Heterogeneous-Parallel-Computing-with-CUDA

This repository contains implementation of various parallel algorithms using CUDA.

Each folder contains a README.md which contains description of programs.

Contents:

• A0
  • Sum of two large arrays (with time metrics)
  • Vector Reduction
• A1
  • Vector addition using thrust
  • Image Blur
• A2
  • Convert RGB image to grey scale
  • Matrix Multiplication
  • Tiled Matrix Multiplication
• A3
  • Histogram for ASCII characters and numbers
  • Histogram sort using thrust
  • Image convolution
  • Shared memory tiling by implementing 7-point Stencil
• A4
  • Parallel BFS
    • Vertex parallel mathod
    • Edge Parallel method
    • Work efficient method