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

Method of improving WRF parallel computing efficiency

A parallel computing and high-efficiency technology, applied in computing, concurrent instruction execution, program control design, etc., can solve problems such as bug-prone, code-difficult, system instability, etc., and achieve simple usage, low energy consumption, and good application foreground effect

Inactive Publication Date: 2016-09-14
CHONGQING INST OF GREEN & INTELLIGENT TECH CHINESE ACADEMY OF SCI
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method requires a deep understanding of the logical structure and code of the WRF program, and the WRF program is updated quickly, and the code needs to be rewritten every time it is updated; Stable; generally those who use WRF are those who are engaged in meteorological applications, and it is difficult to modify the code of parallel computing; the performance of time-consuming functions in WRF is not consistent on different CPU processor platforms, and the modification method for different processor platforms is also different. Same
This method is currently in the stage of academic research, and there is still a distance from practical use

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 of improving WRF parallel computing efficiency

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0030] In the refined numerical weather forecast system implemented in Chongqing, WRF is used to do the main integration work. On the supercomputing platform, 24 computing nodes are used to execute WRF, and each node uses 12 computing cores, that is, 288 processes are used to Execute the WRF program. By configuring different processes in the x direction, the results of multiple experiments are as follows:

[0031] X*Y

[0032] Among them, 18*16 is the setting of WRF itself. The experiment found that the efficiency of WRF parallel computing is the highest at 9*32, which improves the parallel computing efficiency by 34.5% compared with the setting of WRF itself.

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 present invention relates to a method of improving WRF parallel computing efficiency, and belongs to the technical field of weather forecast and supercomputing application. The method reduces the number of processes in the X direction so as to improve the WRF parallel computing efficiency. The method specifically comprises the following steps of (S1) configuring the number of total processes NP of WRF parallel computing; (S2) setting the number of processes of the WRF in x and y directions nproc_x and nproc_y, wherein nproc_x<nproc_y; (S3) searching the optimal nproc_x through experiments; and (S4) using the optimal nproc_x in business application to improve the WRF parallel computing efficiency. According to the method, the WRF parallel computing efficiency can be effectively improved, supercomputing energy consumption can be reduced, and the method is easy to use and has good application prospect.

Description

technical field [0001] The invention belongs to the technical field of meteorological forecasting and supercomputing applications, and relates to a method for improving WRF parallel computing efficiency, in particular to a method for improving WRF parallel computing efficiency based on reducing the number of X-direction processes. Background technique [0002] At present, in order to improve the execution efficiency of the weather forecast model WRF and shorten the calculation time, the following methods are usually adopted: 1) Improve the parallel process to shorten the calculation time. This method can improve computing efficiency with the increase of parallel processes, but it also increases the overhead of inter-process communication. After the number of parallel processes reaches a certain level, the increased time overhead of inter-process communication will offset the shortened time overhead of parallel processes. Therefore There is a limit to shortening WRF computati...

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): G06F9/38
CPCG06F9/3885
Inventor 孙启龙赵学良陈芋文钟坤华张矩张渝林林小光
Owner CHONGQING INST OF GREEN & INTELLIGENT TECH CHINESE ACADEMY OF SCI