CN108647184B - 一种动态比特位卷积乘法实现方法 - Google Patents
一种动态比特位卷积乘法实现方法 Download PDFInfo
- Publication number
- CN108647184B CN108647184B CN201810443471.8A CN201810443471A CN108647184B CN 108647184 B CN108647184 B CN 108647184B CN 201810443471 A CN201810443471 A CN 201810443471A CN 108647184 B CN108647184 B CN 108647184B
- Authority
- CN
- China
- Prior art keywords
- value
- dynamic
- bit
- dynamic bit
- weight
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000004364 calculation method Methods 0.000 claims abstract description 15
- 238000013135 deep learning Methods 0.000 claims abstract description 12
- 238000012360 testing method Methods 0.000 claims abstract description 7
- 238000013527 convolutional neural network Methods 0.000 claims description 23
- 238000012549 training Methods 0.000 claims description 6
- 230000004807 localization Effects 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 2
- 238000013461 design Methods 0.000 abstract description 8
- 238000013528 artificial neural network Methods 0.000 abstract description 5
- 239000010410 layer Substances 0.000 description 48
- 238000010586 diagram Methods 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 2
- 101100370202 Arabidopsis thaliana PTPMT1 gene Proteins 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000002356 single layer Substances 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Images
Classifications
-
- 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
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- 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
- 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
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Image Analysis (AREA)
- Complex Calculations (AREA)
Abstract
Description
Claims (4)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810443471.8A CN108647184B (zh) | 2018-05-10 | 2018-05-10 | 一种动态比特位卷积乘法实现方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810443471.8A CN108647184B (zh) | 2018-05-10 | 2018-05-10 | 一种动态比特位卷积乘法实现方法 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108647184A CN108647184A (zh) | 2018-10-12 |
CN108647184B true CN108647184B (zh) | 2022-04-12 |
Family
ID=63754382
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810443471.8A Active CN108647184B (zh) | 2018-05-10 | 2018-05-10 | 一种动态比特位卷积乘法实现方法 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108647184B (zh) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110458277B (zh) * | 2019-04-17 | 2021-11-16 | 上海酷芯微电子有限公司 | 适用于深度学习硬件加速器的可配置精度的卷积硬件结构 |
CN110852434B (zh) * | 2019-09-30 | 2022-09-23 | 梁磊 | 基于低精度浮点数的cnn量化方法、前向计算方法及硬件装置 |
CN110852416B (zh) * | 2019-09-30 | 2022-10-04 | 梁磊 | 基于低精度浮点数数据表现形式的cnn硬件加速计算方法及系统 |
CN111178513B (zh) * | 2019-12-31 | 2022-04-15 | 深圳云天励飞技术股份有限公司 | 神经网络的卷积实现方法、卷积实现装置及终端设备 |
CN114580628A (zh) * | 2022-03-14 | 2022-06-03 | 北京宏景智驾科技有限公司 | 一种神经网络卷积层的高效量化加速方法及硬件电路 |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105760933A (zh) * | 2016-02-18 | 2016-07-13 | 清华大学 | 卷积神经网络的逐层变精度定点化方法及装置 |
CN106127302A (zh) * | 2016-06-23 | 2016-11-16 | 杭州华为数字技术有限公司 | 处理数据的电路、图像处理系统、处理数据的方法和装置 |
CN107239829A (zh) * | 2016-08-12 | 2017-10-10 | 北京深鉴科技有限公司 | 一种优化人工神经网络的方法 |
CN107480770A (zh) * | 2017-07-27 | 2017-12-15 | 中国科学院自动化研究所 | 可调节量化位宽的神经网络量化与压缩的方法及装置 |
CN107688849A (zh) * | 2017-07-28 | 2018-02-13 | 北京深鉴科技有限公司 | 一种动态策略定点化训练方法及装置 |
CN107832082A (zh) * | 2017-07-20 | 2018-03-23 | 上海寒武纪信息科技有限公司 | 一种用于执行人工神经网络正向运算的装置和方法 |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180046903A1 (en) * | 2016-08-12 | 2018-02-15 | DeePhi Technology Co., Ltd. | Deep processing unit (dpu) for implementing an artificial neural network (ann) |
-
2018
- 2018-05-10 CN CN201810443471.8A patent/CN108647184B/zh active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105760933A (zh) * | 2016-02-18 | 2016-07-13 | 清华大学 | 卷积神经网络的逐层变精度定点化方法及装置 |
CN106127302A (zh) * | 2016-06-23 | 2016-11-16 | 杭州华为数字技术有限公司 | 处理数据的电路、图像处理系统、处理数据的方法和装置 |
CN107239829A (zh) * | 2016-08-12 | 2017-10-10 | 北京深鉴科技有限公司 | 一种优化人工神经网络的方法 |
CN107832082A (zh) * | 2017-07-20 | 2018-03-23 | 上海寒武纪信息科技有限公司 | 一种用于执行人工神经网络正向运算的装置和方法 |
CN107480770A (zh) * | 2017-07-27 | 2017-12-15 | 中国科学院自动化研究所 | 可调节量化位宽的神经网络量化与压缩的方法及装置 |
CN107688849A (zh) * | 2017-07-28 | 2018-02-13 | 北京深鉴科技有限公司 | 一种动态策略定点化训练方法及装置 |
Non-Patent Citations (5)
Title |
---|
A Dynamic Multi-precision Fixed-Point Data Quantization Strategy for Convolutional Neural Network;Lei Shan等;《NCCET 2016: Computer Engineering and Technology》;20161231;第102-111页 * |
Speeding up Convolutional Neural Network Training with Dynamic Precision Scaling and Flexible Multiplier-Accumulator;Taesik Na等;《ISLPED16: Proceedings of the 2016 International Symposium on Low Power Electronics and Design》;20160831;全文 * |
基于FPGA的人工神经网络的研究与实现;杨程;《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》;20170315;全文 * |
基于FPGA的卷积神经网络并行结构研究;陆志坚;《中国优秀博硕士学位论文全文数据库(博士)信息科技辑》;20140415;全文 * |
深度卷积神经网络的数据表示方法分析与实践;王佩琪等;《计算机研究与发展》;20170630;第54卷(第6期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN108647184A (zh) | 2018-10-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108647184B (zh) | 一种动态比特位卷积乘法实现方法 | |
CN109325591B (zh) | 面向Winograd卷积的神经网络处理器 | |
CN106250939B (zh) | 基于fpga+arm多层卷积神经网络的手写体字符识别方法 | |
CN108108809B (zh) | 一种针对卷积神经元网络进行推理加速的硬件架构及其工作方法 | |
WO2019127363A1 (zh) | 神经网络权重编码方法、计算装置及硬件系统 | |
Wang et al. | Low power convolutional neural networks on a chip | |
CN111459877A (zh) | 基于FPGA加速的Winograd YOLOv2目标检测模型方法 | |
CN107256424B (zh) | 三值权重卷积网络处理系统及方法 | |
US20180018555A1 (en) | System and method for building artificial neural network architectures | |
CN108090565A (zh) | 一种卷积神经网络并行化训练加速方法 | |
CN108665063B (zh) | 用于bnn硬件加速器的双向并行处理卷积加速系统 | |
CN108108811A (zh) | 神经网络中的卷积计算方法和电子设备 | |
CN113344179B (zh) | 基于fpga的二值化卷积神经网络算法的ip核 | |
CN110163355A (zh) | 一种计算装置及方法 | |
CN110991631A (zh) | 一种基于fpga的神经网络加速系统 | |
CN110543939A (zh) | 一种基于fpga的卷积神经网络后向训练的硬件加速实现架构 | |
JP6999885B2 (ja) | 二値化ニューラルネットワーク用プロセッサ、データ処理方法、および、プログラム | |
CN110543936A (zh) | 一种cnn全连接层运算的多并行加速方法 | |
CN113283587A (zh) | 一种Winograd卷积运算加速方法及加速模块 | |
CN113792621A (zh) | 一种基于fpga的目标检测加速器设计方法 | |
CN112734020A (zh) | 卷积神经网络的卷积乘累加硬件加速装置、系统以及方法 | |
Xiao et al. | FPGA-based scalable and highly concurrent convolutional neural network acceleration | |
Qi et al. | Learning low resource consumption cnn through pruning and quantization | |
CN110135561B (zh) | 一种实时在线飞行器ai神经网络系统 | |
CN114897159B (zh) | 一种基于神经网络的快速推断电磁信号入射角的方法 |
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 | ||
CB02 | Change of applicant information |
Address after: Room 1210, 12 / F, building 9, Yinhu innovation center, 9 Fuxian Road, Yinhu street, Fuyang District, Hangzhou City, Zhejiang Province Applicant after: Hangzhou xiongmai integrated circuit technology Co.,Ltd. Address before: Room 1210, 12 / F, building 9, Yinhu innovation center, 9 Fuxian Road, Yinhu street, Fuyang District, Hangzhou City, Zhejiang Province Applicant before: HANGZHOU XIONGMAI INTEGRATED CIRCUIT TECHNOLOGY CO.,LTD. |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A dynamic bit convolution multiplication method Effective date of registration: 20230308 Granted publication date: 20220412 Pledgee: Fuyang sub branch of Bank of Hangzhou Co.,Ltd. Pledgor: Hangzhou xiongmai integrated circuit technology Co.,Ltd. Registration number: Y2023330000470 |
|
PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
CP01 | Change in the name or title of a patent holder |
Address after: Room 1210, 12 / F, building 9, Yinhu innovation center, 9 Fuxian Road, Yinhu street, Fuyang District, Hangzhou City, Zhejiang Province Patentee after: Zhejiang Xinmai Microelectronics Co.,Ltd. Address before: Room 1210, 12 / F, building 9, Yinhu innovation center, 9 Fuxian Road, Yinhu street, Fuyang District, Hangzhou City, Zhejiang Province Patentee before: Hangzhou xiongmai integrated circuit technology Co.,Ltd. |
|
CP01 | Change in the name or title of a patent holder |