Processing

Please wait...

Settings

Settings

Goto Application

1. CN111831354 - Data precision configuration method and device, chip, chip array, equipment and medium

Office
China
Application Number 202010656745.9
Application Date 09.07.2020
Publication Number 111831354
Publication Date 27.10.2020
Publication Kind A
IPC
G06F 9/445
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
9Arrangements for program control, e.g. control units
06using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
44Arrangements for executing specific programs
445Program loading or initiating
G06N 3/063
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
06Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
063using electronic means
G06N 3/04
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architecture, e.g. interconnection topology
G06N 3/08
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
CPC
G06F 9/4451
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
9Arrangements for program control, e.g. control units
06using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
44Arrangements for executing specific programs
445Program loading or initiating
44505Configuring for program initiating, e.g. using registry, configuration files
4451User profiles; Roaming
G06N 3/063
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
06Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
063using electronic means
G06N 3/0454
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0454using a combination of multiple neural nets
G06N 3/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
Applicants BEIJING LYNXI TECHNOLOGY CO., LTD.
北京灵汐科技有限公司
Inventors HE WEI
何伟
ZHU YAOLONG
祝夭龙
Agents 北京品源专利代理有限公司 11332
Title
(EN) Data precision configuration method and device, chip, chip array, equipment and medium
(ZH) 数据精度配置方法、装置、芯片、芯片阵列、设备及介质
Abstract
(EN) The embodiment of the invention discloses a data precision configuration method and device, a chip, a chip array, equipment and a medium. The method comprises the steps that to-be-output data of a first layer in a neural network is acquired, the first layer comprises any one or more layers except the last layer in the neural network, the weight precision of a second layer is acquired, the second layer is the next layer of the first layer, and the precision of the to-be-output data of the first layer is configured according to the weight precision of the second layer. By adopting the technicalscheme, the precision of one or more layers of output data in the neural network deployed in the artificial intelligence chip can be flexibly configured, so that the performance of the artificial intelligence chip is optimized.
(ZH) 本发明实施例公开了数据精度配置方法、装置、芯片、芯片阵列、设备及介质。该方法包括:获取神经网络中的第一层的待输出数据,其中,第一层包括神经网络中的最后一层之外的任意一层或多层,获取第二层的权重精度,其中,第二层为第一层的下一层,根据第二层的权重精度对第一层的待输出数据的精度进行配置。本发明实施例通过采用上述技术方案,可以灵活配置部署在人工智能芯片中的神经网络中的一层或多层的输出数据的精度,进而优化人工智能芯片的性能。
Related patent documents