56fd68e7dd
CCCL (CUDA C++ Core Libraries) provides: - CUB: device/block/warp-level GPU primitives (reduce, scan, sort, topk) - Thrust: high-level parallel algorithms (transform_reduce, sort, scan) - libcudacxx: CUDA C++ standard library (atomics, barriers, memory) - cudax: experimental features (memory resources, allocators) - Tuning policies: per-SM hardware-specific algorithm parameters Competition optimization vectors mapped to CCCL: - Output TPS (83% weight): warp_reduce, block_reduce, device_topk - Input TPS (14% weight): device_scan, block_load, prefetch - Cache TPS (3% weight): prefix caching strategy patterns - Memory (0.9 util): pooled/cached/buddy allocators Source: https://github.com/NVIDIA/cccl (shallow clone, HEAD only) License: Apache-2.0
104 lines
2.7 KiB
C++
104 lines
2.7 KiB
C++
//===----------------------------------------------------------------------===//
|
|
//
|
|
// Part of libcu++, the C++ Standard Library for your entire system,
|
|
// 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) 2026 NVIDIA CORPORATION & AFFILIATES.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef _CUDA___FWD_HIERARCHY_H
|
|
#define _CUDA___FWD_HIERARCHY_H
|
|
|
|
#include <cuda/std/detail/__config>
|
|
|
|
#if defined(_CCCL_IMPLICIT_SYSTEM_HEADER_GCC)
|
|
# pragma GCC system_header
|
|
#elif defined(_CCCL_IMPLICIT_SYSTEM_HEADER_CLANG)
|
|
# pragma clang system_header
|
|
#elif defined(_CCCL_IMPLICIT_SYSTEM_HEADER_MSVC)
|
|
# pragma system_header
|
|
#endif // no system header
|
|
|
|
#include <cuda/std/__cstddef/types.h>
|
|
#include <cuda/std/__type_traits/is_base_of.h>
|
|
|
|
#include <cuda/std/__cccl/prologue.h>
|
|
|
|
_CCCL_BEGIN_NAMESPACE_CUDA
|
|
|
|
using dimensions_index_type = unsigned;
|
|
|
|
// hierarchy level
|
|
|
|
template <class _Level>
|
|
struct hierarchy_level_base;
|
|
|
|
template <class _Level>
|
|
struct __native_hierarchy_level_base;
|
|
|
|
struct grid_level;
|
|
struct cluster_level;
|
|
struct block_level;
|
|
struct warp_level;
|
|
struct thread_level;
|
|
|
|
template <class _Tp>
|
|
inline constexpr bool __is_hierarchy_level_v = ::cuda::std::is_base_of_v<hierarchy_level_base<_Tp>, _Tp>;
|
|
|
|
template <class _Tp>
|
|
inline constexpr bool __is_native_hierarchy_level_v =
|
|
::cuda::std::is_base_of_v<__native_hierarchy_level_base<_Tp>, _Tp>;
|
|
|
|
// hierarchy
|
|
|
|
template <class _BottomUnit, class... _Levels>
|
|
class hierarchy;
|
|
|
|
template <class _Tp>
|
|
inline constexpr bool __is_hierarchy_v = false;
|
|
template <class _BottomUnit, class... _Levels>
|
|
inline constexpr bool __is_hierarchy_v<hierarchy<_BottomUnit, _Levels...>> = true;
|
|
|
|
template <typename... _Levels>
|
|
struct __allowed_levels;
|
|
|
|
struct __hierarchy_level_desc_base
|
|
{};
|
|
template <class _Level, class _Exts>
|
|
class hierarchy_level_desc;
|
|
|
|
template <class _Tp>
|
|
inline constexpr bool __is_hierarchy_level_desc_v = ::cuda::std::is_base_of_v<__hierarchy_level_desc_base, _Tp>;
|
|
|
|
template <class _Unit, class _Level>
|
|
struct __extents_query_native;
|
|
|
|
template <class _Unit, class _Level>
|
|
struct __extents_query;
|
|
|
|
template <class _Unit, class _Level>
|
|
struct __count_query_native;
|
|
|
|
template <class _Unit, class _Level>
|
|
struct __count_query;
|
|
|
|
template <class _Unit, class _Level>
|
|
struct __index_query_native;
|
|
|
|
template <class _Unit, class _Level>
|
|
struct __index_query;
|
|
|
|
template <class _Unit, class _Level>
|
|
struct __rank_query_native;
|
|
|
|
template <class _Unit, class _Level>
|
|
struct __rank_query;
|
|
|
|
_CCCL_END_NAMESPACE_CUDA
|
|
|
|
#include <cuda/std/__cccl/epilogue.h>
|
|
|
|
#endif // _CUDA___FWD_HIERARCHY_H
|