Mohit Gupta

Mohit Gupta

Auto-generated profile, based on publicly available information

Mohit Gupta

IMEC, Leuven, Belgium

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
24 June 2021 in IEEE Transactions on Electron Devices
Verified
Journal Article
Closed access
MGMohit Kumar Gupta
Mohit Kumar Gupta
PWPieter Weckx
Pieter Weckx
PSPieter Schuddinck
Pieter Schuddinck
DJDoyoung Jang
Doyoung Jang
BCBilal Chehab
Bilal Chehab
WDWim Dehaene
Wim Dehaene
SRAM bitcell area reduction, lower SRAM parasitic resistance, and higher drive strength are necessary to continue with technology scaling. Nanosheet (NSH) technology improves SRAM cell write-ability by having 50 mV more write trip point (WTP) than FinFET (FF) SRAM due to reduced bit line (BL) resistance (due to wider metal CD) and more drive current strength (more than 15%) than FF for the same leakage. However, due to higher bitcell area (20% larger), BL, and word line (WL) parasitic capacitance than FF, NSH SRAM would not compete with FF SRAM in terms of the read delay (26% more delay) and energy at the 3-nm technology node. PFET to NFET (PN) spacing, composed of gate cut, gate extension, and Fin pitch in an SRAM bitcell, is critical for SRAM cell height because it can take ~46% of the 111 SRAM total cell height. The forksheet (FSH), achieving extremely scaled PN space in SRAM bitcell due to device structure with limited additional processing complexity, reduces the SRAM bitcell area. As a result, BL and WL parasitics reduce and improve the SRAM read delay and stability. FSH SRAM saves 6% area benefit and achieves 24% lesser read delay than FF high density (HD) SRAM.

5 November 2021 in IEEE Transactions on Electron Devices
Verified
Journal Article
Closed access
MGMohit Kumar Gupta
Mohit Kumar Gupta
PWPieter Weckx
Pieter Weckx
PSPieter Schuddinck
Pieter Schuddinck
DJDoyoung Jang
Doyoung Jang
BCBilal Chehab
Bilal Chehab
WDWim Dehaene
Wim Dehaene
This article discusses complementary FET (CFET)-based static random access memory (SRAM) to achieve next-generation bitcell area scaling and performance gain in advanced CMOS technology nodes. SRAM bitcell area reduction, lower SRAM parasitic resistance, and higher drive strength are mandatory to continue SRAM scaling with technology advancement. The CFET reduces the SRAM bitcell area by folding nMOS over pMOS and making SRAM cross-coupled connections in the middle end of line (MEOL). The compact bitcell offers large area scaling combined with lowering bitline and wordline resistance. Lower parasitic resistance improves SRAM write margin and performance. The CFET SRAM cell area, write margin, read margin, and performance are evaluated and compared with FinFET (FF)-based SRAM. The CFET 111 and 122 SRAM provides up to 43.75% and 35% area gain w.r.t. FF 111 and 122 SRAM, respectively. Moreover, the CFET 122 SRAM has 11% faster read operation than FF 122 SRAM, respectively.

11 September 2023
Verified
Conference Paper
Closed access
MGMohit Gupta
Mohit Gupta
SCStefan Cosemans
Stefan Cosemans
PDPeter Debacker
Peter Debacker
WDWim Dehaene
Wim Dehaene
Deep neural networks (DNNs) are widely used in applications like image recognition for high prediction accuracy. Energy efficiency, flexibility, and area efficiency are critical parameters to bring DNN capabilities to the edge. This work presents an SRAM-based digital in-memory computing matrix-vector multiplier (DiMe MVM) that provides flexibility in terms of operand bit width and efficiently accommodates different matrix sizes. Measurement results on the 28 nm CMOS chip illustrate energy and throughput benefits over other state-of-the-art digital implementations.

25 March 2024 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Verified
Journal Article
Closed access
PYPengbo Yu
Pengbo Yu
FPFlavio Ponzina
Flavio Ponzina
ALAlexandre Levisse
Alexandre Levisse
MGMohit Gupta
Mohit Gupta
Dwaipayan BiswasDwaipayan Biswas
Dwaipayan Biswas
FCFrancky CATTHOOR
Francky CATTHOOR
The ever-increasing computational complexity and energy consumption of today’s applications, such as machine learning (ML) algorithms, not only strain the capabilities of the underlying hardware but also significantly restrict their wide deployment at the edge. Addressing these challenges, novel architecture solutions are required by leveraging opportunities exposed by algorithms, e.g., robustness to small-bitwidth operand quantization and high intrinsic data-level parallelism. However, traditional hardware single instruction multiple data (Hard SIMD) architectures only support a small set of operand bitwidths, limiting performance improvement. To fill the gap, this manuscript introduces a novel pipelined processor microarchitecture for arithmetic computing based on the software-defined SIMD (Soft SIMD) paradigm that can define arbitrary SIMD modes through control instructions at run-time. This microarchitecture is optimized for parallel fine-grained fixed-point arithmetic, such as shift/add. It can also efficiently execute sequential shift-add-based multiplication over SIMD subwords, thanks to zero-skipping and canonical signed digit (CSD) coding. A lightweight repacking unit allows changing subword bitwidth dynamically. These features are implemented within a tight energy and area budget. An energy consumption model is established through post-synthesis for performance assessment. We select heterogeneously quantized (HQ) convolutional neural networks (CNNs) from the ML domain as the benchmark and map it onto our microarchitecture. Experimental results showcase that our approach dramatically outperforms traditional Hard SIMD Multiplier-Adder regarding area and energy requirements. In particular, our microarchitecture occupies up to 59.9% less area than a Hard SIMD that supports fewer SIMD bitwidths, while consuming up to 50.1% less energy on average to execute HQ CNNs.

2 February 2024 in IEEE Transactions on Nanotechnology
Verified
Journal Article
Closed access
BWBowen Wang
Bowen Wang
FGFernando García-Redondo
Fernando García-Redondo
MBMarie Garcia Bardon
Marie Garcia Bardon
HOHyungrock Oh
Hyungrock Oh
MGMohit Gupta
Mohit Gupta
WDWim Dehaene
Wim Dehaene
This paper presents a physics-based compact model for Voltage-Controlled Magnetic Anisotropy (VCMA) MRAM, calibrated against fabricated devices. Our model addresses inherent stochasticity, offering a robust tool for the design and simulation of VCMA MRAM peripheral circuits. Achieving a tenfold increase in simulation speed compared to existing stochastic Landau-Lifshitz-Gilbert-Slonczewski (sLLGS) based models (10× to 100×), and overcoming accuracy problems related to VCMA macro-spin sLLGS simulations, our approach enables efficient exploration of MRAM based circuits. The model efficiency and accuracy are demonstrated through a practical use case.

6 August 2024 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
FMFanfan Meng
Fanfan Meng
SLSiang-Yun Lee
Siang-Yun Lee
OZOdysseas Zografos
Odysseas Zografos
MGMohit Gupta
Mohit Gupta
VNVan Dai Nguyen
Van Dai Nguyen
FCFlorin Ciubotaru
Florin Ciubotaru
It is envisaged that spintronic logic devices will ultimately be utilized in hybrid CMOS-spintronic systems where signal interconversion between magnetic and electrical domains via transducers takes place. This underscores the vital role of transducers in influencing the overall performance of such hybrid systems. This paper addresses the question: Can spintronic circuits based on Magnetic Tunnel Junction (MTJ) transducers outperform their state-of-the-art CMOS counterparts? To this end, we use the EPFL (École Polytechnique Fédérale de Lausanne) combinational benchmark sets, synthesize them in 7 nm CMOS and in MTJ transducer based spintronic technologies, and compare the two implementation methods in terms of Energy-Delay-Product (EDP). To fully utilize the technologies’ potential, CMOS and spintronic implementations are built upon standard Boolean and Majority Gates, respectively. For the spintronic circuits, we assumed that domain conversion (electric/magnetic to magnetic/electric) is performed by means of MTJs and the computation is accomplished by domain wall (DW)-based majority gates, and considered two EDP estimation scenarios: (i) Uniform Benchmarking, which ignores the circuit’s internal structure and only includes domain transducers’ power and delay contributions into the calculations, and (ii) Majority-Inverter-Graph Benchmarking, which also embeds the circuit structure, the associated critical path delay and energy consumption by DW propagation. Our results indicate that, for the uniform case, the spintronic route is better suited for the implementation of complex circuits with few inputs and outputs. On the other hand, when the circuit structure is also considered via majority and inverter synthesis, our analysis clearly indicates that in order to match and eventually outperform CMOS performance, MTJ transducers’ efficiency has to be improved by 3-4 orders of magnitude. While it is clear that for the time being the MTJ-based-spintronic way cannot compete with CMOS, further technological transducer developments may tip the balance, which, when combined with information non-volatility, may make spintronic implementation for certain applications that require a large number of calculations and have a rather limited amount of interaction with the environment.