Normalization calculation method, device and equipment based on FPGA (Field Programmable Gate Array)

By shifting and splitting the input vector into integer and fractional parts on the FPGA through subtraction, and then using lookup tables and Taylor expansion to perform exponent calculation, the problem of high-precision normalized exponent functions on FPGA is solved, and efficient normalization calculation is achieved.

CN122087256APending Publication Date: 2026-05-26JIANGSU HIRAIN AUTOMOTIVE ELECTRONICS CO LTD
0 Cites 0 Cited by

Patent Information

Application Number
CN202610155305.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-02-03
Publication Date
2026-05-26

AI Technical Summary

Technical Problem

In the existing technology, it is difficult to perform normalized exponential function (softmax function) calculation with high accuracy on FPGA, especially due to the large resource consumption and long calculation cycle caused by complex exponent and division operations.

Method used

The input vector is shifted into the negative domain by subtraction, compressing the exponent domain. The complex exponent calculation is split into integer and fractional parts, which are calculated separately. The exponent is calculated using lookup tables and Taylor expansion. Finally, the normalized result is obtained through the normalized reference value.

Benefits of technology

It simplifies the computational logic, reduces resource consumption, achieves high-precision normalized exponential function operations, and improves the computational efficiency of FPGA.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a normalization calculation method, device and equipment based on an FPGA (Field Programmable Gate Array). The method comprises the following steps: searching a maximum value from a plurality of elements of an input vector, and subtracting the maximum value from each element in the input vector to obtain a translation value corresponding to each element; extracting an integer part and a decimal part corresponding to each translation value, and respectively determining a first result corresponding to each integer part and a second result corresponding to each decimal part; obtaining an index result corresponding to the translation value according to the first result and the second result corresponding to each translation value; determining a normalized reference value based on an exponential result of all the translation values; and obtaining a normalization result corresponding to each element in the input vector based on the index result of each translation value and the normalization reference value. Therefore, computational logic is simplified, resource consumption is reduced, and normalized exponential function operation is performed with high precision on the basis.
Need to check novelty before this filing date? Find Prior Art