saxpy_cuda_256elements.F90
e0054dc19a68master

saxpy_cuda_256elements.F90
View Options

			module mathOps
			contains
			attributes(global) subroutine saxpy_cuda(x, y, a)
			implicit none
			real :: x(:), y(:)
			real, value :: a
			integer :: i, n
			n = size(x)
			!implement saxpy on GPU here
			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 = 256
			integer istat, i
			real :: x(N), y(N), a, norm2_cpu, norm2_gpu
			real, device :: x_d(N), y_d(N)


			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 the GPU implementation here
			!y = y_d
			istat = cudaDeviceSynchronize()
			call saxpy_cpu(x, y, a)
			write(,) 'L2 norm: ', norm2(y-y_d)
			end program testSaxpy