To gain a bit of practice writing CUDA programs your warm-up task is to implement the SAXPY function in CUDA (The name SAXPY stands for single-precision a times x plus y.). For input arrays x and y, output array dest, and value a (all single-precision floating-point values), the function computes dest[i] = a*x[i] + y[i] for all array elements i. You can assume any value for a. You need to test your program on a real GPU.