CN114846478A - 神经网络处理的方法、装置与系统 - Google Patents

神经网络处理的方法、装置与系统 Download PDF

Info

Publication number
CN114846478A
CN114846478A CN202080089427.7A CN202080089427A CN114846478A CN 114846478 A CN114846478 A CN 114846478A CN 202080089427 A CN202080089427 A CN 202080089427A CN 114846478 A CN114846478 A CN 114846478A
Authority
CN
China
Prior art keywords
array
neural network
storage module
reading
convolution operation
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.)
Pending
Application number
CN202080089427.7A
Other languages
English (en)
Inventor
洪宗会
霍元宏
沈广冲
张广飞
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.)
Beijing Suneng Technology Co ltd
Original Assignee
Beijing Suneng Technology 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 Beijing Suneng Technology Co ltd filed Critical Beijing Suneng Technology Co ltd
Publication of CN114846478A publication Critical patent/CN114846478A/zh
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F7/00—Methods or arrangements for processing data by operating upon the order or content of the data handled
    • G06F7/38—Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation
    • G06F7/48—Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation using non-contact-making devices, e.g. tube, solid state device; using unspecified devices
    • G06F7/544—Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation using non-contact-making devices, e.g. tube, solid state device; using unspecified devices for evaluating functions by calculation
    • G06F7/5443—Sum of products
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/15—Correlation function computation including computation of convolution operations
    • G06F17/153—Multidimensional correlation or convolution
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5061—Partitioning or combining of resources
    • G06F9/5072—Grid computing
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Algebra (AREA)
  • Databases & Information Systems (AREA)
  • Neurology (AREA)
  • Image Analysis (AREA)

Abstract

一种神经网络处理的方法、装置(100)与系统(1000)，该装置(100)包括：第一计算阵列(10)，用于执行第一类神经网络运算；第二计算阵列(20)，用于执行第二类神经网络运算，第二类神经网络运算不同于第一类神经网络运算；控制模块(30)，用于控制第一计算阵列(10)执行第一类神经网络运算，以及控制第二计算阵列(20)执行第二类神经网络运算。通过包括多个用于执行神经网络中不同类型的运算的计算阵列，从而可以实现对神经网络中多种类型的运算进行加速，从而可以提高深度神经网络的计算效率。

Description

PCT国内申请，说明书已公开。

Claims (50)

  1. PCT国内申请，权利要求书已公开。
CN202080089427.7A 2020-01-16 2020-01-16 神经网络处理的方法、装置与系统 Pending CN114846478A (zh)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/072475 WO2021142713A1 (zh) 2020-01-16 2020-01-16 神经网络处理的方法、装置与系统

Publications (1)

Publication Number Publication Date
CN114846478A true CN114846478A (zh) 2022-08-02

Family

ID=76863478

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202080089427.7A Pending CN114846478A (zh) 2020-01-16 2020-01-16 神经网络处理的方法、装置与系统

Country Status (4)

Country Link
US (1) US20220326912A1 (zh)
EP (1) EP4064134B1 (zh)
CN (1) CN114846478A (zh)
WO (1) WO2021142713A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11899745B1 (en) * 2020-08-19 2024-02-13 Meta Platforms Technologies, Llc Systems and methods for speech or text processing using matrix operations
US20230214185A1 (en) * 2021-12-28 2023-07-06 Microsoft Technology Licensing, Llc Multipurpose multiply-accumulator array
CN116306811B (zh) * 2023-02-28 2023-10-27 苏州亿铸智能科技有限公司 一种针对ReRAM部署神经网络的权重分配方法

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB201607713D0 (en) * 2016-05-03 2016-06-15 Imagination Tech Ltd Convolutional neural network
EP3497624A1 (en) * 2016-08-13 2019-06-19 Intel Corporation Apparatuses, methods, and systems for neural networks
US10438115B2 (en) * 2016-12-01 2019-10-08 Via Alliance Semiconductor Co., Ltd. Neural network unit with memory layout to perform efficient 3-dimensional convolutions
CN107341545A (zh) * 2017-07-25 2017-11-10 郑州云海信息技术有限公司 一种深度神经网络运算系统及方法
CN108764466B (zh) * 2018-03-07 2022-02-11 东南大学 基于现场可编程门阵列的卷积神经网络硬件及其加速方法
EP3557485B1 (en) * 2018-04-19 2021-05-26 Aimotive Kft. Method for accelerating operations and accelerator apparatus
CN108665059A (zh) * 2018-05-22 2018-10-16 中国科学技术大学苏州研究院 基于现场可编程门阵列的卷积神经网络加速系统
CN109284817B (zh) * 2018-08-31 2022-07-05 中国科学院上海高等研究院 深度可分离卷积神经网络处理架构/方法/系统及介质
CN109635937B (zh) * 2018-12-30 2023-07-11 南京大学 一种面向低位宽卷积神经网络的低功耗系统

Also Published As

Publication number Publication date
EP4064134A1 (en) 2022-09-28
EP4064134B1 (en) 2024-05-22
EP4064134A4 (en) 2023-01-04
US20220326912A1 (en) 2022-10-13
WO2021142713A1 (zh) 2021-07-22

Similar Documents

Publication Publication Date Title
US10394929B2 (en) Adaptive execution engine for convolution computing systems
CN114846478A (zh) 神经网络处理的方法、装置与系统
CN110073359B (zh) 用于卷积神经网络的有效数据布局
CN112840356B (zh) 运算加速器、处理方法及相关设备
CN111898733B (zh) 一种深度可分离卷积神经网络加速器架构
CN106846235B (zh) 一种利用NVIDIA Kepler GPU汇编指令加速的卷积优化方法及系统
CN110807170B (zh) 多样本多通道卷积神经网络Same卷积向量化实现方法
KR101950786B1 (ko) 분산처리용 인공신경망 연산 가속화 방법
CN110796235B (zh) 卷积神经网络Valid卷积的向量化实现方法
CN110796236B (zh) 多样本多通道卷积神经网络池化的向量化实现方法
TW202123093A (zh) 實行卷積運算的系統及方法
CN112633490B (zh) 执行神经网络模型的数据处理装置、方法及相关产品
US11579921B2 (en) Method and system for performing parallel computations to generate multiple output feature maps
CN109993293B (zh) 一种适用于堆叠式沙漏网络的深度学习加速器
KR102137802B1 (ko) 분산처리용 인공신경망 연산 가속화 장치, 이를 이용한 인공신경망 가속화 시스템, 및 그 인공신경망의 가속화 방법
CN115034402A (zh) 模型推理性能的优化方法、装置及相关产品
CN210924662U (zh) 神经网络处理的装置与系统
CN113261015A (zh) 神经网络系统及数据处理技术
US20230376733A1 (en) Convolutional neural network accelerator hardware
CN112200310A (zh) 智能处理器、数据处理方法及存储介质
US20230025068A1 (en) Hybrid machine learning architecture with neural processing unit and compute-in-memory processing elements
US20230047364A1 (en) Partial sum management and reconfigurable systolic flow architectures for in-memory computation
EP4009240A1 (en) Method and apparatus for performing deep learning operations
TWI798591B (zh) 卷積神經網路運算方法及裝置
CN115470176B (zh) 计算装置、利用计算装置实施卷积运算的方法及相关产品

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