Floating point data processing method and device, and storage medium

A floating-point data and processing method technology, applied in electrical components, code conversion, etc., can solve problems such as low floating-point data processing efficiency, and achieve the effects of reducing the scale of operations, improving processing efficiency, and reducing data volume

Pending Publication Date: 2020-03-24
SHENZHEN IPANEL TECH LTD
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In view of this, the purpose of this application is to provide a floating-point data processing method, device and storage medium to solve the technical problem of low floating-point data processing efficiency in the prior art

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
  • Floating point data processing method and device, and storage medium
  • Floating point data processing method and device, and storage medium
  • Floating point data processing method and device, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] For artificial intelligence (AI) and other application fields, it often contains a large amount of data whose value is fixed or approximate to a fixed value, such as data that is 0 or approximately 0. For such a large number of data whose values ​​are 0 or approximately 0, if the compressed representation can be simplified, the data volume of the floating-point data can be greatly compressed.

[0054] In order to solve the above problems, in this application, for floating-point data that is 0 or approximately 0, it is proposed to use fewer bits to represent the fixed value for floating-point data that is fixed or approximately fixed, which greatly compresses the data. However, the bit-bit floating-point data of other values ​​can still be represented by the original bit, without compression or increase, but one or several bits of precision can be sacrificed to indicate that it is not compressed. Other bits of data still represent the bits of the original floating-point ...

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 discloses a floating point data processing method and a device, and a storage medium. The method comprises the steps of obtaining to-be-compressed first floating point data; sequentiallyreading first target data in the first floating point data according to the number of bits occupied by bytes in the floating point data, and executing the following operations on the first target data; obtaining a data value of a preset system corresponding to the first target data; based on judgment that the data value meets a preset compression condition, compressing the first target data intofirst data, setting a first identifier for the first data, the first data and the first identifier occupying a first number of bits, and the first identifier representing that the data where the firstidentifier is located are compressed data; based on the judgment that the data value does not meet the compression condition, setting a second identifier for the first target data, the second identifier representing that the data where the second identifier is located are uncompressed data, and the first target data and the second identifier occupying a second number of bits; wherein the first quantity is smaller than the bit quantity occupied by the first target data.

Description

technical field [0001] The present application relates to the technical field of data compression, in particular to a floating-point data processing method, device and storage medium. Background technique [0002] With the development of artificial intelligence technology in recent years, the scale of access and communication of floating-point data has become larger and larger, so the processing efficiency of floating-point data will also decrease accordingly. Contents of the invention [0003] In view of this, the purpose of the present application is to provide a floating-point data processing method, device and storage medium to solve the technical problem of low floating-point data processing efficiency in the prior art. [0004] The application provides a floating-point data processing method, including: [0005] Obtain the first floating-point data to be compressed; [0006] According to the number of bits occupied by bytes in the floating-point data, sequentially ...

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 Applications(China)
IPC IPC(8): H03M7/30
CPCH03M7/30H03M7/70
Inventor 徐佳宏成学文
Owner SHENZHEN IPANEL TECH 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