CUDA Programming

Content

• GPUtimer : the timer used in the following codes.

• VectorMultiply1 : This code performs element-wise vector multiplication.

• VectorMultiply2 : This code performs element-wise vector multiplication where each thread calculated two elements of the output vector.
• ColorToGrayscale : This code uses OpenCV libraries, which is an Open Source Computer Vision Library, to read the input color image and then display the resulting Grayscale image.
  You need to include both property sheets for debug and release : DebugPropertySheet.props & PropertySheetRelease.props then adjust their corresponding paths.
  The images used are : lena_color.bmp, Island.jpeg and Scene.jpeg.
• BasicMatrixMultiplication : This code implements basic dense matrix multiplication routine.
• TiledMatrixMultiplication : This code implements tiled dense matrix multiplication routine using shared memory.

References

OpenCV Tutorials:
https://docs.opencv.org/3.0beta/doc/tutorials/introduction/table_of_content_introduction/table_of_content_introduction.html