Tests/CudaOnly/SeparateCompilationPTX/kernels.cu


1
2
3
4
5
6
7
8
9
10
11
12
13
14


__global__ void kernelA(float* r, float* x, float* y, float* z, int size)
{
  for (int i = threadIdx.x; i < size; i += blockDim.x) {
    r[i] = x[i] * y[i] + z[i];
  }
}

__global__ void kernelB(float* r, float* x, float* y, float* z, int size)
{
  for (int i = threadIdx.x; i < size; i += blockDim.x) {
    r[i] = x[i] * y[i] + z[i];
  }
}