cuda sdk sample code : 0_Simple/matrixMul.cu

matrixMul.cu

#include <stdio.h>
#include <assert.h>
#include <cuda_runtime.h>
#include <helper_function.h>
#include <helper_cuda.h>

template <int BLOCK_SIZE> __global__ void MatrixMulCUDA(float *C, float *A,
                                                        float *B, int wA, int wB){
  //Block index
  int bx = blockIdx.x;
  int by = blockIdx.y;
  
  //Thread index
  int tx = threadIdx.x;
  int ty = threadIdx.y;
  
  // Index of the first sub-matrix of A processed by the block
  int aBegin = wA * BLOCK_SIZE * by;
  
  // Index of the last sub-matrix of A processed by the block
  int aEnd = aBegin + wA - 1;
  
  // step size used to iterate through the sub-matrix of A
  int aStep = BLOCK_SIZE;