Unlock instant, AI-driven research and patent intelligence for your innovation.

Bidirectional conversion circuit of floating point data format based on IEEE 754 and POSIT

A floating-point data, two-way conversion technology, applied in code conversion, electrical components, etc., can solve the problem that floating-point conversion circuits cannot achieve mutual conversion, etc.

Active Publication Date: 2021-04-16
SUN YAT SEN UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention provides a kind of bidirectional conversion circuit based on the floating point data format of IEEE 754 and POSIT in order to overcome the technical defect that the existing floating point number conversion circuit cannot realize the mutual conversion of two different standard data formats of IEEE 754 and Posit. It can meet the conversion from IEEE 754 data format to Posit data format, and can also meet the conversion from Posit data format to IEEE 754 data format

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
  • Bidirectional conversion circuit of floating point data format based on IEEE 754 and POSIT
  • Bidirectional conversion circuit of floating point data format based on IEEE 754 and POSIT
  • Bidirectional conversion circuit of floating point data format based on IEEE 754 and POSIT

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] Such as image 3 As shown, the present invention provides a kind of bidirectional conversion circuit based on the floating-point data format of IEEE 754 and POSIT, including data input unit 101, IEEE 754 format field extraction unit 102, Posit format field extraction unit 103, special field detection unit 104, Mantissa reprocessing unit 105, exponent calculation unit 106, IEEE 754 order code reconstruction unit 107, Posit exponent reconstruction unit 108, regime value calculation unit 109, Posit format encoding unit 110, IEEE 754 format encoding unit 111, result encoding output unit 112; of which:

[0051] Described data input unit 101 is used for inputting the first floating-point number, and described first floating-point number is Posit data format or IEEE754 data format;

[0052] The IEEE 754 format field extracting unit 102 is used to extract the different fields of the first floating-point number in the IEEE 754 format of the input, so as to be used in the subseq...

Embodiment 2

[0103] More specifically, such as Figure 6 As shown, a schematic diagram of the circuit structure for converting from the IEEE 754 data format to the Posit data format in this embodiment is given. The circuit structure includes a data input unit 101, an IEEE754 format field extraction unit 102, a special field detection unit 104, a mantissa reprocessing unit 105, an index calculation unit 106, a Posit index reconstruction unit 108, a regime value calculation unit 109, and a Posit format An encoding unit 110 and a result encoding output unit 112 .

[0104] The first floating-point number of the IEEE 754 format to be format converted is input by the data input unit 101, and the first floating-point number of the input is sent to the IEEE 754 format field extraction unit 102, assuming that the bit width of the first floating-point number is N here , the width of the exponent field to which it corresponds is ew, the width of the mantissa field is fw, and the first floating-point...

Embodiment 3

[0121] On the basis of the above examples, if Figure 4 As shown, a schematic diagram of the circuit structure for converting from the Posit data format to the IEEE754 data format in this embodiment is given. In addition to the data input unit 101, special field detection unit 104, and result encoding output unit 112 of the above-mentioned embodiment, this embodiment also includes a Posit format field extraction unit 103, an IEEE754 order code reconstruction unit 107, and an IEEE 754 format encoding unit 111.

[0122] The input of data input unit 101 becomes that the bit width to be converted is N, and the exponent width is the first floating-point number IN of the Posit data format of ES, and the purpose floating-point number format is IEEE 754, and the exponent field (order code) width is ew, mantissa The field width is fw.

[0123]The Posit format field extraction unit 103 includes a splicing device, an XOR circuit, an LOD circuit, a shift device, an adder, and the like. ...

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 bidirectional conversion circuit of a floating point data format based on IEEE 754 and POSIT. The system is composed of a data input unit, an IEEE 754 format field extraction unit, a Poit format field extraction unit, a special field detection unit, a mantissa reprocessing unit, an index calculation unit, an IEEE 754 order code reconstruction unit, a Poit index reconstruction unit, a real time value calculation unit, a Poit format coding unit, an IEEE 754 format coding unit and a result coding output unit. The conversion circuit for converting the IEEE 754 floating point data format into the Poit data format is realized, the conversion circuit for converting the Poit data format into the IEEE 754 format is also realized, and the bidirectional conversion circuit for the IEEE 754 floating point data format and the Poit data format is beneficial to better utilization of advantages and disadvantages of different floating point number data formats. And a proper floating point data format for operation and storage is selected according to different application scene requirements.

Description

technical field [0001] The invention relates to the technical field of computer data processing, and more specifically, to a bidirectional conversion circuit based on IEEE 754 and POSIT floating-point data format. Background technique [0002] Floating-point numbers are a data representation method that must be used in application scenarios that require high-precision data. For example, in aerospace, medicine, chemistry, military and other fields, floating-point numbers are widely used for data processing. [0003] IEEE 754 and Posit are two different standard floating-point data formats. The Posit data format representation method is more flexible. According to the requirements of the application scenario, the allocation of the bit width of different fields of the Posit number of a specific bit width can be adjusted to obtain the desired precision and avoid wasting hardware resources. In the case of the same bit width, Posit can even achieve higher precision than IEEE 754,...

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): H03M7/24
CPCY02D10/00
Inventor 廖琳谭洪舟
Owner SUN YAT SEN UNIV