Halide (programming language)

The main innovation Halide brings is the separation of the algorithm being implemented from its execution schedule, i.e. code specifying the loop nesting, parallelization, loop unrolling and vector instruction.^[3] These two are usually interleaved together and experimenting with changing the schedule requires the programmer to rewrite large portions of the algorithm with every change.^[4] With Halide, changing the schedule does not require any changes to the algorithm, allowing the programmer to experiment with scheduling.^[5][6]

The following function defines and sets the schedule for a 3×3 box filter defined as a series of two 3×1 passes, allowing the blur algorithm to remain independent of the execution schedule.^[7]

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;
}

Halide was developed primarily at MIT's CSAIL lab. Both Google and Adobe have been involved in Halide research.^[5] Google uses Halide in Pixel 2's Pixel Visual Core.^[8][7] Adobe Photoshop also uses Halide.^[9]

• Cuneiform (programming language)
• Algorithmic skeleton
• Parallel programming model