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
70 lines
2.4 KiB
Plaintext
70 lines
2.4 KiB
Plaintext
//===----------------------------------------------------------------------===//
|
|
//
|
|
// 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_STD_RANGES
|
|
#define _CUDA_STD_RANGES
|
|
|
|
#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/__ranges/access.h>
|
|
#include <cuda/std/__ranges/all.h>
|
|
#include <cuda/std/__ranges/common_view.h>
|
|
#include <cuda/std/__ranges/concepts.h>
|
|
#include <cuda/std/__ranges/counted.h>
|
|
#include <cuda/std/__ranges/dangling.h>
|
|
#include <cuda/std/__ranges/data.h>
|
|
#include <cuda/std/__ranges/drop_view.h>
|
|
#include <cuda/std/__ranges/drop_while_view.h>
|
|
#include <cuda/std/__ranges/empty.h>
|
|
#include <cuda/std/__ranges/empty_view.h>
|
|
#include <cuda/std/__ranges/enable_borrowed_range.h>
|
|
#include <cuda/std/__ranges/enable_view.h>
|
|
#include <cuda/std/__ranges/filter_view.h>
|
|
#include <cuda/std/__ranges/iota_view.h>
|
|
#include <cuda/std/__ranges/owning_view.h>
|
|
#include <cuda/std/__ranges/rbegin.h>
|
|
#include <cuda/std/__ranges/ref_view.h>
|
|
#include <cuda/std/__ranges/rend.h>
|
|
#include <cuda/std/__ranges/repeat_view.h>
|
|
#include <cuda/std/__ranges/reverse_view.h>
|
|
#include <cuda/std/__ranges/single_view.h>
|
|
#include <cuda/std/__ranges/size.h>
|
|
#include <cuda/std/__ranges/subrange.h>
|
|
#include <cuda/std/__ranges/take_view.h>
|
|
#include <cuda/std/__ranges/take_while_view.h>
|
|
#include <cuda/std/__ranges/transform_view.h>
|
|
#include <cuda/std/__ranges/view_interface.h>
|
|
#include <cuda/std/__ranges/views.h>
|
|
#include <cuda/std/__ranges/zip_view.h>
|
|
|
|
// standard-mandated includes
|
|
#include <cuda/std/version>
|
|
|
|
// [ranges.syn]
|
|
#if _LIBCUDACXX_HAS_SPACESHIP_OPERATOR()
|
|
# include <cuda/std/compare>
|
|
#endif // _LIBCUDACXX_HAS_SPACESHIP_OPERATOR()
|
|
#include <cuda/std/initializer_list>
|
|
#include <cuda/std/iterator>
|
|
|
|
// [tuple.helper]
|
|
#include <cuda/std/__tuple_dir/tuple_element.h>
|
|
#include <cuda/std/__tuple_dir/tuple_size.h>
|
|
|
|
#endif //_CUDA_STD_RANGES
|