[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/thrust/examples/basic_vector.cu

@@ -0,0 +1,40 @@
+#include <thrust/device_vector.h>
+#include <thrust/host_vector.h>
+
+#include <iostream>
+
+int main()
+{
+  // H holds 4 integers
+  thrust::host_vector<int> H{14, 20, 38, 46};
+
+  // H.size() returns the size of vector H
+  std::cout << "H has size " << H.size() << '\n';
+
+  // print contents of H
+  for (size_t i = 0; i < H.size(); i++)
+  {
+    std::cout << "H[" << i << "] = " << H[i] << '\n';
+  }
+
+  // resize H
+  H.resize(2);
+
+  std::cout << "H now has size " << H.size() << '\n';
+
+  // Copy host_vector H to device_vector D
+  thrust::device_vector<int> D = H;
+
+  // elements of D can be modified
+  D[0] = 99;
+  D[1] = 88;
+
+  // print contents of D
+  for (size_t i = 0; i < D.size(); i++)
+  {
+    std::cout << "D[" << i << "] = " << D[i] << '\n';
+  }
+
+  // H and D are automatically deleted when the function returns
+  return 0;
+}