[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
This commit is contained in:
muh-bot
2026-08-03 12:39:26 +00:00
parent a2a5dd8f00
commit 24ef6a91b5
5439 changed files with 0 additions and 719516 deletions

View File

@@ -1,110 +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_TESTING_H__
#define __COMMON_TESTING_H__
#include <cuda/__cccl_config>
#include <cuda/__driver/driver_api.h>
#include <cuda/std/__exception/terminate.h>
#include <nv/target>
#include <exception> // IWYU pragma: keep
#include <iostream>
#include <sstream>
#include <c2h/catch2_test_helper.h>
namespace cuda::experimental::execution
{
}
namespace cudax = cuda::experimental; // NOLINT: misc-unused-alias-decls
namespace cudax_async = cuda::experimental::execution; // NOLINT: misc-unused-alias-decls
__host__ __device__ constexpr bool operator==(const dim3& lhs, const dim3& rhs) noexcept
{
return (lhs.x == rhs.x) && (lhs.y == rhs.y) && (lhs.z == rhs.z);
}
namespace Catch
{
template <>
struct StringMaker<dim3>
{
static std::string convert(dim3 const& dims)
{
std::ostringstream oss;
oss << "(" << dims.x << ", " << dims.y << ", " << dims.z << ")";
return oss.str();
}
};
} // namespace Catch
namespace
{
namespace test
{
inline int count_driver_stack()
{
if (cuda::__driver::__ctxGetCurrent() != nullptr)
{
auto ctx = cuda::__driver::__ctxPop();
auto result = 1 + count_driver_stack();
cuda::__driver::__ctxPush(ctx);
return result;
}
else
{
return 0;
}
}
inline void empty_driver_stack()
{
while (cuda::__driver::__ctxGetCurrent() != nullptr)
{
cuda::__driver::__ctxPop();
}
}
inline int cuda_driver_version()
{
return cuda::__driver::__getVersion();
}
// Needs to be a template because we use template catch2 macro
template <typename Dummy = void>
struct ccclrt_test_fixture
{
ccclrt_test_fixture()
{
empty_driver_stack();
}
~ccclrt_test_fixture()
{
CHECK(count_driver_stack() == 0);
}
};
} // namespace test
} // namespace
// Test macro that should be used in all cccl-rt tests
// It first empties the driver stack in case some other test has left it non-empty
// and then runs the test. At the end it checks if it remained empty, which ensures
// we don't accidentally initialize device 0 through REQUIRE_CUDART usage and makes sure
// our APIs work with empty driver stack.
#define C2H_CCCLRT_TEST(NAME, TAGS, ...) C2H_TEST_WITH_FIXTURE(::test::ccclrt_test_fixture, NAME, TAGS, __VA_ARGS__)
#define C2H_CCCLRT_TEST_LIST(NAME, TAGS, ...) \
C2H_TEST_LIST_WITH_FIXTURE(::test::ccclrt_test_fixture, NAME, TAGS, __VA_ARGS__)
#endif // __COMMON_TESTING_H__