(1)    Init CUDA environment
(2)   Allocate GPU global memory .
(3)   Init variables and arrays on GPU
(4)   record time
(5)   call kernel
(6)   for     to     by Step  1 do
(7)               call kernel
(8)               call kernel
(9)               for     to     by Step  1 do
(10)                     call kernel
(11)              call kernel
(12) record time
(13) output and
(14) free GPU memory and stop CUDA environment
Algorithm 1: Parallel solution for Caputo fractional reaction-diffusion equation with CUDA.