[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/include/cuda/__cmath/pow2.h

@@ -0,0 +1,74 @@
+//===----------------------------------------------------------------------===//
+//
+// 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) 2025 NVIDIA CORPORATION & AFFILIATES.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef _CUDA___CMATH_POW2_H
+#define _CUDA___CMATH_POW2_H
+
+#include <cuda/std/detail/__config>
+
+#if defined(_CCCL_IMPLICIT_SYSTEM_HEADER_GCC)
+#  pragma GCC system_header
+#elif defined(_CCCL_IMPLICIT_SYSTEM_HEADER_CLANG)
+#  pragma clang system_header
+#elif defined(_CCCL_IMPLICIT_SYSTEM_HEADER_MSVC)
+#  pragma system_header
+#endif // no system header
+
+#include <cuda/std/__bit/has_single_bit.h>
+#include <cuda/std/__bit/integral.h>
+#include <cuda/std/__type_traits/is_integer.h>
+#include <cuda/std/__type_traits/is_signed.h>
+#include <cuda/std/__type_traits/make_unsigned.h>
+
+#include <cuda/std/__cccl/prologue.h>
+
+_CCCL_BEGIN_NAMESPACE_CUDA
+
+_CCCL_TEMPLATE(typename _Tp)
+_CCCL_REQUIRES(::cuda::std::__cccl_is_integer_v<_Tp>)
+[[nodiscard]] _CCCL_API constexpr bool is_power_of_two(_Tp __t) noexcept
+{
+  if constexpr (::cuda::std::is_signed_v<_Tp>)
+  {
+    _CCCL_ASSERT(__t >= _Tp{0}, "cuda::is_power_of_two requires non-negative input");
+  }
+  using _Up = ::cuda::std::make_unsigned_t<_Tp>;
+  return ::cuda::std::has_single_bit(static_cast<_Up>(__t));
+}
+
+_CCCL_TEMPLATE(typename _Tp)
+_CCCL_REQUIRES(::cuda::std::__cccl_is_integer_v<_Tp>)
+[[nodiscard]] _CCCL_API constexpr _Tp next_power_of_two(_Tp __t) noexcept
+{
+  if constexpr (::cuda::std::is_signed_v<_Tp>)
+  {
+    _CCCL_ASSERT(__t >= _Tp{0}, "cuda::is_power_of_two requires non-negative input");
+  }
+  using _Up = ::cuda::std::make_unsigned_t<_Tp>;
+  return ::cuda::std::bit_ceil(static_cast<_Up>(__t));
+}
+
+_CCCL_TEMPLATE(typename _Tp)
+_CCCL_REQUIRES(::cuda::std::__cccl_is_integer_v<_Tp>)
+[[nodiscard]] _CCCL_API constexpr _Tp prev_power_of_two(_Tp __t) noexcept
+{
+  if constexpr (::cuda::std::is_signed_v<_Tp>)
+  {
+    _CCCL_ASSERT(__t >= _Tp{0}, "cuda::is_power_of_two requires non-negative input");
+  }
+  using _Up = ::cuda::std::make_unsigned_t<_Tp>;
+  return ::cuda::std::bit_floor(static_cast<_Up>(__t));
+}
+
+_CCCL_END_NAMESPACE_CUDA
+
+#include <cuda/std/__cccl/epilogue.h>
+
+#endif // _CUDA___CMATH_POW2_H