An In-Memory Analog Computing Co-Processor for Energy-Efficient CNN Inference on Mobile Devices

2021-05-24 · Mohammed Elbtity, Abhishek Singh, Brendan Reidy, Xiaochen Guo, Ramtin Zand

In this paper, we develop an in-memory analog computing (IMAC) architecture realizing both synaptic behavior and activation functions within non-volatile memory arrays. Spin-orbit torque magnetoresistive random-access memory (SOT-MRAM) devices are leveraged to realize sigmoidal neurons as well as binarized synapses. First, it is shown the proposed IMAC architecture can be utilized to realize a multilayer perceptron (MLP) classifier achieving orders of magnitude performance improvement compared to previous mixed-signal and digital implementations. Next, a heterogeneous mixed-signal and mixed-precision CPU-IMAC architecture is proposed for convolutional neural networks (CNNs) inference on mobile processors, in which IMAC is designed as a co-processor to realize fully-connected (FC) layers whereas convolution layers are executed in CPU. Architecture-level analytical models are developed to evaluate the performance and energy consumption of the CPU-IMAC architecture. Simulation results exhibit 6.5% and 10% energy savings for CPU-IMAC based realizations of LeNet and VGG CNN models, for MNIST and CIFAR-10 pattern recognition tasks, respectively.

📄 PDF Abstract BibTeX arXiv:2105.13904

Code (0)

등록된 구현이 없습니다.

Tasks

CPU

Methods 이 논문이 사용한 방법론

Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Analog, In-memory Compute Architectures for Artificial Intelligence

2023-01-13 · Patrick Bowen, Guy Regev, Nir Regev, Bruno Pedroni 외

This paper presents an analysis of the fundamental limits on energy efficiency in both digital and analog in-memory computing architectures, and compares their performance to single instruction, single data (scalar) mach…

Bias-Scalable Near-Memory CMOS Analog Processor for Machine Learning

2022-02-10 · Pratik Kumar, Ankita Nandi, Shantanu Chakrabartty, Chetan Singh Thakur

Bias-scalable analog computing is attractive for implementing machine learning (ML) processors with distinct power-performance specifications. For instance, ML implementations for server workloads are focused on higher c…

An Analog and Digital Hybrid Attention Accelerator for Transformers with Charge-based In-memory Computing

2024-09-08 · Ashkan Moradifirouzabadi, Divya Sri Dodla, Mingu Kang

The attention mechanism is a key computing kernel of Transformers, calculating pairwise correlations across the entire input sequence. The computing complexity and frequent memory access in computing self-attention put a…

A Microprocessor implemented in 65nm CMOS with Configurable and Bit-scalable Accelerator for Programmable In-memory Computing

2018-11-09 · Hongyang Jia, Yinqi Tang, Hossein Valavi, Jintao Zhang 외

This paper presents a programmable in-memory-computing processor, demonstrated in a 65nm CMOS technology. For data-centric workloads, such as deep neural networks, data movement often dominates when implemented with toda…

CPU

AnalogNAS: A Neural Network Design Framework for Accurate Inference with Analog In-Memory Computing

2023-05-17 · Hadjer Benmeziane, Corey Lammie, Irem Boybat, Malte Rasch 외

The advancement of Deep Learning (DL) is driven by efficient Deep Neural Network (DNN) design and new hardware accelerators. Current DNN design is primarily tailored for general-purpose use and deployment on commercially…