Implement CUDA multipass for knn > GPU_MAX_SELECTION_K (#7381)

The KNN search on GPU breaks silently when the k value is larger than the macro GPU_MAX_SELECTION_K, resulting in a trash output (all 0s, large indices > number of total points, or even negative indices). The macro GPU_MAX_SELECTION_K is 2048 if CUDA_VERSION > 9000, otherwise it is 1024. On CPU, the KNN search obviously has no such limits. To improve the GPU KNN search without altering the macro GPU_MAX_SELECTION_K, a multipass algorithm should be implemented, splitting the KNN search into batches where each batch size is < GPU_MAX_SELECTION_K.

Author: nicolaloi

CHANGELOG.md

@@ -69,6 +69,7 @@
 -   Fix advanced indexing bug with sliced boolean masks on CUDA devices (PR #7340)
 -   Fix logic for adding -allow-unsupported-compiler to nvcc (PR #7337)
 -   Fix linker error "library limit of 65535 objects exceeded" with Ninja generator on MSVC (PR #7335)
+-   Implement CUDA multipass for KNN > `GPU_MAX_SELECTION_K` (PR #7381)
 -   Download tarballs instead of Git repos for "3rdparty/uvatlas" (PR #7371)
 -   macOS x86_64 not longer supported, only macOS arm64 is supported.
 -   Python 3.13+3.14 support