[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/python/cuda_cccl/benchmarks/compute/reduce/custom.py

@@ -1,82 +0,0 @@
-# Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. ALL RIGHTS RESERVED.
-#
-# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
-
-"""
-Python benchmark for reduce custom operation using cuda.compute.reduce_into.
-
-C++ equivalent: cub/benchmarks/bench/reduce/custom.cu
-
-Notes:
-- Uses a custom max operator (not OpKind) to exercise generic path
-- int128 and complex32 are not supported by cupy
-- Migration: Python limits to basic numeric types; C++ includes int128/complex.
-"""
-
-import sys
-from pathlib import Path
-
-sys.path.insert(0, str(Path(__file__).parent.parent))
-
-import cupy as cp
-import numpy as np
-from utils import SIGNED_TYPES as TYPE_MAP
-from utils import as_cupy_stream, generate_data_with_entropy
-
-import cuda.bench as bench
-from cuda.compute import make_reduce_into
-
-
-def max_op(a, b):
-    return a if a > b else b
-
-
-def bench_reduce_custom(state: bench.State):
-    type_str = state.get_string("T{ct}")
-    dtype = TYPE_MAP[type_str]
-    num_items = int(state.get_int64("Elements{io}"))
-
-    alloc_stream = as_cupy_stream(state.get_stream())
-    with alloc_stream:
-        d_in = generate_data_with_entropy(num_items, dtype, "1.000", alloc_stream)
-        d_out = cp.empty(1, dtype=dtype)
-
-    h_init = np.zeros(1, dtype=dtype)
-
-    reducer = make_reduce_into(d_in=d_in, d_out=d_out, op=max_op, h_init=h_init)
-
-    temp_storage_bytes = reducer(
-        temp_storage=None,
-        d_in=d_in,
-        d_out=d_out,
-        num_items=num_items,
-        op=max_op,
-        h_init=h_init,
-    )
-    with alloc_stream:
-        temp_storage = cp.empty(temp_storage_bytes, dtype=np.uint8)
-
-    state.add_element_count(num_items)
-    state.add_global_memory_reads(num_items * d_in.dtype.itemsize, "Size")
-    state.add_global_memory_writes(d_out.dtype.itemsize)
-
-    def launcher(launch: bench.Launch):
-        reducer(
-            temp_storage=temp_storage,
-            d_in=d_in,
-            d_out=d_out,
-            num_items=num_items,
-            op=max_op,
-            h_init=h_init,
-            stream=launch.get_stream(),
-        )
-
-    state.exec(launcher, batched=False)
-
-
-if __name__ == "__main__":
-    b = bench.register(bench_reduce_custom)
-    b.set_name("base")
-    b.add_string_axis("T{ct}", list(TYPE_MAP.keys()))
-    b.add_int64_power_of_two_axis("Elements{io}", range(16, 29, 4))
-    bench.run_all_benchmarks(sys.argv)

cccl_upstream/python/cuda_cccl/benchmarks/compute/reduce/min.py

@@ -1,85 +0,0 @@
-# Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. ALL RIGHTS RESERVED.
-#
-# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
-
-"""
-Python benchmark for reduce min operation using cuda.compute.reduce_into.
-
-C++ equivalent: cub/benchmarks/bench/reduce/min.cu
-
-Notes:
-- Uses OpKind.MINIMUM for minimum reduction
-- C++ uses cuda::minimum<> which CUB recognizes for optimized code paths (DPX on Hopper+)
-- int128 and complex32 are not supported by cupy
-"""
-
-import sys
-from pathlib import Path
-
-sys.path.insert(0, str(Path(__file__).parent.parent))
-
-import cupy as cp
-import numpy as np
-from utils import FUNDAMENTAL_TYPES as TYPE_MAP
-from utils import as_cupy_stream, generate_data_with_entropy
-
-import cuda.bench as bench
-from cuda.compute import OpKind, make_reduce_into
-
-
-def bench_reduce_min(state: bench.State):
-    type_str = state.get_string("T{ct}")
-    dtype = TYPE_MAP[type_str]
-    num_items = int(state.get_int64("Elements{io}"))
-
-    alloc_stream = as_cupy_stream(state.get_stream())
-    with alloc_stream:
-        d_in = generate_data_with_entropy(num_items, dtype, "1.000", alloc_stream)
-        d_out = cp.empty(1, dtype=dtype)
-
-    # Initial value for min reduction (max value of type)
-    if np.issubdtype(dtype, np.integer):
-        init_val = np.iinfo(dtype).max
-    else:
-        init_val = np.finfo(dtype).max
-    h_init = np.array([init_val], dtype=dtype)
-
-    reducer = make_reduce_into(d_in=d_in, d_out=d_out, op=OpKind.MINIMUM, h_init=h_init)
-
-    temp_storage_bytes = reducer(
-        temp_storage=None,
-        d_in=d_in,
-        d_out=d_out,
-        num_items=num_items,
-        op=OpKind.MINIMUM,
-        h_init=h_init,
-    )
-    with alloc_stream:
-        temp_storage = cp.empty(temp_storage_bytes, dtype=np.uint8)
-
-    state.add_element_count(num_items)
-    state.add_global_memory_reads(num_items * d_in.dtype.itemsize, "Size")
-    state.add_global_memory_writes(d_out.dtype.itemsize)
-
-    def launcher(launch: bench.Launch):
-        reducer(
-            temp_storage=temp_storage,
-            d_in=d_in,
-            d_out=d_out,
-            num_items=num_items,
-            op=OpKind.MINIMUM,
-            h_init=h_init,
-            stream=launch.get_stream(),
-        )
-
-    state.exec(launcher, batched=False)
-
-
-if __name__ == "__main__":
-    b = bench.register(bench_reduce_min)
-    b.set_name("base")
-
-    b.add_string_axis("T{ct}", list(TYPE_MAP.keys()))
-    b.add_int64_power_of_two_axis("Elements{io}", range(16, 29, 4))
-
-    bench.run_all_benchmarks(sys.argv)

cccl_upstream/python/cuda_cccl/benchmarks/compute/reduce/nondeterministic.py

@@ -1,87 +0,0 @@
-# Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. ALL RIGHTS RESERVED.
-#
-# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
-
-"""
-Python benchmark for nondeterministic reduce sum using cuda.compute.reduce_into.
-
-C++ equivalent: cub/benchmarks/bench/reduce/nondeterministic.cu
-
-Notes:
-- Uses Determinism.NOT_GUARANTEED
-- C++ tests int32, int64, float, double
-- Migration: Python fixes offsets; C++ exposes an OffsetT axis.
-- OffsetT axis is omitted because the Python API does not expose offset type.
-"""
-
-import sys
-from pathlib import Path
-
-sys.path.insert(0, str(Path(__file__).parent.parent))
-
-import cupy as cp
-import numpy as np
-from utils import ALL_TYPES as _ALL_TYPES
-from utils import as_cupy_stream, generate_data_with_entropy
-
-import cuda.bench as bench
-from cuda.compute import Determinism, OpKind, make_reduce_into
-
-TYPE_MAP = {k: _ALL_TYPES[k] for k in ("I32", "I64", "F32", "F64")}
-
-
-def bench_reduce_nondeterministic(state: bench.State):
-    type_str = state.get_string("T{ct}")
-    dtype = TYPE_MAP[type_str]
-    num_items = int(state.get_int64("Elements{io}"))
-
-    alloc_stream = as_cupy_stream(state.get_stream())
-    with alloc_stream:
-        d_in = generate_data_with_entropy(num_items, dtype, "1.000", alloc_stream)
-        d_out = cp.empty(1, dtype=dtype)
-
-    h_init = np.zeros(1, dtype=dtype)
-
-    reducer = make_reduce_into(
-        d_in=d_in,
-        d_out=d_out,
-        op=OpKind.PLUS,
-        h_init=h_init,
-        determinism=Determinism.NOT_GUARANTEED,
-    )
-
-    temp_storage_bytes = reducer(
-        temp_storage=None,
-        d_in=d_in,
-        d_out=d_out,
-        num_items=num_items,
-        op=OpKind.PLUS,
-        h_init=h_init,
-    )
-    with alloc_stream:
-        temp_storage = cp.empty(temp_storage_bytes, dtype=np.uint8)
-
-    state.add_element_count(num_items)
-    state.add_global_memory_reads(num_items * d_in.dtype.itemsize, "Size")
-    state.add_global_memory_writes(1 * d_out.dtype.itemsize)
-
-    def launcher(launch: bench.Launch):
-        reducer(
-            temp_storage=temp_storage,
-            d_in=d_in,
-            d_out=d_out,
-            num_items=num_items,
-            op=OpKind.PLUS,
-            h_init=h_init,
-            stream=launch.get_stream(),
-        )
-
-    state.exec(launcher, batched=False)
-
-
-if __name__ == "__main__":
-    b = bench.register(bench_reduce_nondeterministic)
-    b.set_name("base")
-    b.add_string_axis("T{ct}", list(TYPE_MAP.keys()))
-    b.add_int64_power_of_two_axis("Elements{io}", range(16, 29, 4))
-    bench.run_all_benchmarks(sys.argv)

cccl_upstream/python/cuda_cccl/benchmarks/compute/reduce/sum.py

@@ -1,80 +0,0 @@
-# Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. ALL RIGHTS RESERVED.
-#
-# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
-
-"""
-Python benchmark for reduce sum operation using cuda.compute.reduce_into.
-
-C++ equivalent: cub/benchmarks/bench/reduce/sum.cu
-
-Notes:
-- int128 and complex32 are not supported by cupy
-- Migration: Python excludes int128/complex; C++ supports more types/tuning.
-"""
-
-import sys
-from pathlib import Path
-
-sys.path.insert(0, str(Path(__file__).parent.parent))
-
-import cupy as cp
-import numpy as np
-from utils import SIGNED_TYPES as TYPE_MAP
-from utils import as_cupy_stream, generate_data_with_entropy
-
-import cuda.bench as bench
-from cuda.compute import OpKind, make_reduce_into
-
-
-def bench_reduce_sum(state: bench.State):
-    type_str = state.get_string("T{ct}")
-    dtype = TYPE_MAP[type_str]
-    num_items = int(state.get_int64("Elements{io}"))
-
-    alloc_stream = as_cupy_stream(state.get_stream())
-    with alloc_stream:
-        d_in = generate_data_with_entropy(num_items, dtype, "1.000", alloc_stream)
-        d_out = cp.empty(1, dtype=dtype)
-
-    # Initial value for reduction
-    h_init = np.zeros(1, dtype=dtype)
-
-    reducer = make_reduce_into(d_in=d_in, d_out=d_out, op=OpKind.PLUS, h_init=h_init)
-
-    temp_storage_bytes = reducer(
-        temp_storage=None,
-        d_in=d_in,
-        d_out=d_out,
-        num_items=num_items,
-        op=OpKind.PLUS,
-        h_init=h_init,
-    )
-    with alloc_stream:
-        temp_storage = cp.empty(temp_storage_bytes, dtype=np.uint8)
-
-    state.add_element_count(num_items)
-    state.add_global_memory_reads(num_items * d_in.dtype.itemsize, "Size")
-    state.add_global_memory_writes(d_out.dtype.itemsize)
-
-    def launcher(launch: bench.Launch):
-        reducer(
-            temp_storage=temp_storage,
-            d_in=d_in,
-            d_out=d_out,
-            num_items=num_items,
-            op=OpKind.PLUS,
-            h_init=h_init,
-            stream=launch.get_stream(),
-        )
-
-    state.exec(launcher, batched=False)
-
-
-if __name__ == "__main__":
-    b = bench.register(bench_reduce_sum)
-    b.set_name("base")
-
-    b.add_string_axis("T{ct}", list(TYPE_MAP.keys()))
-    b.add_int64_power_of_two_axis("Elements{io}", range(16, 29, 4))
-
-    bench.run_all_benchmarks(sys.argv)