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
72 lines
2.8 KiB
Plaintext
72 lines
2.8 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) 2024 NVIDIA CORPORATION & AFFILIATES.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef _CUDA_STD_ITERATOR
|
|
#define _CUDA_STD_ITERATOR
|
|
|
|
#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/__fwd/string.h>
|
|
#include <cuda/std/__iterator/access.h>
|
|
#include <cuda/std/__iterator/advance.h>
|
|
#include <cuda/std/__iterator/back_insert_iterator.h>
|
|
#include <cuda/std/__iterator/bounded_iter.h>
|
|
#include <cuda/std/__iterator/common_iterator.h>
|
|
#include <cuda/std/__iterator/concepts.h>
|
|
#include <cuda/std/__iterator/counted_iterator.h>
|
|
#include <cuda/std/__iterator/data.h>
|
|
#include <cuda/std/__iterator/default_sentinel.h>
|
|
#include <cuda/std/__iterator/distance.h>
|
|
#include <cuda/std/__iterator/empty.h>
|
|
#include <cuda/std/__iterator/erase_if_container.h>
|
|
#include <cuda/std/__iterator/front_insert_iterator.h>
|
|
#include <cuda/std/__iterator/incrementable_traits.h>
|
|
#include <cuda/std/__iterator/indirectly_comparable.h>
|
|
#include <cuda/std/__iterator/insert_iterator.h>
|
|
#include <cuda/std/__iterator/istream_iterator.h>
|
|
#include <cuda/std/__iterator/istreambuf_iterator.h>
|
|
#include <cuda/std/__iterator/iter_move.h>
|
|
#include <cuda/std/__iterator/iter_swap.h>
|
|
#include <cuda/std/__iterator/iterator.h>
|
|
#include <cuda/std/__iterator/iterator_traits.h>
|
|
#include <cuda/std/__iterator/mergeable.h>
|
|
#include <cuda/std/__iterator/move_iterator.h>
|
|
#include <cuda/std/__iterator/move_sentinel.h>
|
|
#include <cuda/std/__iterator/next.h>
|
|
#include <cuda/std/__iterator/ostream_iterator.h>
|
|
#include <cuda/std/__iterator/ostreambuf_iterator.h>
|
|
#include <cuda/std/__iterator/permutable.h>
|
|
#include <cuda/std/__iterator/prev.h>
|
|
#include <cuda/std/__iterator/projected.h>
|
|
#include <cuda/std/__iterator/readable_traits.h>
|
|
#include <cuda/std/__iterator/reverse_access.h>
|
|
#include <cuda/std/__iterator/reverse_iterator.h>
|
|
#include <cuda/std/__iterator/size.h>
|
|
#include <cuda/std/__iterator/sortable.h>
|
|
#include <cuda/std/__iterator/unreachable_sentinel.h>
|
|
#include <cuda/std/__iterator/wrap_iter.h>
|
|
#include <cuda/std/version>
|
|
|
|
// Mandated by the Standard.
|
|
#if _LIBCUDACXX_HAS_SPACESHIP_OPERATOR()
|
|
# include <cuda/std/detail/libcxx/include/compare>
|
|
#endif // _LIBCUDACXX_HAS_SPACESHIP_OPERATOR()
|
|
#include <cuda/std/concepts>
|
|
|
|
#endif // _CUDA_STD_ITERATOR
|