首页/论文/1901.09614

arXiv 1901.096142019-01-28cs.NEcs.CVcs.LG

A Simple Method to Reduce Off-chip Memory Accesses on Convolutional Neural Networks

Samsung Electronics（三星电子）

Doyun Kim, Kyoung-Young Kim, Sangsoo Ko, Sanghyuck Ha

备注：: 9 pages, 10 figures, under review (by ICML2019)

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

For convolutional neural networks, a simple algorithm to reduce off-chip memory accesses is proposed by maximally utilizing on-chip memory in a neural process unit. Especially, the algorithm provides an effective way to process a module which consists of multiple branches and a merge layer. For Inception-V3 on Samsung's NPU in Exynos, our evaluation shows that the proposed algorithm makes off-chip memory accesses reduced by 1/50, and accordingly achieves 97.59 % reduction in the amount of feature-map data to be transferred from/to off-chip memory.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Recursive Binary Neural Network Learning Model with 2.28b/Weight Storage Requirement

This paper presents a storage-efficient learning model titled Recursive Binary Neural Networks for sensing devices having a limited amount of on-chip data storage such as < 100's kilo-Bytes. The main idea of the proposed model is to recursively recycle data storage of synaptic weights (parameters) during training. This enables a device with a given storage constraint to train and instantiate a neural network classifier with a larger number of weights on a chip and with a less number of off-chip storage accesses. This enables higher classification accuracy, shorter training time, less energy di…

2017-09-15cs.NE

Selective Deep Convolutional Neural Network for Low Cost Distorted Image Classification

Deep convolutional neural networks have proven to be well suited for image classification applications. However, if there is distortion in the image, the classification accuracy can be significantly degraded, even with state-of-the-art neural networks. The accuracy cannot be significantly improved by simply training with distorted images. Instead, this paper proposes a multiple neural network topology referred to as a selective deep convolutional neural network. By modifying existing state-of-the-art neural networks in the proposed manner, it is shown that a similar level of classification acc…

2019-02-14cs.CVcs.NE

Improving Memory Utilization in Convolutional Neural Network Accelerators

CSEM SA（瑞士电子与微技术中心）；Swiss Federal Institute of Technology, ETH Zurich（苏黎世联邦理工学院）；University of Bologna（博洛尼亚大学）

While the accuracy of convolutional neural networks has achieved vast improvements by introducing larger and deeper network architectures, also the memory footprint for storing their parameters and activations has increased. This trend especially challenges power- and resource-limited accelerator designs, which are often restricted to store all network data in on-chip memory to avoid interfacing energy-hungry external memories. Maximizing the network size that fits on a given accelerator thus requires to maximize its memory utilization. While the traditionally used ping-pong buffering techniqu…

2021-04-06cs.CVcs.LGcs.NE

A Systematic Approach to Blocking Convolutional Neural Networks

Convolutional Neural Networks (CNNs) are the state of the art solution for many computer vision problems, and many researchers have explored optimized implementations. Most implementations heuristically block the computation to deal with the large data sizes and high data reuse of CNNs. This paper explores how to block CNN computations for memory locality by creating an analytical model for CNN-like loop nests. Using this model we automatically derive optimized blockings for common networks that improve the energy efficiency of custom hardware implementations by up to an order of magnitude. Co…

2016-06-14cs.DCcs.NE

A 28-nm Convolutional Neuromorphic Processor Enabling Online Learning with Spike-Based Retinas

In an attempt to follow biological information representation and organization principles, the field of neuromorphic engineering is usually approached bottom-up, from the biophysical models to large-scale integration in silico. While ideal as experimentation platforms for cognitive computing and neuroscience, bottom-up neuromorphic processors have yet to demonstrate an efficiency advantage compared to specialized neural network accelerators for real-world problems. Top-down approaches aim at answering this difficulty by (i) starting from the applicative problem and (ii) investigating how to ma…

2020-05-13cs.ETcs.NEeess.IV

TrIM：面向卷积神经网络的三角输入移动脉动阵列——架构与硬件实现

TrIM, Triangular Input Movement Systolic Array for Convolutional Neural Networks: Architecture and Hardware Implementation

The University of Edinburgh（爱丁堡大学）；School of Engineering（工程学院）；Centre for Electronics Frontiers（电子前沿中心）；Institute for Integrated Micro and Nano Systems（集成微纳系统研究所）

本研究提出基于三角输入移动数据流的TrIM脉动阵列CNN硬件架构，FPGA实现后在访存次数、能效上显著优于现有方案。

2025-01-14cs.AIcs.ARcs.NE

更多相关论文收起更多论文

Darwin3：具有新型指令集架构和片上学习的大规模神经形态芯片

Darwin3: A large-scale neuromorphic chip with a Novel ISA and On-Chip Learning

本文提出大规模神经形态芯片Darwin3，采用新型指令集架构和片上学习，支持235万神经元，通过连接压缩显著提升代码密度和内存效率，并在准确性和延迟上达到领先水平。

2023-12-29cs.ARcs.NE

BinarEye: An Always-On Energy-Accuracy-Scalable Binary CNN Processor With All Memory On Chip in 28nm CMOS

This paper introduces BinarEye: a digital processor for always-on Binary Convolutional Neural Networks. The chip maximizes data reuse through a Neuron Array exploiting local weight Flip-Flops. It stores full network models and feature maps and hence requires no off-chip bandwidth, which leads to a 230 1b-TOPS/W peak efficiency. Its 3 levels of flexibility - (a) weight reconfiguration, (b) a programmable network depth and (c) a programmable network width - allow trading energy for accuracy depending on the task's requirements. BinarEye's full system input-to-label energy consumption ranges from…

2018-04-16cs.DCcs.NE

A Power-Efficient Binary-Weight Spiking Neural Network Architecture for Real-Time Object Classification

National Tsing Hua University（国立清华大学）；National Cheng Kung University（国立成功大学）；Industrial Technology Research Institute（工业技术研究院）

Neural network hardware is considered an essential part of future edge devices. In this paper, we propose a binary-weight spiking neural network (BW-SNN) hardware architecture for low-power real-time object classification on edge platforms. This design stores a full neural network on-chip, and hence requires no off-chip bandwidth. The proposed systolic array maximizes data reuse for a typical convolutional layer. A 5-layer convolutional BW-SNN hardware is implemented in 90nm CMOS. Compared with state-of-the-art designs, the area cost and energy per classification are reduced by 7$\times$ and 2…

2020-03-12cs.ARcs.CVcs.NE

XNORBIN: A 95 TOp/s/W Hardware Accelerator for Binary Convolutional Neural Networks

ETH Zurich（苏黎世联邦理工学院）

Deploying state-of-the-art CNNs requires power-hungry processors and off-chip memory. This precludes the implementation of CNNs in low-power embedded systems. Recent research shows CNNs sustain extreme quantization, binarizing their weights and intermediate feature maps, thereby saving 8-32\x memory and collapsing energy-intensive sum-of-products into XNOR-and-popcount operations. We present XNORBIN, an accelerator for binary CNNs with computation tightly coupled to memory for aggressive data reuse. Implemented in UMC 65nm technology XNORBIN achieves an energy efficiency of 95 TOp/s/W and an a…

2018-03-05cs.AIcs.ARcs.CV

Structured Pruning of Deep Convolutional Neural Networks

Seoul National University（首尔大学）

Real time application of deep learning algorithms is often hindered by high computational complexity and frequent memory accesses. Network pruning is a promising technique to solve this problem. However, pruning usually results in irregular network connections that not only demand extra representation efforts but also do not fit well on parallel computation. We introduce structured sparsity at various scales for convolutional neural networks, which are channel wise, kernel wise and intra kernel strided sparsity. This structured sparsity is very advantageous for direct computational resource sa…

2015-12-29cs.LGcs.NEstat.ML

Shenjing: A low power reconfigurable neuromorphic accelerator with partial-sum and spike networks-on-chip

The next wave of on-device AI will likely require energy-efficient deep neural networks. Brain-inspired spiking neural networks (SNN) has been identified to be a promising candidate. Doing away with the need for multipliers significantly reduces energy. For on-device applications, besides computation, communication also incurs a significant amount of energy and time. In this paper, we propose Shenjing, a configurable SNN architecture which fully exposes all on-chip communications to software, enabling software mapping of SNN models with high accuracy at low power. Unlike prior SNN architecture…

2019-11-25cs.ARcs.ETcs.NE

MorphIC: A 65-nm 738k-Synapse/mm$^2$ Quad-Core Binary-Weight Digital Neuromorphic Processor with Stochastic Spike-Driven Online Learning

Recent trends in the field of neural network accelerators investigate weight quantization as a means to increase the resource- and power-efficiency of hardware devices. As full on-chip weight storage is necessary to avoid the high energy cost of off-chip memory accesses, memory reduction requirements for weight storage pushed toward the use of binary weights, which were demonstrated to have a limited accuracy reduction on many applications when quantization-aware training techniques are used. In parallel, spiking neural network (SNN) architectures are explored to further reduce power when proc…

2019-07-16cs.ETcs.NE

Speck：一种具有低延迟327K神经元卷积神经网络处理流水线的智能事件视觉传感器

Speck: A Smart event-based Vision Sensor with a low latency 327K Neuron Convolutional Neuronal Network Processing Pipeline

SynSense AG；SynSense；University of Groningen（格罗宁根大学）；Zernike Institute for Advanced Materials, University of Groningen（格罗宁根大学泽尼克先进材料研究所）；Groningen Cognitive Systems and Materials Center (CogniGron), University of Groningen（格罗宁根大学格罗宁根认知系统与材料中心（CogniGron））

本文提出Speck智能视觉SoC，集成事件相机与低功耗异步sCNN，实现9层网络单事件3.36微秒延迟，以低成本和低能耗支持边缘端到端视觉处理。

2024-05-27cs.LGcs.NEeess.IV

Probabilistic spike propagation for FPGA implementation of spiking neural networks

IIT Madras（印度理工学院马德拉斯分校）

Evaluation of spiking neural networks requires fetching a large number of synaptic weights to update postsynaptic neurons. This limits parallelism and becomes a bottleneck for hardware. We present an approach for spike propagation based on a probabilistic interpretation of weights, thus reducing memory accesses and updates. We study the effects of introducing randomness into the spike processing, and show on benchmark networks that this can be done with minimal impact on the recognition accuracy. We present an architecture and the trade-offs in accuracy on fully connected and convolutional net…

2020-01-07cs.LGcs.NE

A Self-Driving Robot Using Deep Convolutional Neural Networks on Neuromorphic Hardware

University of California, Irvine（加州大学欧文分校）；Northrop Grumman（诺斯洛普·格鲁曼公司）；University of Maryland（马里兰大学）；BrainChip LLC（BrainChip有限责任公司）

Neuromorphic computing is a promising solution for reducing the size, weight and power of mobile embedded systems. In this paper, we introduce a realization of such a system by creating the first closed-loop battery-powered communication system between an IBM TrueNorth NS1e and an autonomous Android-Based Robotics platform. Using this system, we constructed a dataset of path following behavior by manually driving the Android-Based robot along steep mountain trails and recording video frames from the camera mounted on the robot along with the corresponding motor commands. We used this dataset t…

2016-11-04cs.NEcs.RO