Vivek Saraswat

Vivek Saraswat

Auto-generated profile, based on publicly available information

Vivek Saraswat

Department of Electrical Engineering, Indian Institute of Technology Bombay, Mumbai, India

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 May 2022 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
ASAjay Kumar Singh
Ajay Kumar Singh
VSVivek Saraswat
Vivek Saraswat
MBMaryam Shojaei Baghini
Maryam Shojaei Baghini
UGUdayan Ganguly
Udayan Ganguly
Low-power and low-area neurons are essential for hardware implementation of large-scale SNNs. Various novel-physics-based leaky-integrate-and-fire (LIF) neuron architectures have been proposed with low power and area, but are not compatible with CMOS technology to enable brain scale implementation of SNN. In this paper, for the first time, we demonstrate hardware implementation of recurrent SNN using proposed low-power, low-area, and low-leakage band-to-band-tunneling (BTBT) based neurons. A low-power thresholding circuit is proposed. We further propose a predistortion technique to linearize a nonlinear neuron without any area and power overhead. We establish the equivalence of the proposed neuron with the ideal LIF neuron to demonstrate its versatility. The tunneling regime enables a high input impedance in the BTBT neurons (few $\text{G}\Omega$ ) to enable a voltage input without loading the synaptic array. To verify the effect of the proposed neuron, a 36-neuron recurrent SNN is fabricated in GF-45nm PDSOI technology. We achieved 5000x lower energy-per-spike at a similar area and 10x lower standby power at a similar area and energy-per-spike. Such overall performance improvement enables brain scale computing.

1 September 2019 in APL Materials
Verified
Journal Article
Open access
PDF file
DKDevesh Khilwani
Devesh Khilwani
VMVineet Moghe
Vineet Moghe
SLSandip Lashkare
Sandip Lashkare
VSVivek Saraswat
Vivek Saraswat
PKPankaj Kumbhare
Pankaj Kumbhare
UGUdayan Ganguly
Udayan Ganguly
The neural network enables efficient solutions for Nondeterministic Polynomial-time (NP) hard problems, which are challenging for conventional von Neumann computing. The hardware implementation, i.e., neuromorphic computing, aspires to enhance this efficiency by custom hardware. Particularly, NP hard graphical constraint optimization problems are solved by a network of stochastic binary neurons to form a Boltzmann Machine (BM). The implementation of stochastic neurons in hardware is a major challenge. In this work, we demonstrate that the high to low resistance switching (set) process of a PrxCa1−xMnO3 (PCMO) based RRAM (Resistive Random Access Memory) is probabilistic. Additionally, the voltage-dependent probability distribution approximates a sigmoid function with 1.35%–3.5% error. Such a sigmoid function is required for a BM. Thus, the Analog Approximate Sigmoid (AAS) stochastic neuron is proposed to solve the maximum cut—an NP hard problem. It is compared with Digital Precision-controlled Sigmoid (DPS) implementation using (a) pure CMOS design and (b) hybrid (RRAM integrated with CMOS). The AAS design solves the problem with 98% accuracy, which is comparable with the DPS design but with 10× area and 4× energy advantage. Thus, ASIC neuro-processors based on novel analog neuromorphic devices based BM are promising for efficiently solving large scale NP hard optimization problems.

10 July 2018 in IEEE Electron Device Letters
Verified
Journal Article
Closed access
SLS. Lashkare
S. Lashkare
PKP. Kumbhare
P. Kumbhare
VSV. Saraswat
V. Saraswat
UGU. Ganguly
U. Ganguly
Oscillatory Neural Networks (ONN), based on the thalamocortical neural system, uses the phase dynamics of oscillator neurons to solve NP-hard problems – a key challenge for von-Neumann computing. For hardware realization of ONN, a scalable and low power oscillator neuron is essential. Recently, a transient Joule heating induced high-nonlinearity in the I-V characteristics was demonstrated in area-scalable PrMnO3 (PMO) based RRAM. The extraordinarily high thermal resistivity of PMO (300× of Si) enables thermal runaway at lower power densities. In this work, utilizing this highly non-linear and hysteretic I-V, we propose an oscillator neuron consisting of PMO device put in series with a resistor and a capacitor to produce self-sustained oscillations. The area scalable, sub-3V operation, large output swing, along with the availability of synapse in the same material system makes the PMO based oscillator attractive for ONN. A behavioural model of the oscillator is also developed in Verilog-A to explore the design space over which the device operates. Based on such experimentally calibrated circuit models, a large network of oscillators can be designed and performance can be evaluated for solving complex real-life applications.

5 August 2020 in IEEE Transactions on Electron Devices
Verified
Journal Article
Closed access
VSVivek Saraswat
Vivek Saraswat
SPShankar Prasad
Shankar Prasad
AKAbhishek Khanna
Abhishek Khanna
AWAshwin Wagh
Ashwin Wagh
ABAshwin Bhat
Ashwin Bhat
UGUdayan Ganguly
Udayan Ganguly
Pr0.7Ca0.3MnO3 (PCMO)-based resistive RAM (RRAM) shows promising memory properties like nonvolatility, low variability, multiple resistance states, and scalability. From a modeling perspective, the charge carrier dc current modeling of PCMO RRAM by drift diffusion (DD) in the presence of fixed oxygen ion vacancy traps and self-heating (SH) in Technology Computer Aided Design (TCAD) (but without oxygen ionic transport) was able to explain the experimentally observed space charge limited conduction (SCLC) characteristics, prior to resistive switching. Further, transient analysis using DD+SH model was able to reproduce the experimentally observed fast current increase at ~100 ns timescale, prior to resistive switching. However, a complete quantitative transient current transport plus resistive switching model requires the inclusion of ionic transport. We propose a reaction-drift (RD) model for oxygen ion vacancy-related trap density variation, which is combined with the DD+SH model. Earlier, we have shown that the Set transient consists of three stages and Reset transient consists of four stages experimentally. In this work, the DD+SH+RD model is able to reproduce the entire transient behavior over 10 ns-1 s range in timescale for both the Set and Reset operations for different applied biases and ambient temperatures. Remarkably, a universal Reset experimental behavior, log(I)∝ (m x log(t)) where m≈ -1/10 is reproduced in simulations. This model is the first model for PCMO RRAMs to significantly reproduce transient Set/Reset behavior. This model establishes the presence of SH and ionic-drift limited resistive switching as primary physical phenomena in these RRAMs.

9 February 2024 in IEEE Transactions on Electron Devices
Verified
Journal Article
Closed access
PMParitosh Meihar
Paritosh Meihar
RSRowtu Srinu
Rowtu Srinu
VSVivek Saraswat
Vivek Saraswat
SLSandip Lashkare
Sandip Lashkare
HMHalid Mulaosmanovic
Halid Mulaosmanovic
UGUdayan Ganguly
Udayan Ganguly
The HfO $_\text{2}$ -based ferroelectric field-effect transistor (FeFET) has become a center of attraction for nonvolatile memory application because of their low power, fast switching speed, high scalability, and CMOS compatibility. In this work, we show an n-channel FeFET-based multibit memory, termed “MirrorBit”, which effectively doubles the chip density via programming the gradient ferroelectric polarizations in the gate, using an appropriate biasing scheme. We have experimentally demonstrated MirrorBit on the GlobalFoundries’ HfO $_\text{2}$ -based FeFET devices fabricated at the 28-nm bulk HKMG CMOS technology. Retention of MirrorBit states has been shown up to 10 $^\text{5}$ s at different temperatures. In addition, the endurance is found to be more than 10 $^\text{3}$ cycles. A TCAD simulation is also presented to explain the origin and working of MirrorBit states, based on the FeFET model calibrated using the GlobalFoundries FeFET device. We have also proposed the array-level implementation and sensing methodology of the MirrorBit memory. Thus, we have converted 1-bit FeFET into 2-bit FeFET using programming and reading schemes in the existing FeFET, without the need for any special fabrication process alteration, to double the storage capacity.

5 July 2023 in Neural Networks
Verified
Journal Article
Closed access
RSRaghav Singhal
Raghav Singhal
VSVivek Saraswat
Vivek Saraswat
SDShreyas Deshmukh
Shreyas Deshmukh
SSSreenivas Subramoney
Sreenivas Subramoney
LSLaxmeesha Somappa
Laxmeesha Somappa
UGUdayan Ganguly
Udayan Ganguly