Skip to content

The final project of Parallel Computing course in HCMUS. Here, we use CUDA to parallelize the implementation of Convolutional layer in a simple CNN architecture, as well as measure performance of various parallelize stategy.

Notifications You must be signed in to change notification settings

DreamyWanderer/Parallel_Computing-CNN_Parellelization-HCMUS

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

19 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Parallel Computation Course Repository - HCMUS-VNUHCM - Final Project

Information

  • Topic: CNN Architecture Parallelization
  • Student: Nguyễn Thế Hoàng (20120090)
  • Instructor: PhD. Phạm Trọng Nghĩa
  • Department: Computer Science

About repository

This repository contains tasks description, source code and other related documents for this course. It includes:

  • 1 final project

System requirement

Without further notices, every projects/labs. in this repository is self-contained, excep we may need:

  • CUDA and related NVIDIA drivers installed on local system.

How to run

  1. Open the ./CNN_Parallelizatin/Source/mini-dnn-cpp-master/report.ipynb.
  2. Change the location to the CNN_Parallelization directory in the third cells in report.ipynb as instructed.
  3. Compile the program, then run ./demo.exe (as instructed in the report.ipynb).

Youtube video link

Link

About

The final project of Parallel Computing course in HCMUS. Here, we use CUDA to parallelize the implementation of Convolutional layer in a simple CNN architecture, as well as measure performance of various parallelize stategy.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published