CUDA Academy · Lesson

Launching Kernels from a Kernel

Device-side recursion and refinement.

Kernels Launching Kernels

With dynamic parallelism, a running GPU kernel can launch another kernel itself, no trip back to the CPU required. 🚀

The launch looks identical to a host launch: the familiar triple angle brackets work right inside device code.

__global__ void child(int* d);
__global__ void parent(int* d) {
    child<<<1, 32>>>(d);
}