webgpu

Code Passed all Unit Test provided by WebGPU The Courser is provided by Coursera, Heterogeneous Parallel Programming by Wen-mei W. Hwu University of Illinois at Urbana-Champaign

• Basic_Vector_Addition
  • The "hello world" of CUDA
• Basic_Matrix_Multiplication
  • Basic A * B Matrix Multiplication (none shared memory)
• Tiled_Matrix_Multiplication
  • A * B Matrix Multiplication with Tiled memory (shared memory)
• Image_Convolution
  • Image Template Block pixels Convolution
• List_Reduction
  • Given a list (lst) of length n
  • Output its sum = lst[0] + lst[1] + ... + lst[n-1];
• List_Scan
  • Given a list (lst) of length n
  • Output its prefix sum = {lst[0], lst[0] + lst[1], lst[0] + lst[1] + ... + lst[n-1]}
• Histogram
  • Image Histogram Equalization
• Vector_Addition_with_Streams
  • CUDA streaming API vector addition
• OpenCL_Vecton_Addition
  • "hello world" of OpenCL
• OpenACC_Vector_Addition
  • "hello world" of OpenACC
• C++AMP_Vector_Addition
  • "hello world" of C++ AMP