Machine learning based method for predicating parameters during MPI (message passing interface) optimal operation in multi-core environments

A machine learning, multi-core technology, applied in neural learning methods, biological neural network models, etc., can solve the problems of huge configuration set optimization space and difficult manual implementation.

Inactive Publication Date: 2012-10-03
BEIJING COMPUTING CENT
View PDF2 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] figure 1 and figure 2 It shows that adjustable runtime parameters can bring considerable performance improvement to MPI applications, but at the same time, the configuration set of runtime parameters and the corresponding optimization space are quite large and difficult to implement manually

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
  • Machine learning based method for predicating parameters during MPI (message passing interface) optimal operation in multi-core environments
  • Machine learning based method for predicating parameters during MPI (message passing interface) optimal operation in multi-core environments
  • Machine learning based method for predicating parameters during MPI (message passing interface) optimal operation in multi-core environments

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] Further description will be made below in conjunction with the accompanying drawings and specific embodiments.

[0031] Adjustable runtime parameters have an important impact on the performance of MPI applications under multi-core clusters, but the optimal runtime parameters depend on the underlying architecture of the multi-core cluster and the characteristics of the MPI program itself. In this section, we introduce the method and steps of using machine learning technology to predict the optimal runtime parameters of MPI under multi-core.

[0032] Our approach consists of four stages: model construction, model training, parameter prediction using the trained model, and model prediction accuracy evaluation. In the first stage, we used two standard machine learning techniques—decision tree and artificial neural network were used to build the optimization model. In the model training phase, we use the constructed training benchmark to generate training data by setting a ...

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 novel method for optimizing an MPI (message passing interface) application in multi-core environments, and particularly relates to a machine learning based method for predicating parameters during MPI application optimal operation under multi-core clusters. According to the method, training benchmarks with different ratios of point-to-point communication data to collective communication data are designed to generate training data under the specific multi-core clusters, parameter optimized models during operation are constructed by a decision tree REPTree capable of quickly outputting results and an ANN (artificial neural network) capable of generating multiple output and good in noise immunity, the optimized models are trained by the training data generated by the training benchmarks, and the trained models are used for predicating the unknown parameters inputted to the MPI application during optimal operation. Experiments show that speed-up ratios generated by the parameters obtained by the REPTree-based predication model and the ANN-based predication model during optimal operation are averagely higher than 90% of a practical maximum speed-up ratio.

Description

technical field [0001] The invention relates to MPI optimization in a multi-core environment, in particular to a machine learning-based parameter prediction method for MPI optimal operation in a multi-core environment. Background technique [0002] As multi-core technology is more widely used in clusters, the performance optimization of MPI applications under multi-core clusters has become a research hotspot. The current mainstream MPI library implementations (Open MPI, MPICH, etc.) provide adjustable runtime parameter mechanisms, allowing users to tune runtime parameters according to specific application requirements, hardware, and operating systems to improve the performance of MPI applications. [0003] In this chapter, we design and implement a machine learning-based general MPI runtime parameter optimization model in a multi-core environment, which can automatically predict the near-optimal runtime parameter combination for an MPI program under a multi-core cluster with...

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): G06N3/08
Inventor 曾宇
Owner BEIJING COMPUTING CENT
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