convolutional neural network10.1109/tcsi.2021.3055830 ↗
9. 14.4 all-digital time-domain CNN engine using bidirectional memory delay lines for energy-efficient edge computing
10. Design of an area-efficient computing in memory platform based on STT-MRAM10.1109/tmag.2020.3016741 ↗
11. Computing-in-memory paradigm based on STT-MRAM with synergetic read/write-like modes
12. Time-based sensing for reference-less and robust read in STT-MRAM memories10.1109/tcsi.2018.2828611 ↗
13. Compact model of dielectric breakdown in spin-transfer torque magnetic tunnel junction10.1109/ted.2016.2533438 ↗
14. Compact modeling of perpendicular-magnetic-anisotropy double-barrier magnetic tunnel junction with enhanced thermal stability recording structure10.1109/ted.2019.2906932 ↗