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
57 lines
2.2 KiB
Plaintext
57 lines
2.2 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_FUNCTIONAL
|
|
#define _CUDA_STD_FUNCTIONAL
|
|
|
|
#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/__algorithm/max.h>
|
|
#include <cuda/std/__algorithm/min.h>
|
|
#include <cuda/std/__functional/binary_function.h>
|
|
#include <cuda/std/__functional/binary_negate.h>
|
|
#include <cuda/std/__functional/bind.h>
|
|
#include <cuda/std/__functional/bind_back.h>
|
|
#include <cuda/std/__functional/bind_front.h>
|
|
#include <cuda/std/__functional/binder1st.h>
|
|
#include <cuda/std/__functional/binder2nd.h>
|
|
#include <cuda/std/__functional/compose.h>
|
|
#include <cuda/std/__functional/default_searcher.h>
|
|
#include <cuda/std/__functional/function.h>
|
|
#include <cuda/std/__functional/hash.h>
|
|
#include <cuda/std/__functional/identity.h>
|
|
#include <cuda/std/__functional/invoke.h>
|
|
#include <cuda/std/__functional/is_transparent.h>
|
|
#include <cuda/std/__functional/mem_fn.h>
|
|
#include <cuda/std/__functional/mem_fun_ref.h>
|
|
#include <cuda/std/__functional/not_fn.h>
|
|
#include <cuda/std/__functional/operations.h>
|
|
#include <cuda/std/__functional/perfect_forward.h>
|
|
#include <cuda/std/__functional/pointer_to_binary_function.h>
|
|
#include <cuda/std/__functional/pointer_to_unary_function.h>
|
|
#include <cuda/std/__functional/ranges_operations.h>
|
|
#include <cuda/std/__functional/reference_wrapper.h>
|
|
#include <cuda/std/__functional/unary_function.h>
|
|
#include <cuda/std/__functional/unary_negate.h>
|
|
#include <cuda/std/__functional/unwrap_ref.h>
|
|
#include <cuda/std/__functional/weak_result_type.h>
|
|
#include <cuda/std/__fwd/string.h>
|
|
#include <cuda/std/version>
|
|
|
|
#endif // _CUDA_STD_FUNCTIONAL
|