Method and device suitable for CPU floating point operation theoretical value extraction

A floating-point operation, floating-point operation unit technology, applied in the direction of computing, electrical digital data processing, digital data processing components, etc., can solve the problems of complex technology, long calculation time, etc., to achieve strong operability, convenient theoretical value Extract, extract the quick effect

Active Publication Date: 2019-07-05
北京市合芯数字科技有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Therefore, the technical problem to be solved by the present invention is to overcome the disadvantages of complex fixed-floating-point theoretical value extraction technology and long calculation time in the prior art, thereby providing a method and device suitable for CPU floating-point theoretical value extraction

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 suitable for CPU floating point operation theoretical value extraction
  • Method and device suitable for CPU floating point operation theoretical value extraction
  • Method and device suitable for CPU floating point operation theoretical value extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] The floating-point operation unit is a processing unit dedicated to floating-point operations. There are dozens of floating-point instructions in the floating-point operation unit. What the embodiment of the present invention extracts is the theoretical value of the floating-point instructions in the floating-point operation unit.

[0037] An embodiment of the present invention provides a method suitable for extracting theoretical values ​​of CPU floating-point operations, as shown in Figure 1, including the following steps:

[0038] Step S1. Obtain the instructions in the CPU floating-point unit, the instruction codes of all instructions are identified by opcode, and the opcode command line interface is provided.

[0039] Step S2. Extract the instruction code of the instruction, and determine the function for executing the instruction according to the instruction code.

[0040] Step S3. Execute the function according to the source operand file and the instruction code ...

Embodiment 2

[0055] The embodiment of the present invention provides a device suitable for extracting theoretical values ​​of CPU floating-point operations, such as Figure 10 As shown, an instruction acquisition module 10 is included, configured to acquire instructions in the CPU floating-point unit; for details, refer to the relevant description of step S1 in the above method embodiment.

[0056] The function determination module 20 is used to extract the instruction code of the instruction, and determine the function for executing the specific instruction according to the instruction code; for details, please refer to the relevant description of step S2 in the above method embodiment.

[0057] The theoretical value extraction module 30 is used to execute the function according to the source operand file and the instruction code to obtain the theoretical value. For details, refer to the related description of step S3 in the above method embodiment.

[0058] The device suitable for extr...

Embodiment 3

[0063] This embodiment provides a computer device, such as Figure 14 As shown, the computer device mainly includes one or more processors 51 and memory 52, image 3 A processor 51 is taken as an example.

[0064] The computer device may also include: an input device 53 and an output device 54 .

[0065] Processor 51, memory 52, input device 53 and output device 54 can be connected by bus or other ways, Figure 14 Take connection via bus as an example.

[0066] The processor 51 may be a central processing unit (Central Processing Unit, CPU). Processor 51 can also be other general processors, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-Programmable Gate Array, FPGA) or Other chips such as programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations of the above-mentioned types of c...

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 and device suitable for CPU floating point operation theoretical value extraction. The method comprises the steps of obtaining an instruction in a CPU floating point operation unit; extracting an instruction code of the instruction, and determining a function for executing the instruction according to the instruction code; and obtaining a theoretical value accordingto the source operand file and the instruction coding execution function. According to the method suitable for the CPU floating point operation theoretical value extraction provided by the invention,the floating point operation theoretical value extraction is realized by adopting a pure software mode, and the complex problems are simplified by implementing the method provided by the invention.

Description

technical field [0001] The invention relates to the field of CPU floating-point calculations, in particular to a method and device suitable for extracting theoretical values ​​of CPU floating-point calculations. Background technique [0002] The floating-point computing performance of the CPU reflects the processing capability of the CPU, and the key to the success of independent research and development of the CPU depends on whether the independent design of the floating-point computing unit is correct. In order to ensure the correctness of the independent design of the floating-point operation unit, a fixed-floating-point theoretical value extraction technology is proposed. By comparing the execution results of the floating-point operation unit with the extracted theoretical values, the floating-point operation unit is adjusted according to the comparison results. Thereby improving the correctness of the floating-point unit. However, the current fixed-floating-point theor...

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): G06F7/575
CPCG06F7/575Y02D10/00
Inventor 王俊杰冯春阳黄晶刘刚彭琅张兴革张帅
Owner 北京市合芯数字科技有限公司
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