Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A parallel optimization method of diamond block for template calculation

An optimization method and block technology, applied in computing, concurrent instruction execution, machine execution devices, etc., to achieve high concurrency, maintain concurrency, optimize locality and parallelism

Active Publication Date: 2022-07-12
XI AN JIAOTONG UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] With the iterative update of computing devices, the "storage wall" problem caused by the imbalance between the computing power of computing devices and the communication bandwidth of the system is still a bottleneck problem in improving program performance.

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 parallel optimization method of diamond block for template calculation
  • A parallel optimization method of diamond block for template calculation
  • A parallel optimization method of diamond block for template calculation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] A kind of diamond block parallel optimization method for template calculation of the present invention comprises the following steps:

[0044] S1. Diamond block strategy for template calculation

[0045] S101. Define template calculation

[0046] Template computing is actually a method of traversing all spatial grid points under a large number of time step iterations in a fixed pattern on a structured spatial computing grid, and a certain fixed pattern for updating grid points is called a template.

[0047] The template is to define how the value of a point in space is calculated or updated from itself, the values ​​of neighboring points, and the values ​​of neighboring points at different time steps.

[0048] Jacobi is a typical template calculation. The core code of Jacobi-1d is as follows:

[0049]

[0050]

[0051] The fixed template of the data update calculated by the above template is represented by the following formula:

[0052]

[0053] Among them,...

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 discloses a diamond block parallel optimization method for template calculation. A d-dimensional space iterative domain calculation definition template is defined, the shape of the diamond block is selected according to the slope calculated by the template and the width and height of the diamond block, and the template calculation operation is performed. Cache size of the computer system, determine the size of the diamond block, and determine the diamond block strategy for the template calculation; perform a parallel scheduling strategy on the obtained diamond block, and take a dimension of the diamond block without diamond block. The wavefront parallel strategy adopts all the diamond block coarse-grained parallel strategy and the fine-grained wavefront parallel strategy within the diamond block to complete parallel optimization for template calculation. Compared with the original template calculation program, the optimized template calculation program can obtain better data locality and better program parallelism, thereby further shortening the running time.

Description

technical field [0001] The invention belongs to the technical field of locality and parallelism development of computer programs, and in particular relates to a diamond-shaped block parallel optimization method for template calculation. Background technique [0002] Stencil Computations is an iterative process based on a fixed template and new data. It has attracted attention as a computing core in the fields of image and video processing, large-scale scientific and engineering simulation, and computing. Common template calculations include structured mesh calculations in computational fluid dynamics (LBM, etc.), explicit and implicit partial differential equation solvers (PDEsolver), Jacobi and Gauss-Seidel methods And finite difference time domain method (FDTD) and so on. [0003] With the iterative update of computing devices, the "storage wall" problem constituted by the imbalance between the computing capabilities of the computing devices and the system communication b...

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): G06F9/38
CPCG06F9/3836G06F9/3856
Inventor 伍卫国王倩刘松屈彬
Owner XI AN JIAOTONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com