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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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 ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com