[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/support/Counter.h

@@ -0,0 +1,96 @@
+//===----------------------------------------------------------------------===//
+//
+// Part of the LLVM Project, 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
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef COUNTER_H
+#define COUNTER_H
+
+#include <functional> // for std::hash
+
+#include "test_macros.h"
+
+struct Counter_base
+{
+  static int gConstructed;
+};
+
+template <typename T>
+class Counter : public Counter_base
+{
+public:
+  Counter()
+      : data_()
+  {
+    ++gConstructed;
+  }
+  Counter(const T& data)
+      : data_(data)
+  {
+    ++gConstructed;
+  }
+  Counter(const Counter& rhs)
+      : data_(rhs.data_)
+  {
+    ++gConstructed;
+  }
+  Counter& operator=(const Counter& rhs)
+  {
+    data_ = rhs.data_;
+    return *this;
+  }
+  Counter(Counter&& rhs)
+      : data_(std::move(rhs.data_))
+  {
+    ++gConstructed;
+  }
+  Counter& operator=(Counter&& rhs)
+  {
+    ++gConstructed;
+    data_ = std::move(rhs.data_);
+    return *this;
+  }
+  ~Counter()
+  {
+    --gConstructed;
+  }
+
+  const T& get() const
+  {
+    return data_;
+  }
+
+  bool operator==(const Counter& x) const
+  {
+    return data_ == x.data_;
+  }
+  bool operator<(const Counter& x) const
+  {
+    return data_ < x.data_;
+  }
+
+private:
+  T data_;
+};
+
+int Counter_base::gConstructed = 0;
+
+namespace std
+{
+template <class T>
+struct hash<Counter<T>>
+{
+  using argument_type = Counter<T>;
+  using result_type   = std::size_t;
+
+  std::size_t operator()(const Counter<T>& x) const
+  {
+    return std::hash<T>()(x.get());
+  }
+};
+} // namespace std
+
+#endif