arXiv subjects

Amit Ranjan Trivedi

Publications and source records attributed to Amit Ranjan Trivedi.

48 records · Page 3Linked to original sources

arXiv2023

Towards Model-Size Agnostic, Compute-Free, Memorization-based Inference of Deep Learning

The rapid advancement of deep neural networks has significantly improved various tasks, such as image and speech recognition. However, as the complexity of these models increases, so does the computational cost and the number of parameters, making it difficult to deploy them on resource-constrained devices. This paper proposes a novel memorization-based inference (MBI) that is compute free and only requires lookups. Specifically, our work capitalizes on the inference mechanism of the recurrent attention model (RAM), where only a small window of input domain (glimpse) is processed in a one time step, and the outputs from multiple glimpses are combined through a hidden vector to determine the overall classification output of the problem. By leveraging the low-dimensionality of glimpse, our inference procedure stores key value pairs comprising of glimpse location, patch vector, etc. in a table. The computations are obviated during inference by utilizing the table to read out key-value pairs and performing compute-free inference by memorization. By exploiting Bayesian optimization and clustering, the necessary lookups are reduced, and accuracy is improved. We also present in-memory computing circuits to quickly look up the matching key vector to an input query. Compared to competitive compute-in-memory (CIM) approaches, MBI improves energy efficiency by almost 2.7 times than multilayer perceptions (MLP)-CIM and by almost 83 times than ResNet20-CIM for MNIST character recognition.

cs.LG↗

arXiv2023

Memory-Immersed Collaborative Digitization for Area-Efficient Compute-in-Memory Deep Learning

This work discusses memory-immersed collaborative digitization among compute-in-memory (CiM) arrays to minimize the area overheads of a conventional analog-to-digital converter (ADC) for deep learning inference. Thereby, using the proposed scheme, significantly more CiM arrays can be accommodated within limited footprint designs to improve parallelism and minimize external memory accesses. Under the digitization scheme, CiM arrays exploit their parasitic bit lines to form a within-memory capacitive digital-to-analog converter (DAC) that facilitates area-efficient successive approximation (SA) digitization. CiM arrays collaborate where a proximal array digitizes the analog-domain product-sums when an array computes the scalar product of input and weights. We discuss various networking configurations among CiM arrays where Flash, SA, and their hybrid digitization steps can be efficiently implemented using the proposed memory-immersed scheme. The results are demonstrated using a 65 nm CMOS test chip. Compared to a 40 nm-node 5-bit SAR ADC, our 65 nm design requires $\sim$25$\times$ less area and $\sim$1.4$\times$ less energy by leveraging in-memory computing structures. Compared to a 40 nm-node 5-bit Flash ADC, our design requires $\sim$51$\times$ less area and $\sim$13$\times$ less energy.

cs.AR↗

arXiv2023

Lightweight, Uncertainty-Aware Conformalized Visual Odometry

Data-driven visual odometry (VO) is a critical subroutine for autonomous edge robotics, and recent progress in the field has produced highly accurate point predictions in complex environments. However, emerging autonomous edge robotics devices like insect-scale drones and surgical robots lack a computationally efficient framework to estimate VO's predictive uncertainties. Meanwhile, as edge robotics continue to proliferate into mission-critical application spaces, awareness of model's the predictive uncertainties has become crucial for risk-aware decision-making. This paper addresses this challenge by presenting a novel, lightweight, and statistically robust framework that leverages conformal inference (CI) to extract VO's uncertainty bands. Our approach represents the uncertainties using flexible, adaptable, and adjustable prediction intervals that, on average, guarantee the inclusion of the ground truth across all degrees of freedom (DOF) of pose estimation. We discuss the architectures of generative deep neural networks for estimating multivariate uncertainty bands along with point (mean) prediction. We also present techniques to improve the uncertainty estimation accuracy, such as leveraging Monte Carlo dropout (MC-dropout) for data augmentation. Finally, we propose a novel training loss function that combines interval scoring and calibration loss with traditional training metrics--mean-squared error and KL-divergence--to improve uncertainty-aware learning. Our simulation results demonstrate that the presented framework consistently captures true uncertainty in pose estimations across different datasets, estimation models, and applied noise types, indicating its wide applicability.

cs.CV↗

arXiv2021

MC-CIM: Compute-in-Memory with Monte-Carlo Dropouts for Bayesian Edge Intelligence

We propose MC-CIM, a compute-in-memory (CIM) framework for robust, yet low power, Bayesian edge intelligence. Deep neural networks (DNN) with deterministic weights cannot express their prediction uncertainties, thereby pose critical risks for applications where the consequences of mispredictions are fatal such as surgical robotics. To address this limitation, Bayesian inference of a DNN has gained attention. Using Bayesian inference, not only the prediction itself, but the prediction confidence can also be extracted for planning risk-aware actions. However, Bayesian inference of a DNN is computationally expensive, ill-suited for real-time and/or edge deployment. An approximation to Bayesian DNN using Monte Carlo Dropout (MC-Dropout) has shown high robustness along with low computational complexity. Enhancing the computational efficiency of the method, we discuss a novel CIM module that can perform in-memory probabilistic dropout in addition to in-memory weight-input scalar product to support the method. We also propose a compute-reuse reformulation of MC-Dropout where each successive instance can utilize the product-sum computations from the previous iteration. Even more, we discuss how the random instances can be optimally ordered to minimize the overall MC-Dropout workload by exploiting combinatorial optimization methods. Application of the proposed CIM-based MC-Dropout execution is discussed for MNIST character recognition and visual odometry (VO) of autonomous drones. The framework reliably gives prediction confidence amidst non-idealities imposed by MC-CIM to a good extent. Proposed MC-CIM with 16x31 SRAM array, 0.85 V supply, 16nm low-standby power (LSTP) technology consumes 27.8 pJ for 30 MC-Dropout instances of probabilistic inference in its most optimal computing and peripheral configuration, saving 43% energy compared to typical execution.

cs.LG↗

arXiv2021

Probabilistic Localization of Insect-Scale Drones on Floating-Gate Inverter Arrays

We propose a novel compute-in-memory (CIM)-based ultra-low-power framework for probabilistic localization of insect-scale drones. The conventional probabilistic localization approaches rely on the three-dimensional (3D) Gaussian Mixture Model (GMM)-based representation of a 3D map. A GMM model with hundreds of mixture functions is typically needed to adequately learn and represent the intricacies of the map. Meanwhile, localization using complex GMM map models is computationally intensive. Since insect-scale drones operate under extremely limited area/power budget, continuous localization using GMM models entails much higher operating energy -- thereby, limiting flying duration and/or size of the drone due to a larger battery. Addressing the computational challenges of localization in an insect-scale drone using a CIM approach, we propose a novel framework of 3D map representation using a harmonic mean of "Gaussian-like" mixture (HMGM) model. The likelihood function useful for drone localization can be efficiently implemented by connecting many multi-input inverters in parallel, each programmed with the parameters of the 3D map model represented as HMGM. When the depth measurements are projected to the input of the implementation, the summed current of the inverters emulates the likelihood of the measurement. We have characterized our approach on an RGB-D indoor localization dataset. The average localization error in our approach is $\sim$0.1125 m which is only slightly degraded than software-based evaluation ($\sim$0.08 m). Meanwhile, our localization framework is ultra-low-power, consuming as little as $\sim$17 $μ$W power while processing a depth frame in 1.33 ms over hundred pose hypotheses in the particle-filtering (PF) algorithm used to localize the drone.

cs.RO↗

arXiv2021

ENOS: Energy-Aware Network Operator Search for Hybrid Digital and Compute-in-Memory DNN Accelerators

This work proposes a novel Energy-Aware Network Operator Search (ENOS) approach to address the energy-accuracy trade-offs of a deep neural network (DNN) accelerator. In recent years, novel inference operators have been proposed to improve the computational efficiency of a DNN. Augmenting the operators, their corresponding novel computing modes have also been explored. However, simplification of DNN operators invariably comes at the cost of lower accuracy, especially on complex processing tasks. Our proposed ENOS framework allows an optimal layer-wise integration of inference operators and computing modes to achieve the desired balance of energy and accuracy. The search in ENOS is formulated as a continuous optimization problem, solvable using typical gradient descent methods, thereby scalable to larger DNNs with minimal increase in training cost. We characterize ENOS under two settings. In the first setting, for digital accelerators, we discuss ENOS on multiply-accumulate (MAC) cores that can be reconfigured to different operators. ENOS training methods with single and bi-level optimization objectives are discussed and compared. We also discuss a sequential operator assignment strategy in ENOS that only learns the assignment for one layer in one training step, enabling greater flexibility in converging towards the optimal operator allocations. Furthermore, following Bayesian principles, a sampling-based variational mode of ENOS is also presented. ENOS is characterized on popular DNNs ShuffleNet and SqueezeNet on CIFAR10 and CIFAR100.

eess.SY↗

arXiv2021

MF-Net: Compute-In-Memory SRAM for Multibit Precision Inference using Memory-immersed Data Conversion and Multiplication-free Operators

We propose a co-design approach for compute-in-memory inference for deep neural networks (DNN). We use multiplication-free function approximators based on ell_1 norm along with a co-adapted processing array and compute flow. Using the approach, we overcame many deficiencies in the current art of in-SRAM DNN processing such as the need for digital-to-analog converters (DACs) at each operating SRAM row/column, the need for high precision analog-to-digital converters (ADCs), limited support for multi-bit precision weights, and limited vector-scale parallelism. Our co-adapted implementation seamlessly extends to multi-bit precision weights, it doesn't require DACs, and it easily extends to higher vector-scale parallelism. We also propose an SRAM-immersed successive approximation ADC (SA-ADC), where we exploit the parasitic capacitance of bit lines of SRAM array as a capacitive DAC. Since the dominant area overhead in SA-ADC comes due to its capacitive DAC, by exploiting the intrinsic parasitic of SRAM array, our approach allows low area implementation of within-SRAM SA-ADC. Our 8$\times$62 SRAM macro, which requires a 5-bit ADC, achieves $\sim$105 tera operations per second per Watt (TOPS/W) with 8-bit input/weight processing at 45 nm CMOS.

cs.AR↗

arXiv2020

Low Latency CMOS Hardware Acceleration for Fully Connected Layers in Deep Neural Networks

We present a novel low latency CMOS hardware accelerator for fully connected (FC) layers in deep neural networks (DNNs). The FC accelerator, FC-ACCL, is based on 128 8x8 or 16x16 processing elements (PEs) for matrix-vector multiplication, and 128 multiply-accumulate (MAC) units integrated with 128 High Bandwidth Memory (HBM) units for storing the pretrained weights. Micro-architectural details for CMOS ASIC implementations are presented and simulated performance is compared to recent hardware accelerators for DNNs for AlexNet and VGG 16. When comparing simulated processing latency for a 4096-1000 FC8 layer, our FC-ACCL is able to achieve 48.4 GOPS (with a 100 MHz clock) which improves on a recent FC8 layer accelerator quoted at 28.8 GOPS with a 150 MHz clock. We have achieved this considerable improvement by fully utilizing the HBM units for storing and reading out column-specific FClayer weights in 1 cycle with a novel colum-row-column schedule, and implementing a maximally parallel datapath for processing these weights with the corresponding MAC and PE units. When up-scaled to 128 16x16 PEs, for 16x16 tiles of weights, the design can reduce latency for the large FC6 layer by 60 % in AlexNet and by 3 % in VGG16 when compared to an alternative EIE solution which uses compression.

cs.AR↗

arXiv2020

Low Power Unsupervised Anomaly Detection by Non-Parametric Modeling of Sensor Statistics

This work presents AEGIS, a novel mixed-signal framework for real-time anomaly detection by examining sensor stream statistics. AEGIS utilizes Kernel Density Estimation (KDE)-based non-parametric density estimation to generate a real-time statistical model of the sensor data stream. The likelihood estimate of the sensor data point can be obtained based on the generated statistical model to detect outliers. We present CMOS Gilbert Gaussian cell-based design to realize Gaussian kernels for KDE. For outlier detection, the decision boundary is defined in terms of kernel standard deviation ($σ_{Kernel}$) and likelihood threshold ($P_{Thres}$). We adopt a sliding window to update the detection model in real-time. We use time-series dataset provided from Yahoo to benchmark the performance of AEGIS. A f1-score higher than 0.87 is achieved by optimizing parameters such as length of the sliding window and decision thresholds which are programmable in AEGIS. Discussed architecture is designed using 45nm technology node and our approach on average consumes $\sim$75 $μ$W power at a sampling rate of 2 MHz while using ten recent inlier samples for density estimation. \textcolor{red}{Full-version of this research has been published at IEEE TVLSI}

eess.SP↗

arXiv2020

$MC^2RAM$: Markov Chain Monte Carlo Sampling in SRAM for Fast Bayesian Inference

This work discusses the implementation of Markov Chain Monte Carlo (MCMC) sampling from an arbitrary Gaussian mixture model (GMM) within SRAM. We show a novel architecture of SRAM by embedding it with random number generators (RNGs), digital-to-analog converters (DACs), and analog-to-digital converters (ADCs) so that SRAM arrays can be used for high performance Metropolis-Hastings (MH) algorithm-based MCMC sampling. Most of the expensive computations are performed within the SRAM and can be parallelized for high speed sampling. Our iterative compute flow minimizes data movement during sampling. We characterize power-performance trade-off of our design by simulating on 45 nm CMOS technology. For a two-dimensional, two mixture GMM, the implementation consumes ~ 91 micro-Watts power per sampling iteration and produces 500 samples in 2000 clock cycles on an average at 1 GHz clock frequency. Our study highlights interesting insights on how low-level hardware non-idealities can affect high-level sampling characteristics, and recommends ways to optimally operate SRAM within area/power constraints for high performance sampling.

eess.SP↗

arXiv2019

Supported-BinaryNet: Bitcell Array-based Weight Supports for Dynamic Accuracy-Latency Trade-offs in SRAM-based Binarized Neural Network

In this work, we introduce bitcell array-based support parameters to improve the prediction accuracy of SRAM-based binarized neural network (SRAM-BNN). Our approach enhances the training weight space of SRAM-BNN while requiring minimal overheads to a typical design. More flexibility of the weight space leads to higher prediction accuracy in our design. We adapt row digital-to-analog (DAC) converter, and computing flow in SRAM-BNN for bitcell array-based weight supports. Using the discussed interventions, our scheme also allows a dynamic trade-off of accuracy against latency to address dynamic latency constraints in typical real-time applications. We specifically discuss results on two training cases: (i) learning of support parameters on a pre-trained BNN and (ii) simultaneous learning of supports and weight binarization. In the former case, our approach reduces classification error in MNIST by 35.71% (error rate decreases from 1.4% to 0.91%). In the latter case, the error is reduced by 27.65% (error rate decreases from 1.4% to 1.13%). To reduce the power overheads, we propose a dynamic drop out a part of the support parameters. Our architecture can drop out 52% of the bitcell array-based support parameters without losing accuracy. We also characterize our design under varying degrees of process variability in the transistors.

cs.NE↗

arXiv2019

Using your ADC and Backend Capacitors to Authenticate for Free: (Virtually) Free from Database, Enrollment, and Excessive Area/Power Overhead

Detection of counterfeit chips has emerged as a crucial concern. Physically-unclonable-function (PUF)-based techniques are widely used for authentication, however, require dedicated hardware and large signature database. In this work, we show intrinsic & database-free authentication using back-end capacitors. The discussed technique simplifies authentication setup and reduces the test cost. We show that an analog-to-digital converter (ADC) can be modified for back-end capacitor-based authentication in addition to its regular functionality; hence, a dedicated authentication module is not necessary. Moreover, since back-end capacitors are quite insensitive to temperature and aging-induced variations than transistors, the discussed technique result in a more reliable authentication than transistor PUF-based authentication. The modifications to conventional ADC incur 3.2% power overhead and 75% active-area overhead; however, arguably, the advantages of the discussed intrinsic & database-free authentication outweigh the overheads. Full version of this article is published at IEEE TVLSI.

eess.SP↗