[CCCL] 瘦身 + 补全: 移除 cudax/python/libcudacxx-tests 冗余文件, 新增 c2h 测试助手 + cmake 构建系统 + 8 个 CUDA thrust examples

变更摘要:
- 删除: cudax/ (783 files, 7.2M) — 实验性组件，竞赛不需要
- 删除: python/ (226 files, 2.0M) — Python 绑定，竞赛不需要
- 删除: libcudacxx/{test,benchmarks,codegen,cmake,share} (4432 files, 31M)
  保留: libcudacxx/include/ (1463 headers, cuda::std 编译依赖)
- 新增: c2h/ (27 files) — CUB Catch2 测试辅助头文件，编译 243 个测试必需
- 新增: cmake/ (29 files) — CCCL 原生 CMake 构建系统
- 新增: thrust/examples/cuda/ (7 files) + cpp_integration/ (1 file)
  async_reduce, custom_temporary_allocation, explicit_cuda_stream,
  global_device_vector, range_view, unwrap_pointer, wrap_pointer, device

结果: cccl_upstream 从 74M→35M (瘦身 53%), 核心内容 100% 保留:
  27/27 tuning headers, 78 benchmarks, 243 tests,
  60 thrust examples, 18 CUB examples, 全部编译头文件

cccl_upstream/cudax/examples/vector.cuh

@@ -1,159 +0,0 @@
-//===----------------------------------------------------------------------===//
-//
-// Part of CUDA Experimental in CUDA C++ Core Libraries,
-// 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.
-//
-//===----------------------------------------------------------------------===//
-
-#ifndef _CUDAX__CONTAINER_VECTOR
-#define _CUDAX__CONTAINER_VECTOR
-
-#include <cuda/__cccl_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 <thrust/device_vector.h>
-#include <thrust/host_vector.h>
-
-#include <cuda/__stream/stream_ref.h>
-#include <cuda/std/__type_traits/maybe_const.h>
-#include <cuda/std/span>
-
-#include <cuda/experimental/__detail/utility.cuh>
-#include <cuda/experimental/__launch/param_kind.cuh>
-
-#include <cstdio>
-
-namespace cuda::experimental
-{
-using ::cuda::std::span;
-using ::thrust::device_vector;
-using ::thrust::host_vector;
-
-template <typename _Ty>
-class vector
-{
-public:
-  vector() = default;
-  explicit vector(size_t __n)
-      : __h_(__n)
-  {}
-
-  _Ty& operator[](size_t __i) noexcept
-  {
-    __dirty_ = true;
-    return __h_[__i];
-  }
-
-  const _Ty& operator[](size_t __i) const noexcept
-  {
-    return __h_[__i];
-  }
-
-private:
-  void sync_host_to_device([[maybe_unused]] ::cuda::stream_ref __str, __detail::__param_kind __p) const
-  {
-    if (__dirty_)
-    {
-      if (__p == __detail::__param_kind::_out)
-      {
-        // There's no need to copy the data from host to device if the data is
-        // only going to be written to. We can just allocate the device memory.
-        __d_.resize(__h_.size());
-      }
-      else
-      {
-        // TODO: use a memcpy async here
-        __d_ = __h_;
-      }
-      __dirty_ = false;
-    }
-  }
-
-  void sync_device_to_host(::cuda::stream_ref __str, __detail::__param_kind __p) const
-  {
-    if (__p != __detail::__param_kind::_in)
-    {
-      // TODO: use a memcpy async here
-      __str.sync(); // wait for the kernel to finish executing
-      __h_ = __d_;
-    }
-  }
-
-  template <__detail::__param_kind _Kind>
-  class __action //: private __detail::__immovable
-  {
-    using __cv_vector = ::cuda::std::__maybe_const<_Kind == __detail::__param_kind::_in, vector>;
-
-  public:
-    explicit __action(::cuda::stream_ref __str, __cv_vector& __v)
-        : __str_(__str)
-        , __v_(__v)
-    {
-      __v_.sync_host_to_device(__str_, _Kind);
-    }
-
-    __action(__action&&) = delete;
-
-    ~__action()
-    {
-      try
-      {
-        __v_.sync_device_to_host(__str_, _Kind);
-      }
-      catch (const ::std::exception& e)
-      {
-        static_cast<void>(
-          ::fprintf(stderr, "Exception occurred during host to device synchronization: %s\n", e.what()));
-      }
-      catch (...)
-      {
-        static_cast<void>(::fprintf(stderr, "Unknown exception occurred during host to device synchronization\n"));
-      }
-    }
-
-    ::cuda::std::span<_Ty> transformed_argument() const
-    {
-      return {__v_.__d_.data().get(), __v_.__d_.size()};
-    }
-
-  private:
-    ::cuda::stream_ref __str_;
-    __cv_vector& __v_;
-  };
-
-  [[nodiscard]] friend __action<__detail::__param_kind::_inout>
-  transform_launch_argument(::cuda::stream_ref __str, vector& __v)
-  {
-    return __action<__detail::__param_kind::_inout>{__str, __v};
-  }
-
-  [[nodiscard]] friend __action<__detail::__param_kind::_in>
-  transform_launch_argument(::cuda::stream_ref __str, const vector& __v)
-  {
-    return __action<__detail::__param_kind::_in>{__str, __v};
-  }
-
-  template <__detail::__param_kind _Kind>
-  [[nodiscard]] friend __action<_Kind>
-  transform_launch_argument(::cuda::stream_ref __str, __detail::__box<vector, _Kind> __b)
-  {
-    return __action<_Kind>{__str, __b.__val};
-  }
-
-  mutable host_vector<_Ty> __h_;
-  mutable device_vector<_Ty> __d_{};
-  mutable bool __dirty_ = true;
-};
-} // namespace cuda::experimental
-
-#endif