Performance Optimization of 3D Lattice Boltzmann Flow Solver on a GPU

Algorithm 4

Single CUDA kernel after combining two phases of LBM.

()  int  i;

()  for  (i = 0; i < timeSteps; i++)

() 

()   lbm_kernel<<<GRID, BLOCK>>>(source_grid,

      dest_grid, xdim, ydim, zdim, cell_size,

      grid_size);

()   cudaThreadSyncronize();

()   swap_grid(source_grid, dest_grid);

()