CN110178146A - 反卷积器及其所应用的人工智能处理装置 - Google Patents

反卷积器及其所应用的人工智能处理装置 Download PDF

Info

Publication number
CN110178146A
CN110178146A CN201880002766.XA CN201880002766A CN110178146A CN 110178146 A CN110178146 A CN 110178146A CN 201880002766 A CN201880002766 A CN 201880002766A CN 110178146 A CN110178146 A CN 110178146A
Authority
CN
China
Prior art keywords
convolution operation
deconvolution
data
output
external memory
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201880002766.XA
Other languages
English (en)
Other versions
CN110178146B (zh
Inventor
肖梦秋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Corerain Technologies Co Ltd
Original Assignee
Shenzhen Corerain Technologies Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Corerain Technologies Co Ltd filed Critical Shenzhen Corerain Technologies Co Ltd
Publication of CN110178146A publication Critical patent/CN110178146A/zh
Application granted granted Critical
Publication of CN110178146B publication Critical patent/CN110178146B/zh
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Theoretical Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Neurology (AREA)
  • Complex Calculations (AREA)
  • Microcomputers (AREA)
  • Image Processing (AREA)

Abstract

一种反卷积器(100)及其所应用的人工智能处理装置，电性连接至外部存储器(200)，所述外部存储器(200)存储有待处理数据及权重参数；反卷积器(100)包括：参数缓存器(110)、输入缓存器、反卷积运算电路(140)及输出缓存器(150)；参数缓存器(110)用于接收并输出所述权重参数；输入缓存器包括：多个相连的行缓存器，用于接收并输出待处理数据；其中，各行缓存器每输出一位数据则集合形成一列数据输出；反卷积运算电路(140)用于从所述输入缓存器接收待处理数据、从参数缓存器(110)接收权重参数，据以进行反卷积运算并输出反卷积运算结果；输出缓存器(150)用于接收反卷积运算结果并将该反卷积运算结果向外部存储器(200)输出。可有效解决现有技术中通过软件运算实现带来的处理速度变慢，对处理器性能要求高的问题。

Description

PCT国内申请，说明书已公开。

Claims (9)

  1. PCT国内申请，权利要求书已公开。
CN201880002766.XA 2018-01-15 2018-01-15 反卷积器及其所应用的人工智能处理装置 Active CN110178146B (zh)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/072659 WO2019136747A1 (zh) 2018-01-15 2018-01-15 反卷积器及其所应用的人工智能处理装置

Publications (2)

Publication Number Publication Date
CN110178146A true CN110178146A (zh) 2019-08-27
CN110178146B CN110178146B (zh) 2023-05-12

Family

ID=67218472

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201880002766.XA Active CN110178146B (zh) 2018-01-15 2018-01-15 反卷积器及其所应用的人工智能处理装置

Country Status (2)

Country Link
CN (1) CN110178146B (zh)
WO (1) WO2019136747A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110727633A (zh) * 2019-09-17 2020-01-24 广东高云半导体科技股份有限公司 基于SoC FPGA的边缘人工智能计算系统构架

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106022468A (zh) * 2016-05-17 2016-10-12 成都启英泰伦科技有限公司 人工神经网络处理器集成电路及该集成电路的设计方法
CN106066783A (zh) * 2016-06-02 2016-11-02 华为技术有限公司 基于幂次权重量化的神经网络前向运算硬件结构
CN106228240A (zh) * 2016-07-30 2016-12-14 复旦大学 基于fpga的深度卷积神经网络实现方法
US20160379109A1 (en) * 2015-06-29 2016-12-29 Microsoft Technology Licensing, Llc Convolutional neural networks on hardware accelerators
CN106355244A (zh) * 2016-08-30 2017-01-25 深圳市诺比邻科技有限公司 卷积神经网络的构建方法及系统
CN106875011A (zh) * 2017-01-12 2017-06-20 南京大学 二值权重卷积神经网络加速器的硬件架构及其计算流程
US20170221176A1 (en) * 2016-01-29 2017-08-03 Fotonation Limited Convolutional neural network
CN107239824A (zh) * 2016-12-05 2017-10-10 北京深鉴智能科技有限公司 用于实现稀疏卷积神经网络加速器的装置和方法
CN107392309A (zh) * 2017-09-11 2017-11-24 东南大学—无锡集成电路技术研究所 一种基于fpga的通用定点数神经网络卷积加速器硬件结构
CN107403117A (zh) * 2017-07-28 2017-11-28 西安电子科技大学 基于fpga的三维卷积器

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160379109A1 (en) * 2015-06-29 2016-12-29 Microsoft Technology Licensing, Llc Convolutional neural networks on hardware accelerators
US20170221176A1 (en) * 2016-01-29 2017-08-03 Fotonation Limited Convolutional neural network
CN106022468A (zh) * 2016-05-17 2016-10-12 成都启英泰伦科技有限公司 人工神经网络处理器集成电路及该集成电路的设计方法
CN106066783A (zh) * 2016-06-02 2016-11-02 华为技术有限公司 基于幂次权重量化的神经网络前向运算硬件结构
CN106228240A (zh) * 2016-07-30 2016-12-14 复旦大学 基于fpga的深度卷积神经网络实现方法
CN106355244A (zh) * 2016-08-30 2017-01-25 深圳市诺比邻科技有限公司 卷积神经网络的构建方法及系统
CN107239824A (zh) * 2016-12-05 2017-10-10 北京深鉴智能科技有限公司 用于实现稀疏卷积神经网络加速器的装置和方法
CN106875011A (zh) * 2017-01-12 2017-06-20 南京大学 二值权重卷积神经网络加速器的硬件架构及其计算流程
CN107403117A (zh) * 2017-07-28 2017-11-28 西安电子科技大学 基于fpga的三维卷积器
CN107392309A (zh) * 2017-09-11 2017-11-24 东南大学—无锡集成电路技术研究所 一种基于fpga的通用定点数神经网络卷积加速器硬件结构

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
HONGXIANG FAN 等: "F-C3D: FPGA-based 3-Dimensional Convolutional Neural Network", 《2017 27TH INTERNATIONAL CONFERENCE ON FIELD PROGRAMMABLE LOGIC AND APPLICATIONS (FPL)》 *

Also Published As

Publication number Publication date
CN110178146B (zh) 2023-05-12
WO2019136747A1 (zh) 2019-07-18

Similar Documents

Publication Publication Date Title
CN109416756A (zh) 卷积器及其所应用的人工智能处理装置
US20230325348A1 (en) Performing concurrent operations in a processing element
CN110050267B (zh) 用于数据管理的系统和方法
CN109284817B (zh) 深度可分离卷积神经网络处理架构/方法/系统及介质
US11775430B1 (en) Memory access for multiple circuit components
CN109784489A (zh) 基于fpga的卷积神经网络ip核
WO2020073211A1 (zh) 运算加速器、处理方法及相关设备
CN107704923A (zh) 卷积神经网络运算电路
CN109726822B (zh) 运算方法、装置及相关产品
CN110766127B (zh) 神经网络计算专用电路及其相关计算平台与实现方法
CN109685201A (zh) 运算方法、装置及相关产品
WO2023045445A1 (zh) 数据处理装置、数据处理方法及相关产品
WO2023123919A1 (zh) 数据处理电路、数据处理方法及相关产品
CN109496319A (zh) 人工智能处理装置硬件优化方法、系统、存储介质、终端
CN111047022A (zh) 一种计算装置及相关产品
Shahshahani et al. Memory optimization techniques for fpga based cnn implementations
Xie et al. High throughput CNN accelerator design based on FPGA
Xiao et al. FPGA-based scalable and highly concurrent convolutional neural network acceleration
WO2022151779A1 (zh) 卷积运算的实现方法、数据处理方法及装置
CN110178146A (zh) 反卷积器及其所应用的人工智能处理装置
Song et al. Design and implementation of convolutional neural networks accelerator based on multidie
CN109711538B (zh) 运算方法、装置及相关产品
CN109740729B (zh) 运算方法、装置及相关产品
CN214586992U (zh) 神经网络加速电路、图像处理器及三维成像电子设备
CN109993290A (zh) 集成电路芯片装置及相关产品

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant