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
2.5 KiB
Plaintext
72 lines
2.5 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_UTILITY
|
|
#define _CUDA_STD_UTILITY
|
|
|
|
#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/__functional/binary_function.h>
|
|
#include <cuda/std/__functional/hash.h>
|
|
#include <cuda/std/__functional/reference_wrapper.h>
|
|
#include <cuda/std/__functional/unary_function.h>
|
|
#include <cuda/std/__functional/unwrap_ref.h>
|
|
#include <cuda/std/__functional/weak_result_type.h>
|
|
#include <cuda/std/__fwd/get.h>
|
|
#include <cuda/std/__memory/construct_at.h>
|
|
#include <cuda/std/__utility/as_const.h>
|
|
#include <cuda/std/__utility/auto_cast.h>
|
|
#include <cuda/std/__utility/cmp.h>
|
|
#include <cuda/std/__utility/constant_wrapper.h>
|
|
#include <cuda/std/__utility/convert_to_integral.h>
|
|
#include <cuda/std/__utility/declval.h>
|
|
#include <cuda/std/__utility/exchange.h>
|
|
#include <cuda/std/__utility/forward.h>
|
|
#include <cuda/std/__utility/forward_like.h>
|
|
#include <cuda/std/__utility/in_place.h>
|
|
#include <cuda/std/__utility/integer_sequence.h>
|
|
#include <cuda/std/__utility/monostate.h>
|
|
#include <cuda/std/__utility/move.h>
|
|
#include <cuda/std/__utility/pair.h>
|
|
#include <cuda/std/__utility/piecewise_construct.h>
|
|
#include <cuda/std/__utility/priority_tag.h>
|
|
#include <cuda/std/__utility/rel_ops.h>
|
|
#include <cuda/std/__utility/swap.h>
|
|
#include <cuda/std/__utility/to_underlying.h>
|
|
#include <cuda/std/__utility/unreachable.h>
|
|
#include <cuda/std/limits>
|
|
|
|
// standard-mandated includes
|
|
#include <cuda/std/concepts>
|
|
#include <cuda/std/version>
|
|
|
|
// [utility.syn]
|
|
#if _LIBCUDACXX_HAS_SPACESHIP_OPERATOR()
|
|
# include <cuda/std/compare>
|
|
#endif // _LIBCUDACXX_HAS_SPACESHIP_OPERATOR()
|
|
#include <cuda/std/initializer_list>
|
|
|
|
// [tuple.creation]
|
|
#include <cuda/std/__tuple_dir/ignore.h>
|
|
|
|
// [tuple.helper]
|
|
#include <cuda/std/__tuple_dir/tuple_element.h>
|
|
#include <cuda/std/__tuple_dir/tuple_size.h>
|
|
|
|
#endif // _CUDA_STD_UTILITY
|