CN112789627A - 一种神经网络处理器、数据处理方法及相关设备 - Google Patents
一种神经网络处理器、数据处理方法及相关设备 Download PDFInfo
- Publication number
- CN112789627A CN112789627A CN201880098253.3A CN201880098253A CN112789627A CN 112789627 A CN112789627 A CN 112789627A CN 201880098253 A CN201880098253 A CN 201880098253A CN 112789627 A CN112789627 A CN 112789627A
- Authority
- CN
- China
- Prior art keywords
- cores
- input
- matrix
- core
- global
- 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
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 47
- 238000003672 processing method Methods 0.000 title claims description 16
- 239000011159 matrix material Substances 0.000 claims abstract description 148
- 238000012549 training Methods 0.000 claims abstract description 106
- 238000009825 accumulation Methods 0.000 claims abstract description 57
- 238000000034 method Methods 0.000 claims abstract description 53
- 238000010606 normalization Methods 0.000 claims description 85
- 238000004364 calculation method Methods 0.000 claims description 50
- 238000012545 processing Methods 0.000 claims description 47
- 238000010586 diagram Methods 0.000 claims description 16
- 238000013519 translation Methods 0.000 claims description 14
- 239000000126 substance Substances 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 239000010410 layer Substances 0.000 description 124
- 238000013527 convolutional neural network Methods 0.000 description 52
- 230000015654 memory Effects 0.000 description 37
- 238000011176 pooling Methods 0.000 description 31
- 230000008569 process Effects 0.000 description 28
- 239000013598 vector Substances 0.000 description 26
- 238000009826 distribution Methods 0.000 description 12
- 239000000872 buffer Substances 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 238000013473 artificial intelligence Methods 0.000 description 6
- 230000001360 synchronised effect Effects 0.000 description 6
- 230000004913 activation Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 238000012546 transfer Methods 0.000 description 4
- 238000012935 Averaging Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000002346 layers by function Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000002441 reversible effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- -1 i.e. Substances 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
本发明实施例公开了一种神经网络处理器、方法及相关设备,其中的神经网络处理器,包括:n个计算核Core、原子操作累加单元和片上共享缓存;每一个Core用于根据输入矩阵计算输入矩阵的核内均值μ,并将u写入到原子操作累加单元;根据输入矩阵计算m个x2的均值v,并将v写入到原子操作累加单元;原子操作累加单元,用于对n个Core写入的n个μ进行累加得到S1,并将S1写入片上共享缓存;对n个Core写入的n个v的进行累加得到S2,并将S2写入片上共享缓存;每一个Core还用于:从片上共享缓存获取S1和S2,并根据S1和S2计算n个Core的n个输入矩阵的全局方差。采用本申请,可以提升神经网络的训练速度。
Description
PCT国内申请,说明书已公开。
Claims (13)
- PCT国内申请,权利要求书已公开。
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2018/109208 WO2020062299A1 (zh) | 2018-09-30 | 2018-09-30 | 一种神经网络处理器、数据处理方法及相关设备 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112789627A true CN112789627A (zh) | 2021-05-11 |
CN112789627B CN112789627B (zh) | 2023-08-22 |
Family
ID=69949555
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201880098253.3A Active CN112789627B (zh) | 2018-09-30 | 2018-09-30 | 一种神经网络处理器、数据处理方法及相关设备 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN112789627B (zh) |
WO (1) | WO2020062299A1 (zh) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115278360A (zh) * | 2022-07-18 | 2022-11-01 | 天翼云科技有限公司 | 一种视频数据处理方法及电子设备 |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111881880A (zh) * | 2020-08-10 | 2020-11-03 | 晶璞(上海)人工智能科技有限公司 | 一种基于新型网络的票据文本识别方法 |
CN112308762A (zh) * | 2020-10-23 | 2021-02-02 | 北京三快在线科技有限公司 | 一种数据处理方法及装置 |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106529668A (zh) * | 2015-11-17 | 2017-03-22 | 中国科学院计算技术研究所 | 加速深度神经网络算法的加速芯片的运算装置及方法 |
US20170140268A1 (en) * | 2015-11-12 | 2017-05-18 | Google Inc. | Training neural networks using normalized target outputs |
US20170286830A1 (en) * | 2016-04-04 | 2017-10-05 | Technion Research & Development Foundation Limited | Quantized neural network training and inference |
WO2017185335A1 (zh) * | 2016-04-29 | 2017-11-02 | 北京中科寒武纪科技有限公司 | 一种用于执行batch normalization运算的装置和方法 |
CN107454965A (zh) * | 2015-05-21 | 2017-12-08 | 谷歌公司 | 神经网络处理器中的批处理 |
CN108090565A (zh) * | 2018-01-16 | 2018-05-29 | 电子科技大学 | 一种卷积神经网络并行化训练加速方法 |
US20180197084A1 (en) * | 2017-01-11 | 2018-07-12 | Electronics And Telecommunications Research Institute | Convolutional neural network system having binary parameter and operation method thereof |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106022468B (zh) * | 2016-05-17 | 2018-06-01 | 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 |
CN106056211B (zh) * | 2016-05-25 | 2018-11-23 | 清华大学 | 神经元计算单元、神经元计算模块及人工神经网络计算核 |
CN106844294B (zh) * | 2016-12-29 | 2019-05-03 | 华为机器有限公司 | 卷积运算芯片和通信设备 |
CN108256638B (zh) * | 2018-01-05 | 2021-06-22 | 上海兆芯集成电路有限公司 | 微处理器电路以及执行神经网络运算的方法 |
-
2018
- 2018-09-30 WO PCT/CN2018/109208 patent/WO2020062299A1/zh active Application Filing
- 2018-09-30 CN CN201880098253.3A patent/CN112789627B/zh active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107454965A (zh) * | 2015-05-21 | 2017-12-08 | 谷歌公司 | 神经网络处理器中的批处理 |
US20170140268A1 (en) * | 2015-11-12 | 2017-05-18 | Google Inc. | Training neural networks using normalized target outputs |
CN106529668A (zh) * | 2015-11-17 | 2017-03-22 | 中国科学院计算技术研究所 | 加速深度神经网络算法的加速芯片的运算装置及方法 |
US20170286830A1 (en) * | 2016-04-04 | 2017-10-05 | Technion Research & Development Foundation Limited | Quantized neural network training and inference |
WO2017185335A1 (zh) * | 2016-04-29 | 2017-11-02 | 北京中科寒武纪科技有限公司 | 一种用于执行batch normalization运算的装置和方法 |
US20180197084A1 (en) * | 2017-01-11 | 2018-07-12 | Electronics And Telecommunications Research Institute | Convolutional neural network system having binary parameter and operation method thereof |
CN108090565A (zh) * | 2018-01-16 | 2018-05-29 | 电子科技大学 | 一种卷积神经网络并行化训练加速方法 |
Non-Patent Citations (2)
Title |
---|
M. KIMURA等: "Facial point detection based on a convolutional neural network with optimal mini-batch procedure", 《2015 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)》, pages 2860 - 2864 * |
Y. WU等: "Group normalization", 《THE EUROPEAN CONF. ON COMPUTER VISION (ECCV)》, pages 3 - 19 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115278360A (zh) * | 2022-07-18 | 2022-11-01 | 天翼云科技有限公司 | 一种视频数据处理方法及电子设备 |
CN115278360B (zh) * | 2022-07-18 | 2023-11-07 | 天翼云科技有限公司 | 一种视频数据处理方法及电子设备 |
Also Published As
Publication number | Publication date |
---|---|
WO2020062299A1 (zh) | 2020-04-02 |
CN112789627B (zh) | 2023-08-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6946572B2 (ja) | 加速された量子化積和演算 | |
US20230014783A1 (en) | Processing for multiple input data sets | |
CN110188795B (zh) | 图像分类方法、数据处理方法和装置 | |
WO2020177651A1 (zh) | 图像分割方法和图像处理装置 | |
US20210224125A1 (en) | Operation Accelerator, Processing Method, and Related Device | |
US20180260709A1 (en) | Calculating device and method for a sparsely connected artificial neural network | |
US11775430B1 (en) | Memory access for multiple circuit components | |
WO2022001805A1 (zh) | 一种神经网络蒸馏方法及装置 | |
CN111402130B (zh) | 数据处理方法和数据处理装置 | |
WO2023010244A1 (zh) | 神经网络加速器及神经网络加速器的数据处理方法 | |
CN112789627B (zh) | 一种神经网络处理器、数据处理方法及相关设备 | |
KR20200049366A (ko) | 뉴럴 네트워크 프로세서 및 그것의 컨볼루션 연산 방법 | |
EP4235506A1 (en) | Neural network model training method, image processing method, and apparatus | |
WO2022267036A1 (zh) | 神经网络模型训练方法和装置、数据处理方法和装置 | |
CN114078195A (zh) | 分类模型的训练方法、超参数的搜索方法以及装置 | |
WO2019128248A1 (zh) | 一种信号处理方法及装置 | |
WO2022156475A1 (zh) | 神经网络模型的训练方法、数据处理方法及装置 | |
US20210312278A1 (en) | Method and apparatus with incremental learning moddel | |
CN114298289A (zh) | 一种数据处理的方法、数据处理设备及存储介质 | |
CN110083842B (zh) | 译文质量检测方法、装置、机器翻译系统和存储介质 | |
US10990525B2 (en) | Caching data in artificial neural network computations | |
CN113313133A (zh) | 一种生成对抗网络的训练方法、动画图像生成方法 | |
JP2021517310A (ja) | 複数の入力データセットのための処理 | |
WO2023122896A1 (zh) | 一种数据处理方法和装置 | |
WO2022227024A1 (zh) | 神经网络模型的运算方法、训练方法及装置 |
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 |