Method and device for inserting conversion operator

An operator and format conversion technology, which is used in computer security devices, neural learning methods, computing, etc.

Pending Publication Date: 2021-09-28
HUAWEI TECH CO LTD
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The high-speed memory directly accessed by the neural network chip is often very small, and the amount of input data used by the neural network is large,...

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
  • Method and device for inserting conversion operator
  • Method and device for inserting conversion operator
  • Method and device for inserting conversion operator

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] figure 1 It is a schematic diagram of the AI ​​system for this application, which is used to develop AI applications (ie, neural networks), including four modules, chips, chips, frames, and applications, the following respectively The module is a brief introduction.

[0068] Chips for providing hardware computing resources for the AI ​​system. You can use a unified architecture chip that can be used in a variety of scenarios in a variety of scenarios, reducing the difficulty of cross-scene development.

[0069] Different chips apply to different data formats. For example, when using a central processor (CPU) to provide hardware computing resources for the AI ​​system, the data format is faster than the data of the Number Heightwidth Channel, NHWC. When using a graphics processor ( GRAPHICS ProcessingUnit, GPU) When providing hardware computing resources for the AI ​​system, the data format is faster than the data of the number channel height width (NCHW).

[0070] In the a...

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

The invention provides a method for inserting a conversion operator. The method comprises the following steps: determining an initial data format of a first operator in a neural network; determining a current data format of the first operator; and when the initial data format of the first operator is different from the current data format, inserting at least one first conversion operator and at least one second conversion operator around the first operator, wherein the first conversion operator is used for converting the input data of the first operator into the current data format from the initial data format, and the second conversion operator is used for converting the output data of the first operator from the current data format to the initial data format. In the method, the initial data format is a data format beneficial to hardware performance, and the current data format is a data format beneficial to improving the processing efficiency of the first operator, therefore, the conversion operator is inserted according to the initial data format and the current data format of the first operator, and the requirements of the operator and the requirements of hardware can be met at the same time.

Description

Technical field [0001] The present application relates to the field of artificial intelligence and in particular to a method and apparatus for inserting conversion operator. Background technique [0002] Neural networks are artificial intelligence tools (artificial intelligence, AI), which has a large computation when processing the input data, large-scale memory access and the frequency characteristics. Neural network chip direct memory access speed tend to be small, and the amount of input data and a neural network using a large, relatively low speed in the cache needs large memory, therefore, the data throughput has become a bottleneck in computing neural network. [0003] A method for improving neural network processing speed is reasonable strategy planning data slice, slice the data copied to the high-speed memory to improve memory access efficiency. Data slice strategy relies on hardware supported data arrangement (layout), different hardware applicable data arrangement may...

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
IPC IPC(8): G06N3/04G06N3/063G06N3/08G06F21/62
CPCG06N3/063G06N3/08G06F21/6245G06N3/045
Inventor 鲍翀
Owner HUAWEI 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