Func blur_3x3(Func input) {
Func blur_x, blur_y;
Var x, y, xi, yi;
// The algorithm - no storage or order
blur_x(x, y) = (input(x-1, y) + input(x, y) + input(x+1, y))/3;
blur_y(x, y) = (blur_x(x, y-1) + blur_x(x, y) + blur_x(x, y+1))/3;
// The schedule - defines order, locality; implies storage
blur_y.tile(x, y, xi, yi, 256, 32)
.vectorize(xi, 8).parallel(y);
blur_x.compute_at(blur_y, x).vectorize(x, 8);
return blur_y;
}