diff --git a/exercises/ex5/saxpy_cuda.F90 b/exercises/ex5/saxpy_cuda.F90
index a0e5e0e..97159c8 100644
--- a/exercises/ex5/saxpy_cuda.F90
+++ b/exercises/ex5/saxpy_cuda.F90
@@ -1,53 +1,53 @@
 module mathOps
 contains
   attributes(global) subroutine saxpy_cuda(x, y, a)
     implicit none
     real :: x(:), y(:)
     real, value :: a
     integer :: i, j, n
     n = size(x)
     i = blockDim%x * (blockIdx%x - 1) + threadIdx%x
-    do j=1, n, blockDim%x*gridDim%x
+    do j=i, n, blockDim%x*gridDim%x
         y(j) = y(j) + a*x(j)
     end do
   end subroutine saxpy_cuda
 
   subroutine saxpy_cpu(x, y, a)
     implicit none
     real :: x(:), y(:)
     real, value :: a
     integer :: i, n
     n = size(x)
     do i=1, n
         y(i) = y(i) + a*x(i)
     end do
   end subroutine saxpy_cpu
 
 end module mathOps
 
 program testSaxpy
   use mathOps
   use cudafor
   implicit none
   integer, parameter :: N = 4000
   integer istat, i
   real :: x(N), y(N), a, norm2_cpu, norm2_gpu
   real, managed :: x_d(N), y_d(N)
   type(dim3) :: grid, tBlock
 
   tBlock = dim3(256,1,1)
   grid = dim3(ceiling(real(N)/tBlock%x),1,1)
 
   do i=1, N
       y(i) = 0.0
       x(i) = i*0.458
       a = 12.1
   end do
 
   x_d = x
   y_d = y
   call saxpy_cuda<<<grid, tBlock>>>(x_d, y_d, a)
   istat = cudaDeviceSynchronize() 
   call saxpy_cpu(x, y, a)
   write(*,*) 'L2 norm: ', norm2(y-y_d)
 end program testSaxpy