Parallel programming with CUDA - exercises

Created by Zhaoxin Liang, late Sep. 2017

Combining EE5351 mateirals, future material with OpenCV to be included

Contents:

• MP0_function_wrapper: Compiler test
• MP1_function_wrapper: Vector addition
• MP2_function_wrapper: Matrix multiplication
• MP3_function_wrapper: Matrix multiplication with shared memory
• MP4_function_wrapper: Matrix convolution
• MP5_function_wrapper: Reduction tree
• MP6_function_wrapper: Prefix scan
• MP7_function_wrapper: Histogram
• cuda_query_function0: query device info
  • ParallelMultiply: Matrix multiplication with template

Project log:

1. 04/23/2017: Serial implementation of matrix multiplication is given in matrix_functionality.cpp and matrix_functionality.h, while the parallel version is give in matrix_kernal.cu and matrix_kernel.cuh
   

Comments:

The code for git file: git add .

git status
git commit -m "..."
git push master