Rediscovering Majority Logic in the Post-CMOS Era: A Perspective from In-Memory Computing

Expanding the Set of Three-Input Logic Functions in Inverted T-Shaped TFETs

Three-input logic primitives show high efficiency in logic synthesis compared to traditional two-input logic, which encourages researchers to implement three-input logic gates with emerging nanotechnologies. This paper demonstrates a compact implementation of three-input monotone logic gates based on the inverted T-shaped TFET. Firstly, based on the gate coupling mechanism in the novel inverted T channel, the BTBT current can be suppressed in the vertical or horizontal region to achieve the channel strobe. Therefore, the typical three-input monotone logic functions, Majority, OrAnd, and AndOr, are successfully implemented on a single transistor. Then, a simplified potential model describing gate coupling is established to describe the impact of key device parameters on the logic behavior. Combined with TCAD simulation, the design rules of devices with different logic functions are given. Finally, a series of three-input monotonic logic gates are designed and verified. The results show that the use of the proposed TFETs can effectively save the number of transistors in the three-input logic gate, which indicates that the three-input TFET is a compact and flexible candidate for three-input logic gates.

Novel In-Memory Computing Adder Using 8+T SRAM

Von Neumann architecture-based computing systems are facing a von Neumann bottleneck owing to data transfer between separated memory and processor units. In-memory computing (IMC), on the other hand, reduces energy consumption and improves computing performance. This study explains an 8+T SRAM IMC circuit based on 8+T differential SRAM (8+T SRAM) and proposes 8+T SRAM-based IMC full adder (FA) and 8+T SRAM-based IMC approximate adder, which are based on the 8+T SRAM IMC circuit. The 8+T SRAM IMC circuit performs SRAM read and bitwise operations simultaneously and performs each logic operation parallelly. The proposed IMC FA and the proposed IMC approximate adder can be applied to a multi-bit adder. The two adders are based on the 8+T SRAM IMC circuit and thus read and compute simultaneously. In this study, the 8+T SRAM IMC circuit was applied to the adder, leveraging its ability to perform read and logic operations simultaneously. According to the performance in this study, the 8+T SRAM IMC circuit, proposed FA, proposed RCA, and proposed approximated adder are good candidates for IMC, which aims to reduce energy consumption and improve overall performance.

Design and Analysis of Low-Power and High Speed Approximate Adders Using CNFETs

Adders are constituted as the fundamental blocks of arithmetic circuits and are considered important for computation devices. Approximate computing has become a popular and developing area, promising to provide energy-efficient circuits with low power and high performance. In this paper, 10T approximate adder (AA) and 13T approximate adder (AA) designs using carbon nanotube field-effect transistor (CNFET) technology are presented. The simulation for the proposed 10T approximate adder and 13T approximate adder designs were carried out using the HSPICE tool with 32 nm CNFET technology. The metrics, such as average power, power-delay product (PDP), energy delay product (EDP) and propagation delay, were carried out through the HSPICE tool and compared to the existing circuit designs. The supply voltage V_dd provided for the proposed circuit designs was 0.9 V. The results indicated that among the existing full adders and approximate adders found in the review of adders, the proposed circuits consumed less PDP and minimum power with more accuracy.

Design of In-Memory Parallel-Prefix Adders

Computational methods in memory array are being researched in many emerging memory technologies to conquer the ‘von Neumann bottleneck’. Resistive RAM (ReRAM) is a non-volatile memory, which supports Boolean logic operation, and adders can be implemented as a sequence of Boolean operations in the memory. While many in-memory adders have recently been proposed, their latency is exorbitant for increasing bit-width (O(n)). Decades of research in computer arithmetic have proven parallel-prefix technique to be the fastest addition technique in conventional CMOS-based binary adders. This work endeavors to move parallel-prefix addition to the memory array to significantly minimize the latency of in-memory addition. Majority logic was chosen as the fundamental logic primitive and parallel-prefix adders synthesized in majority logic were mapped to the memory array using the proposed algorithm. The proposed algorithm can be used to map any parallel-prefix adder to a memory array and mapping is performed in such a way that the latency of addition is minimized. The proposed algorithm enables addition in O(log(n)) latency in the memory array.

Multi-Input Logic-in-Memory for Ultra-Low Power Non-Von Neumann Computing

Logic-in-memory (LIM) circuits based on the material implication logic (IMPLY) and resistive random access memory (RRAM) technologies are a candidate solution for the development of ultra-low power non-von Neumann computing architectures. Such architectures could enable the energy-efficient implementation of hardware accelerators for novel edge computing paradigms such as binarized neural networks (BNNs) which rely on the execution of logic operations. In this work, we present the multi-input IMPLY operation implemented on a recently developed smart IMPLY architecture, SIMPLY, which improves the circuit reliability, reduces energy consumption, and breaks the strict design trade-offs of conventional architectures. We show that the generalization of the typical logic schemes used in LIM circuits to multi-input operations strongly reduces the execution time of complex functions needed for BNNs inference tasks (e.g., the 1-bit Full Addition, XNOR, Popcount). The performance of four different RRAM technologies is compared using circuit simulations leveraging a physics-based RRAM compact model. The proposed solution approaches the performance of its CMOS equivalent while bypassing the von Neumann bottleneck, which gives a huge improvement in bit error rate (by a factor of at least 10⁸) and energy-delay product (projected up to a factor of 10¹⁰).