[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/test/common/host_device.cuh

@@ -1,101 +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) 2023 NVIDIA CORPORATION & AFFILIATES.
-//
-//===----------------------------------------------------------------------===//
-
-#ifndef __COMMON_HOST_DEVICE_H__
-#define __COMMON_HOST_DEVICE_H__
-
-#include "utility.cuh"
-
-template <typename Dims, typename Lambda>
-void __global__ lambda_launcher(const Dims dims, const Lambda lambda)
-{
-  lambda(dims);
-}
-
-template <typename Comparator, unsigned int FilterArch>
-bool arch_filter(const cudaDeviceProp& props)
-{
-  int act_arch = props.major * 10 + props.minor;
-  if (Comparator()(act_arch, FilterArch))
-  {
-    return true;
-  }
-  return false;
-}
-
-static bool skip_host_exec(bool (* /* filter */)(const cudaDeviceProp&))
-{
-  return false;
-}
-
-static bool skip_device_exec(bool (*filter)(const cudaDeviceProp&))
-{
-  cudaDeviceProp props;
-  REQUIRE_CUDART(cudaGetDeviceProperties(&props, 0));
-  return filter(props);
-}
-
-template <typename Dims, typename Lambda, typename... Filters>
-void test_host_dev(const Dims& dims, const Lambda& lambda, const Filters&... filters)
-{
-  SECTION("Host execution")
-  {
-    if ((... && !skip_host_exec(filters)))
-    {
-      // host testing
-      lambda(dims);
-    }
-  }
-
-  SECTION("Device execution")
-  {
-    // Asymmetrical but cleaner
-    if ((... || skip_device_exec(filters)))
-    {
-      return;
-    }
-
-    cudaLaunchConfig_t config = {};
-    config.gridDim            = {0};
-    cudaLaunchAttribute attrs[1];
-    config.attrs = &attrs[0];
-
-    config.blockDim = dims.extents(cuda::gpu_thread, cuda::block);
-    config.gridDim  = dims.extents(cuda::block, cuda::grid);
-
-    if constexpr (Dims::has_level(cluster))
-    {
-      dim3 cluster_dims                            = dims.extents(cuda::block, cuda::cluster);
-      config.attrs[config.numAttrs].id             = cudaLaunchAttributeClusterDimension;
-      config.attrs[config.numAttrs].val.clusterDim = {cluster_dims.x, cluster_dims.y, cluster_dims.z};
-      config.numAttrs                              = 1;
-    }
-    else
-    {
-      config.numAttrs = 0;
-    }
-
-    // device testing
-    REQUIRE_CUDART(cudaLaunchKernelEx(&config, lambda_launcher<Dims, Lambda>, dims, lambda));
-    REQUIRE_CUDART(cudaDeviceSynchronize());
-  }
-}
-
-template <typename Fn, typename Tuple>
-void apply_each(const Fn& fn, const Tuple& tuple)
-{
-  cuda::std::apply(
-    [&](const auto&... elems) {
-      (fn(elems), ...);
-    },
-    tuple);
-}
-
-#endif // __COMMON_HOST_DEVICE_H__