Vaidehi Garg

Vaidehi Garg

Auto-generated profile, based on publicly available information

Vaidehi Garg

School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
21 February 2024 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
PHPo-Kai Hsu
Po-Kai Hsu
VGVaidehi Garg
Vaidehi Garg
ALAnni Lu
Anni Lu
SYShimeng Yu
Shimeng Yu
Hyperdimensional (HD) computing is a promising paradigm for large-scale genome sequencing. In prior work, we proposed a 3D NAND-based HD computing engine as an energy-efficient solution for sequencing several gigabytes or terabytes of genomic data. In this work, we introduce an improved HD computing engine for genome sequencing that leverages heterogeneous 3D integration techniques. We employ Cu-Cu hybrid bonding and CMOS under array (CuA) technologies to integrate the digital logic tier with the 3D NAND-based associative memory tier. We benchmark the performance of the proposed hardware design using a dataset of 10,575 microorganism genomes. The results indicate the robustness of the classification accuracy despite device non-idealities. Compared to conventional methods, the proposed design reduces the system-level energy consumption by $1000\times $ , provided the data is not offloaded from the solid-state drive to the computing units.

21 March 2025 in IEEE Electron Device Letters
Verified
Journal Article
Closed access
OPOmkar Phadke
Omkar Phadke
PHPo-Kai Hsu
Po-Kai Hsu
YLYuan-Chun Luo
Yuan-Chun Luo
JSJanak Sharda
Janak Sharda
VGVaidehi Garg
Vaidehi Garg
SYShimeng Yu
Shimeng Yu
In this letter, a ferroelectric field effect transistor (FeFET)-based charge-domain ternary content addressable memory (TCAM) is experimentally demonstrated for in-memory search. Specifically, foundry based FeFETs are configured in non-volatile capacitor (nvCAP) mode for charge-domain computation. A single TCAM cell consisting of 2 nvCAPs (i.e. two FeFETs) is used to perform the Store: bit ‘0’, ‘1’, ‘X’ and Search: bit ‘0’, ‘1’, ‘X’ operations. Further, SPICE simulations are performed to evaluate the feasibility of a scaled nvCAP device in a large TCAM array. The low CON/COFF ratio of a scaled device can lead to false-positive matchings, which can be countered by introducing a dummy column and input dependent charge cancellation. Finally, the charge-domain nvCAP TCAM is benchmarked against other proposed candidates, showing a ~1.5× improvement in energy efficiency over FeFET based current domain TCAM, and a ~3.3× improvement compared to resistive random access memory (RRAM) based TCAM.

3 December 2025 in IEEE Solid-State Circuits Letters
Verified
Journal Article
Closed access
VGVaidehi Garg
Vaidehi Garg
JJJianwei Jia
Jianwei Jia
OPOmkar Phadke
Omkar Phadke
SYShimeng Yu
Shimeng Yu
Compute-in-memory (CIM) using emerging nonvolatile memory devices is a promising candidate for energy-efficient deep neural network (DNN) inference at the edge. Ferroelectric field-effect transistors (FeFETs) have recently gained attention as nonvolatile, CMOS-compatible devices with a higher on/off ratio and lower read and write energy compared to resistive random-access memory (RRAM). This work demonstrates a 4-kb FeFET-CIM macro fabricated in the GlobalFoundries 28-nm high-k metal gate (HKMG) process. The macro consists of a $64\times 64$ FeFET array with peripheral circuits for program, erase, and current-mode CIM operations and eight 4-bit Flash ADCs to quantize the analog partial sums. The proposed design achieves an energy efficiency of 346.6 TOPS/W for $1\times 1$ b MAC, an inference accuracy of 85.2% for 16 row parallel compute with 4-bit ADC resolution, and 89.1% with 8 row parallel compute with 3-bit resolution, compared to a software baseline of 89.7% on the VGG-8 model for CIFAR-10.

30 August 2023 in IEEE Design & Test
Verified
Journal Article
Closed access
ZCZeyu Chen
Zeyu Chen
ABAnkur Bindal
Ankur Bindal
VGVaidehi Garg
Vaidehi Garg
TKTushar Krishna
Tushar Krishna
In this article, the authors leverage a probe-based deadlock detection system and propose a deadlock recovery mechanism for interconnection networks.

1 January 2026 in IEEE Open Journal of the Solid-State Circuits Society
Verified
Journal Article
Open access
MCMatthew Chen
Matthew Chen
VGVaidehi Garg
Vaidehi Garg
JJJianwei Jia
Jianwei Jia
JSJay Sonawane
Jay Sonawane
OPOmkar Phadke
Omkar Phadke
SYShimeng Yu
Shimeng Yu

1 December 2025 in IEEE Solid-State Circuits Letters
Verified
Journal Article
Closed access
YKYuyao Kong
Yuyao Kong
HLHaomei Liu
Haomei Liu
VGVaidehi Garg
Vaidehi Garg
SYShimeng Yu
Shimeng Yu
This work presents a compact digital compute-in-memory (DCIM) Ising annealer targeting large-scale combinatorial optimization. A centroid-based weight mapping method combined with hierarchical clustering reduces the memory capacity required for traveling salesman problem (TSP) weights, enabling efficient mapping with limited on-chip storage. An asynchronous random number generator (ARNG) based on dual ring oscillator provides high-quality randomness with tunable probability bias while incurring much smaller hardware overhead than conventional linear feedback shift registers (LFSRs). The proposed architecture was fabricated in 28-nm CMOS, integrating a DCIM array and an on-chip asynchronous-clock-based random number generator (ARNG). Measurement results demonstrate annealing on TSP problems up to 3038 cities. Compared to LFSR-based randomness, the ARNG achieves solution quality closer to the software baseline while maintaining compact area. This design highlights a scalable and energy-efficient hardware framework for Ising-based optimization, showing clear advantages in both memory efficiency and random source quality over prior approaches.