[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/libcudacxx/test/maintenance/all-internal-headers

@@ -0,0 +1,34 @@
+#!/usr/bin/env bash
+
+#this creates a set of tests, that ensures, that all internal headers can be build independently
+
+set -euo pipefail
+
+internal_headers=$(find ../../include -path "*cuda/std/__*/*" -not -path "*/__cuda/*")
+
+cd ../../test/libcxx/selftest/internal_headers
+
+for f in $internal_headers
+do
+    short_path=${f##*../include/}
+    test_name=${f##*include/}
+    test_name=${test_name%.h}.pass.cpp
+
+    mkdir -p -- "${test_name%/*}"
+    cat > "$test_name" << EOL
+//===----------------------------------------------------------------------===//
+//
+// Part of libcu++, the C++ Standard Library for your entire system,
+// under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+// SPDX-FileCopyrightText: Copyright (c) 2023 NVIDIA CORPORATION & AFFILIATES.
+//
+//===----------------------------------------------------------------------===//
+
+#include <cuda/std/version>
+#include <$short_path>
+
+int main(int, char**) { return 0; }
+EOL
+done