[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/codegen/codegen.cpp

@@ -0,0 +1,45 @@
+//===----------------------------------------------------------------------===//
+//
+// 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) 2024 NVIDIA CORPORATION & AFFILIATES.
+//
+//===----------------------------------------------------------------------===//
+
+#include <fstream>
+#include <iostream>
+#include <ostream>
+
+#include "generators/compare_and_swap.h"
+#include "generators/exchange.h"
+#include "generators/fence.h"
+#include "generators/fetch_ops.h"
+#include "generators/header.h"
+#include "generators/ld_st.h"
+
+using namespace std::string_literals;
+
+int main(int argc, char** argv)
+{
+  std::fstream filestream;
+
+  if (argc == 2)
+  {
+    filestream.open(argv[1], filestream.out);
+  }
+
+  std::ostream& stream = filestream.is_open() ? filestream : std::cout;
+
+  FormatHeader(stream);
+  FormatFence(stream);
+  FormatLoad(stream);
+  FormatStore(stream);
+  FormatCompareAndSwap(stream);
+  FormatExchange(stream);
+  FormatFetchOps(stream);
+  FormatTail(stream);
+
+  return 0;
+}