[INFRA] Import NVIDIA/CCCL upstream as optimization reference library

CCCL (CUDA C++ Core Libraries) provides:
- CUB: device/block/warp-level GPU primitives (reduce, scan, sort, topk)
- Thrust: high-level parallel algorithms (transform_reduce, sort, scan)
- libcudacxx: CUDA C++ standard library (atomics, barriers, memory)
- cudax: experimental features (memory resources, allocators)
- Tuning policies: per-SM hardware-specific algorithm parameters

Competition optimization vectors mapped to CCCL:
- Output TPS (83% weight): warp_reduce, block_reduce, device_topk
- Input TPS (14% weight): device_scan, block_load, prefetch
- Cache TPS (3% weight): prefix caching strategy patterns
- Memory (0.9 util): pooled/cached/buddy allocators

Source: https://github.com/NVIDIA/cccl (shallow clone, HEAD only)
License: Apache-2.0

cccl_upstream/c/CMakeLists.txt

@@ -0,0 +1,19 @@
+if (CCCL_ENABLE_C_PARALLEL AND CCCL_ENABLE_C_PARALLEL_V2)
+  message(
+    FATAL_ERROR
+    "CCCL_ENABLE_C_PARALLEL and CCCL_ENABLE_C_PARALLEL_V2 are mutually exclusive. "
+    "v2 is the HostJIT-based successor of v1; pick one."
+  )
+endif()
+
+if (CCCL_ENABLE_C_PARALLEL)
+  add_subdirectory(parallel)
+endif()
+
+if (CCCL_ENABLE_C_PARALLEL_V2)
+  add_subdirectory(parallel.v2)
+endif()
+
+if (CCCL_ENABLE_C_EXPERIMENTAL_STF)
+  add_subdirectory(experimental/stf)
+endif()