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

A coding method and terminal for hls instruction optimization

A technology of instruction optimization and coding method, applied in the field of programming, can solve the problem of low efficiency of HLS optimization instruction combination, and achieve the effect of improving efficiency

Active Publication Date: 2020-08-14
FUJIAN NORMAL UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Using existing methods to find the optimal combination of HLS optimization instructions is inefficient

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
  • A coding method and terminal for hls instruction optimization
  • A coding method and terminal for hls instruction optimization
  • A coding method and terminal for hls instruction optimization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0072] This embodiment provides a coding method for HLS instruction optimization, including:

[0073] S1. Obtain the statement type and statement label of a statement in the source code; the statement type includes a function, an array, an interface array and a loop statement;

[0074] Among them, the statement type and statement label of each statement in the C / C++ source code are extracted through the data extraction tool; if the statement type is function, array, and interface array, the statement label is the function name, array name, and interface array name;

[0075] S2, preset depth variable; when the type is a function, set the value of the depth variable to the function level corresponding to the statement; when the type is an array, set the value of the depth variable to be the same as the The dimension corresponding to the statement; when the type is a loop statement, the value of the depth variable is set to the loop nesting depth corresponding to the statement; w...

Embodiment 2

[0098] This embodiment provides a coding terminal for HLS instruction optimization, including one or more processors and memory, the memory is stored with a program, and is configured to perform the following steps by the one or more processors 1:

[0099] S1. Obtain the statement type and statement label of a statement in the source code; the statement type includes a function, an array, an interface array and a loop statement;

[0100] S2, preset depth variable; when the type is a function, set the value of the depth variable to the function level corresponding to the statement; when the type is an array, set the value of the depth variable to be the same as the The dimension corresponding to the statement; when the type is a loop statement, the value of the depth variable is set to the loop nesting depth corresponding to the statement; when the type is an interface array, the depth variable is set The value is the dimension corresponding to the statement;

[0101] S3. Rand...

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 relates to the field of programming and especially relates to a coding method and a terminal. The invention provides a data coding format used for searching HLS optimal instruction combination. In order to improve the efficiency of the hardware circuit running program, it is necessary to try various HLS optimization instruction combinations in the process of translating the program written in high-level language into hardware description language; HLS optimization instructions have a large number of combinations. The data coding format provided by the invention is advantageous to searching for the optimal HLS optimal instruction combination by heuristic algorithm, and thus greatly improves the efficiency of searching for the optimal HLS optimal instruction combination.

Description

technical field [0001] The invention relates to the field of programming, in particular to a coding method and a terminal for optimizing HLS instructions. Background technique [0002] In order to meet the requirements of hardware acceleration for existing algorithms, the traditional hardware description languages: Verilog HDL and VHDL are difficult to meet the existing needs due to the difficulty of development and the long development cycle. The emergence of HLS solves this problem. HLS (High Level Synthesis) can convert the C / C++ code written by software developers into programmable logic design. Usually, there are many functions, arrays, and loops in an algorithm program, and the combination of instructions generated by optimizing the functions, loops, and arrays of the program by using more than 20 optimization instructions provided by HLS is explosive. It is inefficient to use existing methods to find the optimal combination of HLS optimization instructions. Content...

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 Patents(China)
IPC IPC(8): G06F8/41
CPCG06F8/443
Inventor 黄晞陈宝林郭升挺吴家飞苏浩明
Owner FUJIAN NORMAL UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More