Improving Efficiency in Neural Network Accelerator Using Operands Hamming Distance optimization

2020-02-13 · Meng Li, Yilei Li, Pierce Chuang, Liangzhen Lai, Vikas Chandra

Neural network accelerator is a key enabler for the on-device AI inference, for which energy efficiency is an important metric. The data-path energy, including the computation energy and the data movement energy among the arithmetic units, claims a significant part of the total accelerator energy. By revisiting the basic physics of the arithmetic logic circuits, we show that the data-path energy is highly correlated with the bit flips when streaming the input operands into the arithmetic units, defined as the hamming distance of the input operand matrices. Based on the insight, we propose a post-training optimization algorithm and a hamming-distance-aware training algorithm to co-design and co-optimize the accelerator and the network synergistically. The experimental results based on post-layout simulation with MobileNetV2 demonstrate on average 2.85X data-path energy reduction and up to 8.51X data-path energy reduction for certain layers.

📄 PDF Abstract BibTeX arXiv:2002.05293

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…

Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…

Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution …

Batch Normalization 설명 없음

Inverted Residual Block 설명 없음

Average Pooling 설명 없음

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

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…

PiC-BNN: A 128-kbit 65 nm Processing-in-CAM-Based End-to-End Binary Neural Network Accelerator

2026-01-08 · Yuval Harary, Almog Sharoni, Esteban Garzón, Marco Lanuzza 외 arxiv

Binary Neural Networks (BNNs), where weights and activations are constrained to binary values (+1, -1), are a highly efficient alternative to traditional neural networks. Unfortunately, typical BNNs, while binarizing lin…

RAPIDNN: In-Memory Deep Neural Network Acceleration Framework

2018-06-15 · Mohsen Imani, Mohammad Samragh, Yeseong Kim, Saransh Gupta 외

Deep neural networks (DNN) have demonstrated effectiveness for various applications such as image processing, video segmentation, and speech recognition. Running state-of-the-art DNNs on current systems mostly relies on …

Clustering speech-recognition Speech Recognition Video Segmentation+1

Binary Code Ranking with Weighted Hamming Distance

2013-06-01 · CVPR 2013 6 · Lei Zhang, Yongdong Zhang, Jinhu Tang, Ke Lu 외

Binary hashing has been widely used for efficient similarity search due to its query and storage efficiency. In most existing binary hashing methods, the high-dimensional data are embedded into Hamming space and the dist…

HammingMesh: A Network Topology for Large-Scale Deep Learning

2022-09-03 · Torsten Hoefler, Tommaso Bonato, Daniele De Sensi, Salvatore Di Girolamo 외

Numerous microarchitectural optimizations unlocked tremendous processing power for deep neural networks that in turn fueled the AI revolution. With the exhaustion of such optimizations, the growth of modern AI is now gat…

Deep Learning Scheduling

High Throughput Matrix-Matrix Multiplication between Asymmetric Bit-Width Operands

2020-08-03 · Dibakar Gope, Jesse Beu, Matthew Mattina

Matrix multiplications between asymmetric bit-width operands, especially between 8- and 4-bit operands are likely to become a fundamental kernel of many important workloads including neural networks and machine learning.…

BIG-bench Machine Learning Vocal Bursts Intensity Prediction