A computing method and device

A computing method and computing device technology, applied in neural learning methods, physical implementation, creation/generation of source code, etc., can solve problems such as consuming too many computing resources, achieve strong real-time performance, simple and fast computing process, and avoid additional overhead Effect

Active Publication Date: 2021-01-29
SHANGHAI CAMBRICON INFORMATION TECH CO LTD
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in some low-memory, real-time application scenarios, running the entire software architecture will consume too many computing resources

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A computing method and device
  • A computing method and device
  • A computing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0087] Such as figure 2 As shown, this embodiment proposes a computing method, including the following steps:

[0088] When the input data includes data to be processed, network structure and weight data, perform the following steps:

[0089] Step 11, input and read input data;

[0090] Step 12, constructing an offline model according to the network structure and weight data;

[0091] Step 13, analyze the offline model, obtain and cache operation instructions for subsequent calculation calls;

[0092] Step 14, according to the calculation instruction, perform calculation on the data to be processed to obtain the neural network calculation result for output;

[0093] When the input data includes data to be processed and offline models, perform the following steps:

[0094] Step 21, input and read input data;

[0095] Step 22, analyze the offline model, obtain and cache the operation instructions for subsequent calculation calls;

[0096] Step 23, according to the calcula...

Embodiment 2

[0104] Such as image 3 As shown, this embodiment proposes a computing device, including: an input module 101, a model generation module 102, a neural network computing module 103, an output module 104, and a control module 105, wherein the neural network computing module 103 includes a model analysis unit 106 and Neural Network Processor 107

[0105] The key word of this device is offline execution, which means that after the offline model is generated, the offline model is directly used to generate relevant operation instructions and input the weight data to perform processing operations on the data to be processed. more specific:

[0106] The above-mentioned input module 101 is used for inputting a network structure, a combination of weight data and data to be processed, or a combination of an offline model and data to be processed. When the input is the network structure, weight data and data to be processed, the network structure and weight data are passed into the mode...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

An operation method and device, the operation device includes an input module for inputting data; a model generation module for constructing a model according to the input data; a neural network operation module for generating and caching operation instructions based on the model, and Perform operations on the data to be processed to obtain operation results; the output module is used to output operation results. The device and method disclosed in the present disclosure can avoid the extra overhead caused by running the entire software architecture in the traditional method.

Description

technical field [0001] The disclosure belongs to the fields of computer architecture, deep learning and neural network, and more specifically relates to a computing method and device. Background technique [0002] Deep learning is a branch of machine learning that attempts to perform high-level abstractions on data using algorithms that contain complex structures or multiple processing layers consisting of multiple nonlinear transformations. [0003] Deep learning is a method based on representation learning of data in machine learning. Observations (such as an image) can be represented in a variety of ways, such as a vector of intensity values ​​for each pixel, or more abstractly as a series of edges, regions of a specific shape, etc. Whereas it is easier to learn tasks from examples (e.g., face recognition or facial expression recognition) using some specific representations. [0004] So far, several deep learning architectures, such as deep neural network, convolutional...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06N3/08G06N3/04
CPCG06F8/35G06N3/04G06N3/063G06N3/08G06N3/044
Inventor 不公告发明人
Owner SHANGHAI CAMBRICON INFORMATION TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap