// Now a schedule that uses CUDA or OpenCL.
public void ScheduleForGpu()
{
// We make the decision about whether to use the GPU for each
// Func independently. If you have one Func computed on the
// CPU, and the next computed on the GPU, Halide will do the
// copy-to-gpu under the hood. For this pipeline, there's no
// reason to use the CPU for any of the stages. Halide will
// copy the input image to the GPU the first time we run the
// pipeline, and leave it there to reuse on subsequent runs.
// As before, we'll compute the LUT once at the start of the
// pipeline.
Lut.ComputeRoot();
// Let's compute the look-up-table using the GPU in 16-wide
// one-dimensional thread blocks. First we split the index
// into blocks of size 16:
var block = new HSVar("block");
var thread = new HSVar("thread");
Lut.Split(I, block, thread, 16);
// Then we tell cuda that our Vars 'block' and 'thread'
// correspond to CUDA's notions of blocks and threads, or
// OpenCL's notions of thread groups and threads.
Lut.GpuBlocks(block)
.GpuThreads(thread);
// This is a very common scheduling pattern on the GPU, so
// there's a shorthand for it:
// lut.gpu_tile(i, block, thread, 16);
// Func::gpu_tile behaves the same as Func::tile, except that
// it also specifies that the tile coordinates correspond to
// GPU blocks, and the coordinates within each tile correspond
// to GPU threads.
// Compute color channels innermost. Promise that there will
// be three of them and unroll across them.
Curved.Reorder(C, X, Y)
.Bound(C, 0, 3)
.Unroll(C);
// Compute curved in 2D 8x8 tiles using the GPU.
Curved.GpuTile(X, Y, XO, YO, XI, YI, 8, 8);
// This is equivalent to:
// curved.tile(x, y, xo, yo, xi, yi, 8, 8)
// .gpu_blocks(xo, yo)
// .gpu_threads(xi, yi);
// We'll leave sharpen as inlined into curved.
// Compute the padded input as needed per GPU block, storing
// the intermediate result in shared memory. In the schedule
// above xo corresponds to GPU blocks.
Padded.ComputeAt(Curved, XO);
// Use the GPU threads for the x and y coordinates of the
// padded input.
Padded.GpuThreads(X, Y);
// JIT-compile the pipeline for the GPU. CUDA, OpenCL, or
// Metal are not enabled by default. We have to construct a
// Target object, enable one of them, and then pass that
// target object to compile_jit. Otherwise your CPU will very
// slowly pretend it's a GPU, and use one thread per output
// pixel.
// Start with a target suitable for the machine you're running
// this on.
var target = HS.GetHostTarget();
// Then enable OpenCL or Metal, depending on which platform
// we're on. OS X doesn't update its OpenCL drivers, so they
// tend to be broken. CUDA would also be a fine choice on
// machines with NVidia GPUs.
if (target.OS == HSOperatingSystem.OSX)
{
target.SetFeature(HSFeature.Metal);
}
else
{
target.SetFeature(HSFeature.OpenCL);
}
// Uncomment the next line and comment out the lines above to
// try CUDA instead.
//target.SetFeature(HSFeature.CUDA);
// If you want to see all of the OpenCL, Metal, or CUDA API
// calls done by the pipeline, you can also enable the Debug
// flag. This is helpful for figuring out which stages are
// slow, or when CPU -> GPU copies happen. It hurts
// performance though, so we'll leave it commented out.
// target.set_feature(Target::Debug);
Curved.CompileJit(target);
}