mratsim · September 16, 2017 10:50
diff --git a/grid-stride.cu b/grid-stride.cu
 __global__
 void saxpy(int n, float a, float *x, float *y)
 {
    for (int i = blockIdx.x * blockDim.x + threadIdx.x; 
         i < n; 
         i += blockDim.x * gridDim.x) 
      {
          y[i] = a * x[i] + y[i];
      }
 }
	__global__
	void saxpy(int n, float a, float x, float y)
	{
	for (int i = blockIdx.x * blockDim.x + threadIdx.x;
	i < n;
	i += blockDim.x * gridDim.x)
	{
	y[i] = a * x[i] + y[i];
	}
	}