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

Reinforcement method of parallel matrix multiplication algorithm

A matrix multiplication and matrix multiplication technology, which is applied in the reinforcement field of parallel matrix multiplication algorithms, can solve problems such as limited resources

Active Publication Date: 2018-11-02
HOHAI UNIV CHANGZHOU
View PDF2 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But although TMR can effectively solve the problem of soft errors, it can cause three times resource consumption, and in some applications, resources are limited

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
  • Reinforcement method of parallel matrix multiplication algorithm
  • Reinforcement method of parallel matrix multiplication algorithm
  • Reinforcement method of parallel matrix multiplication algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] Such as image 3 As shown, the errors are randomly distributed. The code verification process will detect deviations between the 3-row and 4-column codes, that is, there are 12 possible error points, but in fact there are only 4 errors. Using formula (1) will identify positions ③ and ④ detected as a single error, which will be corrected preferentially. Once successfully corrected using Equation (2) or Equation (3), Faulty_rows and Faulty_cols will be updated, leaving 2 errors in the same row, so can be corrected with very few operations. The correction procedure for this example is in the following Figure 4 shown in . In this example, the proposed scheme avoids unnecessary correction of "false" errors and reduces the total potential error in very few iterations.

[0030] In error injection simulation, the efficiency of this method is better than that of existing methods. We performed error injection simulation tests on matrix multiplications of different sizes. ...

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 reinforcement method of a parallel matrix multiplication algorithm. The method is used for lowering ABFT reinforcement overhead of the matrix algorithm. The method comprisesthe following steps of (1) encoding input and output of matrix multiplication, checking a calculation result according to an encoding value and storing all possible error lists; (2) preprocessing theerror lists, and eliminating some misjudgment errors and avoiding unnecessary correction, wherein the method of eliminating errors is a relative error law, error detection is performed before error correction, then left errors are corrected; if one or more errors are corrected, the error list is updated, and most errors are corrected after iteration for many times; and (3) adopting a re-calculation policy for left errors that cannot be corrected by the algorithm. The reinforcement method improves both system reliability and execution efficiency.

Description

technical field [0001] The invention relates to a reinforcement technology of a parallel matrix multiplication algorithm, which can be applied to various technical fields applied to the matrix multiplication algorithm, such as image processing, data statistics and the like. Background technique [0002] At present, the parallel computing architecture of the graphics processing unit (GPU) has greatly improved the speed of large-scale computer operations, and has shown great potential in high-performance computing applications. GPU is used in various fields, such as image processing, data statistics and other high-performance computing applications, etc., and it is also becoming more and more popular in modern industry. In recent years, GPU makers such as NVIDIA have been developing GPU computing platforms for automotive driving applications. [0003] High-energy particles can cause bit flips in memory elements, or cause transient voltage pulses in other logic circuits such a...

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): G06F17/16G06T1/20
CPCG06F17/16G06T1/20
Inventor 王海滨王杨圣戴茜茜惠志坚叶静孙洪文
Owner HOHAI UNIV CHANGZHOU