Design and Implementation of Carbon Nano-tube based Full Adder at 32nm Technology for High Speed and Power Efficient Arithmetic Applications

Due to physical, material, technological, power-thermal and economical difficulties, scaling of CMOS transistors will stop very soon. Due to efficiency of power and speed compared to CMOS transistors, Carbon Nano-tube transistors are best suitable element to design logic circuits. So, CNTFETS have been utilized in designing of proposed full adder (FA) and 4-bit ripple carry adder (RCA) in this paper. Proposed FA and RCA have been compared to rival designs on bases of power, speed and power-delay-product (PDP). FA and RCA circuits have been analysed with the variation of temperature from 0°C to 100°C while the variation of supply voltages is from 0.7V to 1.3V. For all temperatures and all supply voltages, proposed FA and proposed RCA have the least power consumption, shortest delay and lowest PDP. SPICE has been utilized for simulating FAs and RCAs in 32 nm process node. Even though the fabrication is complicated than CMOS counterparts but simulation results confirm usefulness of proposed FA and RCA for high speed and power efficient arithmetic applications.

Dynamic Reliability Management in Neuromorphic Computing

Neuromorphic computing systems execute machine learning tasks designed with spiking neural networks. These systems are embracing non-volatile memory to implement high-density and low-energy synaptic storage. Elevated voltages and currents needed to operate non-volatile memories cause aging of CMOS-based transistors in each neuron and synapse circuit in the hardware, drifting the transistor’s parameters from their nominal values. If these circuits are used continuously for too long, the parameter drifts cannot be reversed, resulting in permanent degradation of circuit performance over time, eventually leading to hardware faults. Aggressive device scaling increases power density and temperature, which further accelerates the aging, challenging the reliable operation of neuromorphic systems. Existing reliability-oriented techniques periodically de-stress all neuron and synapse circuits in the hardware at fixed intervals, assuming worst-case operating conditions, without actually tracking their aging at run-time. To de-stress these circuits, normal operation must be interrupted, which introduces latency in spike generation and propagation, impacting the inter-spike interval and hence, performance (e.g., accuracy). We observe that in contrast to long-term aging, which permanently damages the hardware, short-term aging in scaled CMOS transistors is mostly due to bias temperature instability. The latter is heavily workload-dependent and, more importantly, partially reversible. We propose a new architectural technique to mitigate the aging-related reliability problems in neuromorphic systems by designing an intelligent run-time manager (NCRTM), which dynamically de-stresses neuron and synapse circuits in response to the short-term aging in their CMOS transistors during the execution of machine learning workloads, with the objective of meeting a reliability target. NCRTM de-stresses these circuits only when it is absolutely necessary to do so, otherwise reducing the performance impact by scheduling de-stress operations off the critical path. We evaluate NCRTM with state-of-the-art machine learning workloads on a neuromorphic hardware. Our results demonstrate that NCRTM significantly improves the reliability of neuromorphic hardware, with marginal impact on performance.

Hybrid memristor-CMOS implementation of logic gates design using LTSpice

In this paper, a hybrid memristor-CMOS implementation of logic gates simulated using LTSpice. Memristors' implementation in computer architecture designs explored in various design structures proposed by researchers from all around the world. However, all prior designs have some drawbacks in terms of applicability, scalability, and performance. In this research, logic gates design based on the hybrid memristor-CMOS structure presented. 2-inputs AND, OR, NAND, NOR, XOR, and XNOR are demonstrated with minimum components requirements. In addition, a 1-bit full adder circuit with high performance and low area consumption is also proposed. The proposed full adder only consists of 4 memristors and 7 CMOS transistors. Half design of the adder base on the memristor component created. Through analysis and simulations, the memristor implementation on designing logic gates using memristor-CMOS structure demonstrated using the generalized metastable switch memristor (MSS) model and LTSpice. In conclusion, the proposed approach improves speed and require less area.