Vivek Parmar

Mr. Vivek Parmar

Indian Institute of Technology (IIT) Delhi
orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
13 February 2020 in Scientific Reports
Verified
Journal Article
Open access
PDF file
SKSandeep Kaur Kingra
Sandeep Kaur Kingra
VPVivek Parmar
Vivek Parmar
CCChe-Chia Chang
Che-Chia Chang
BHBoris Hudec
Boris Hudec
THTuo-Hung Hou
Tuo-Hung Hou
MSManan Suri
Manan Suri
Von Neumann architecture based computers isolate computation and storage (i.e. data is shuttled between computation blocks (processor) and memory blocks). The to-and-fro movement of data leads to a fundamental limitation of modern computers, known as the Memory wall. Logic in-Memory (LIM)/In-Memory Computing (IMC) approaches aim to address this bottleneck by directly computing inside memory units thereby eliminating energy-intensive and time-consuming data movement. Several recent works in literature, propose realization of logic function(s) directly using arrays of emerging resistive memory devices (example- memristors, RRAM/ReRAM, PCM, CBRAM, OxRAM, STT-MRAM etc.), rather than using conventional transistors for computing. The logic/embedded-side of digital systems (like processors, micro-controllers) can greatly benefit from such LIM realizations. However, the pure storage-side of digital systems (example SSDs, enterprise storage etc.) will not benefit much from such LIM approaches as when memory arrays are used for logic they lose their core functionality of storage. Thus, there is the need for an approach complementary to existing LIM techniques, that’s more beneficial for the storage-side of digital systems; one that gives compute capability to memory arrays not at the cost of their existing stored states. Fundamentally, this would require memory nanodevice arrays that are capable of storing and computing simultaneously. In this paper, we propose a novel ‘Simultaneous Logic in-Memory’ (SLIM) methodology which is complementary to existing LIM approaches in literature. Through extensive experiments we demonstrate novel SLIM bitcells (1T-1R/2T-1R) comprising non-filamentary bilayer analog OxRAM devices with NMOS transistors. Proposed bitcells are capable of implementing both Memory and Logic operations simultaneously. Detailed programming scheme, array level implementation, and controller architecture are also proposed. Furthermore, to study the impact of proposed SLIM approach for real-world implementations, we performed analysis for two applications: (i) Sobel Edge Detection, and (ii) Binary Neural Network- Multi layer Perceptron (BNN-MLP). By performing all computations in SLIM bitcell array, huge Energy Delay Product (EDP) savings of ≈75× for 1T-1R (≈40× for 2T-1R) SLIM bitcell were observed for edge-detection application while EDP savings of ≈3.5× for 1T-1R (≈1.6× for 2T-1R) SLIM bitcell were observed for BNN-MLP application respectively, in comparison to conventional computing. EDP savings owing to reduction in data transfer between CPU ↔ memory is observed to be ≈780× (for both SLIM bitcells).

15 June 2015 in IEEE Transactions on Nanotechnology
Verified
Journal Article
Closed access
MSManan Suri
Manan Suri
VPVivek Parmar
Vivek Parmar
In this paper, we show for the first time how unavoidable device variability of emerging nonvolatile resistive memory devices can be exploited to design efficient low-power, low-footprint extreme learning machine (ELM) architectures. In particular, we utilize the uncontrollable off-state resistance (Roff/HRS) spreads, of nanoscale filamentary-resistive memory devices, to realize random input weights and random hidden neuron biases; a characteristic requirement of ELM. We propose a novel RRAM-ELM architecture. To validate our approach, experimental data from different filamentary-resistive switching devices (CBRAM, OXRAM) are used for full-network simulations. Learning capability of our RRAM-ELM architecture is illustrated with the help of two real-world applications: 1) diabetes diagnosis test (classification) and 2) SinC curve fitting (regression).

4 January 2017 in IEEE Transactions on Nanotechnology
Verified
Journal Article
Closed access
SSShubham Sahay
Shubham Sahay
AKAshwani Kumar
Ashwani Kumar
VPVivek Parmar
Vivek Parmar
MSManan Suri
Manan Suri
Compact, low-power random number generators (RNG) are essential for applications such as stochastic-, bioinspired-computing, data-encryption, cryptography in communication and security systems. We demonstrate two highly scalable hybrid CMOS-OxRAM RNG implementations based on single OxRAM and 2-OxRAM -circuits. We show how multiple undesirable nanoscale OxRAM phenomena, such as reset-current fluctuation, random telegraph noise (RTN), and reset-state resistance variability in HfOX devices can be coupled to realize RNGs. We show that mitigation of history (memory) effect in 2-OxRAM RNGs can be achieved by using optional OxRAM switching and smaller sampling frequency. Using circuit simulations with calibrated compact models, the proposed hybrid RNG circuits have been validated for 10 nm thick HfO x devices and 180 nm CMOS node. RNG performance is characterized using chi-square test, serial spectral test, and covariance/correlation-based analysis.

2 June 2019
Verified
Conference Paper
Open access
CCChih-Cheng Chang
Chih-Cheng Chang
MWMing-Hung Wu
Ming-Hung Wu
JLJia-Wei Lin
Jia-Wei Lin
CLChun-Hsien Li
Chun-Hsien Li
VPVivek Parmar
Vivek Parmar
THTuo-Hung Hou
Tuo-Hung Hou

17 January 2022 in Applied Physics Letters
Verified
Journal Article
Closed access
PDF file
SKSandeep Kaur Kingra
Sandeep Kaur Kingra
VPVivek Parmar
Vivek Parmar
SNShubham Negi
Shubham Negi
ABAlessandro Bricalli
Alessandro Bricalli
GPGiuseppe Piccolboni
Giuseppe Piccolboni
MSManan Suri
Manan Suri
Conventional DNN (deep neural network) implementations rely on networks with sizes in the order of MBs (megabytes) and computation complexity of the order of Tera FLOPs (floating point operations per second). However, implementing such networks in the context of edge-AI (artificial intelligence) poses limitations due to the requirement of high precision computation blocks, large memory requirement, and memory wall. To address this, low-precision DNN implementations based on IMC (in-memory computing) approaches utilizing NVM (non-volatile memory) devices have been explored recently. In this work, we experimentally demonstrate a dual-configuration XNOR (exclusive NOR) IMC bitcell. The bitcell is realized using fabricated 1T-1R SiOx RRAM (resistive random access memory) arrays. We have analyzed the trade-off in terms of circuit-overhead, energy, and latency for both IMC bitcell configurations. Furthermore, we demonstrate the functionality of the proposed IMC bitcells with mobilenet architecture based BNNs (binarized neural networks). The network is trained on VWW (visual wake words) and CIFAR-10 datasets, leading to an inference accuracy of ≈ 80.3% and ≈ 84.9%, respectively. Additionally, the impact of simulated BER (bit error rate) on the BNN accuracy is also analyzed.

22 February 2023 in Advanced Intelligent Systems
Verified
Journal Article
Open access
VPVivek Parmar
Vivek Parmar
FMFranz Müller
Franz Müller
JHJing-Hua Hsuen
Jing-Hua Hsuen
SKSandeep Kaur Kingra
Sandeep Kaur Kingra
NLNellie Laleni
Nellie Laleni
TKThomas Kämpfe
Thomas Kämpfe
Harnessing multibit precision in nonvolatile memory (NVM)‐based synaptic core can accelerate multiply and accumulate (MAC) operation of deep neural network (DNN). However, NVM‐based synaptic cores suffer from the trade‐off between bit density and performance. The undesired performance degradation with scaling, limited bit precision, and asymmetry associated with weight update poses a severe bottleneck in realizing a high‐density synaptic core. Herein, 1) evaluation of novel differential mode ferroelectric field‐effect transistor (DM‐FeFET) bitcell on a crossbar array of 4 K devices; 2) validation of weighted sum operation on 28 nm DM‐FeFET crossbar array; 3) bit density of 223Mb mm−2, which is ≈2× improvement compared to conventional FeFET array; 4) 196 TOPS/W energy efficiency for VGG‐8 network; and 5) superior bit error rate (BER) resilience showing ≈94% training and 88% inference accuracy with 1% BER are demonstrated.