The Immersed Boundary-Lattice Boltzmann Method Parallel Model for Fluid-Structure Interaction on Heterogeneous Platforms

Algorithm 1

The IB-LBM parallel algorithm on CPU-GPU heterogeneous platforms

	Heterogeneous:
	//The data in the array is assigned to the buffer in the flow field.
	buffer_to_field<<<Grid_4, Block_4>>>()
	//The GPU performs IB-LBM simulation.
	for i = 0 ⟶ buffer do
	compute_force<<<Grid_1, Block_1>>>()
	spread_force<<<Grid_1, Block_1>>>()
	discrete_force<<<Grid_2, Block_2>>>()
	collision<<<Grid_2, Block_2>>>()
	streaming<<<Grid_2, Block_2>>>()
	boundary<<<Grid_3, Block_3>>>()
	compute_macroscopic<<<Grid_2, Block_2>>>()
	interpolation_velocity<<<Grid_1, Block_1>>>()
	lagrangian_move<<<Grid_1, Block_1>>>()
	end for
	//Copy the data of the buffer area in the flow field to a separate array.
	field_to_buffer<<<Grid_4, Block_4>>>()
	//The CPU performs IB-LBM simulation.
	for j = 0 ⟶ buffer do
	compute_force ()
	spread_force ()
	discrete_force ()
	collision ()
	streaming ()
	boundary ()
	compute_macroscopic ()
	interpolation_velocity ()
	lagrangian_move ()
	cudaMemcpy (cudaMemcpyDeviceToHost)
	exchange_data ()
	cudaMemcpy (cudaMemcpyHostToDevice)
	step_count+ = buffer
	if (step_count! = total_step)
	goto heterogeneous