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
93 lines
3.6 KiB
Plaintext
93 lines
3.6 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) 2025 NVIDIA CORPORATION & AFFILIATES.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef _CUDA_STD_EXECUTION
|
|
#define _CUDA_STD_EXECUTION
|
|
|
|
#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/__execution/policy.h> // IWYU pragma: export
|
|
#include <cuda/std/__execution/env.h> // IWYU pragma: export
|
|
#include <cuda/std/__execution/policy.h> // IWYU pragma: export
|
|
#include <cuda/std/__type_traits/is_execution_policy.h> // IWYU pragma: export
|
|
|
|
// parallel algorithms
|
|
#if _CCCL_HAS_PSTL_BACKEND()
|
|
# include <cuda/std/__pstl/adjacent_difference.h>
|
|
# include <cuda/std/__pstl/adjacent_find.h>
|
|
# include <cuda/std/__pstl/all_of.h>
|
|
# include <cuda/std/__pstl/any_of.h>
|
|
# include <cuda/std/__pstl/copy.h>
|
|
# include <cuda/std/__pstl/copy_if.h>
|
|
# include <cuda/std/__pstl/copy_n.h>
|
|
# include <cuda/std/__pstl/count.h>
|
|
# include <cuda/std/__pstl/count_if.h>
|
|
# include <cuda/std/__pstl/equal.h>
|
|
# include <cuda/std/__pstl/exclusive_scan.h>
|
|
# include <cuda/std/__pstl/fill.h>
|
|
# include <cuda/std/__pstl/fill_n.h>
|
|
# include <cuda/std/__pstl/find.h>
|
|
# include <cuda/std/__pstl/find_if.h>
|
|
# include <cuda/std/__pstl/find_if_not.h>
|
|
# include <cuda/std/__pstl/for_each.h>
|
|
# include <cuda/std/__pstl/for_each_n.h>
|
|
# include <cuda/std/__pstl/generate.h>
|
|
# include <cuda/std/__pstl/generate_n.h>
|
|
# include <cuda/std/__pstl/inclusive_scan.h>
|
|
# include <cuda/std/__pstl/is_heap.h>
|
|
# include <cuda/std/__pstl/is_heap_until.h>
|
|
# include <cuda/std/__pstl/is_partitioned.h>
|
|
# include <cuda/std/__pstl/is_sorted.h>
|
|
# include <cuda/std/__pstl/is_sorted_until.h>
|
|
# include <cuda/std/__pstl/max_element.h>
|
|
# include <cuda/std/__pstl/merge.h>
|
|
# include <cuda/std/__pstl/min_element.h>
|
|
# include <cuda/std/__pstl/mismatch.h>
|
|
# include <cuda/std/__pstl/none_of.h>
|
|
# include <cuda/std/__pstl/partition.h>
|
|
# include <cuda/std/__pstl/partition_copy.h>
|
|
# include <cuda/std/__pstl/reduce.h>
|
|
# include <cuda/std/__pstl/remove.h>
|
|
# include <cuda/std/__pstl/remove_copy.h>
|
|
# include <cuda/std/__pstl/remove_copy_if.h>
|
|
# include <cuda/std/__pstl/remove_if.h>
|
|
# include <cuda/std/__pstl/replace.h>
|
|
# include <cuda/std/__pstl/replace_copy.h>
|
|
# include <cuda/std/__pstl/replace_copy_if.h>
|
|
# include <cuda/std/__pstl/replace_if.h>
|
|
# include <cuda/std/__pstl/reverse.h>
|
|
# include <cuda/std/__pstl/reverse_copy.h>
|
|
# include <cuda/std/__pstl/rotate.h>
|
|
# include <cuda/std/__pstl/rotate_copy.h>
|
|
# include <cuda/std/__pstl/shift_left.h>
|
|
# include <cuda/std/__pstl/shift_right.h>
|
|
# include <cuda/std/__pstl/sort.h>
|
|
# include <cuda/std/__pstl/stable_partition.h>
|
|
# include <cuda/std/__pstl/swap_ranges.h>
|
|
# include <cuda/std/__pstl/transform.h>
|
|
# include <cuda/std/__pstl/transform_exclusive_scan.h>
|
|
# include <cuda/std/__pstl/transform_inclusive_scan.h>
|
|
# include <cuda/std/__pstl/transform_reduce.h>
|
|
# include <cuda/std/__pstl/unique.h>
|
|
# include <cuda/std/__pstl/unique_copy.h>
|
|
#endif // _CCCL_HAS_PSTL_BACKEND
|
|
|
|
#include <cuda/std/version>
|
|
|
|
#endif //_CUDA_STD_EXECUTION
|