[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/stf/utility/source_location_map.cu

@@ -1,51 +0,0 @@
-//===----------------------------------------------------------------------===//
-//
-// Part of CUDASTF 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) 2022-2025 NVIDIA CORPORATION & AFFILIATES.
-//
-//===----------------------------------------------------------------------===//
-
-#include <cuda/std/source_location>
-
-#include <cuda/experimental/__stf/utility/source_location.cuh>
-#include <cuda/experimental/stf.cuh>
-
-using namespace cuda::experimental::stf;
-
-// Create a map indexed by source locations
-::std::unordered_map<::cuda::std::source_location, int, reserved::source_location_hash, reserved::source_location_equal>
-  stats_map;
-
-void update_counter(::cuda::std::source_location loc = ::cuda::std::source_location::current())
-{
-  stats_map[loc]++;
-}
-
-void funcA()
-{
-  update_counter();
-}
-
-void funcB()
-{
-  update_counter();
-}
-
-int main()
-{
-  for (size_t i = 0; i < 10; i++)
-  {
-    funcA();
-    funcB();
-    funcB();
-  }
-
-  for (auto& e : stats_map)
-  {
-    auto& loc = e.first;
-    fprintf(stderr, "loc.function_name() %s : count %d\n", loc.function_name(), e.second);
-  }
-}

cccl_upstream/cudax/test/stf/utility/timing_with_fences.cu

@@ -1,101 +0,0 @@
-//===----------------------------------------------------------------------===//
-//
-// Part of CUDASTF 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) 2022-2024 NVIDIA CORPORATION & AFFILIATES.
-//
-//===----------------------------------------------------------------------===//
-
-#include <cuda/experimental/stf.cuh>
-
-using namespace cuda::experimental::stf;
-
-static __global__ void cuda_sleep_kernel(long long int clock_cnt)
-{
-  long long int start_clock  = clock64();
-  long long int clock_offset = 0;
-  while (clock_offset < clock_cnt)
-  {
-    clock_offset = clock64() - start_clock;
-  }
-}
-
-void cuda_sleep(double ms, cudaStream_t stream)
-{
-  int device;
-  cudaGetDevice(&device);
-
-  // cudaDevAttrClockRate: Peak clock frequency in kilohertz;
-  int clock_rate;
-  cudaDeviceGetAttribute(&clock_rate, cudaDevAttrClockRate, device);
-
-  long long int clock_cnt = (long long int) (ms * clock_rate);
-  cuda_sleep_kernel<<<1, 1, 0, stream>>>(clock_cnt);
-}
-
-template <typename Ctx_t>
-void run(int NTASKS, int ms)
-{
-  Ctx_t ctx;
-
-  int dummy[1];
-  auto handle = ctx.logical_data(dummy);
-
-  cudaEvent_t start, stop;
-  cuda_safe_call(cudaEventCreate(&start));
-  cuda_safe_call(cudaEventCreate(&stop));
-
-  // warm-up
-  ctx.task(handle.rw())->*[ms](cudaStream_t stream, auto) {
-    cuda_sleep(ms, stream);
-  };
-
-  cuda_safe_call(cudaEventRecord(start, ctx.fence()));
-
-  for (int iter = 0; iter < NTASKS; iter++)
-  {
-    ctx.task(handle.rw())->*[ms](cudaStream_t stream, auto) {
-      cuda_sleep(ms, stream);
-    };
-  }
-
-  cuda_safe_call(cudaEventRecord(stop, ctx.fence()));
-
-  ctx.finalize();
-
-  [[maybe_unused]] float elapsed;
-  cuda_safe_call(cudaEventElapsedTime(&elapsed, start, stop));
-
-  [[maybe_unused]] float expected = 1.0f * NTASKS * ms;
-
-  /* We cannot really expect this measurement to be accurate because the
-   * thread(s) executing the code might be preempted on a system with a high load
-   * (as during unit tests). So the best we can expect is that the elapsed time
-   * is larger than the sleep time, but event the timer on the GPU is not
-   * perfectly accurate so we do not make any strict assumptions about the
-   * test, and just keep this test to demonstrate how to use the mechanisms,
-   * and ensure they are functional . */
-  // EXPECT(elapsed >= expected);
-}
-
-int main(int argc, char** argv)
-{
-  int NTASKS = 25;
-  int ms     = 200;
-
-  if (argc > 1)
-  {
-    NTASKS = atoi(argv[1]);
-  }
-
-  if (argc > 2)
-  {
-    ms = atoi(argv[2]);
-  }
-
-  run<context>(NTASKS, ms);
-  run<stream_ctx>(NTASKS, ms);
-  run<graph_ctx>(NTASKS, ms);
-}