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
44 lines
1.4 KiB
C++
44 lines
1.4 KiB
C++
//===----------------------------------------------------------------------===//
|
|
//
|
|
// Part of the LLVM Project, 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___EXECUTION_POLICY_H
|
|
#define _CUDA___EXECUTION_POLICY_H
|
|
|
|
#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
|
|
|
|
#if _CCCL_HAS_BACKEND_CUDA()
|
|
|
|
# include <cuda/std/__execution/policy.h>
|
|
|
|
# include <cuda/std/__cccl/prologue.h>
|
|
|
|
_CCCL_BEGIN_NAMESPACE_CUDA_EXECUTION
|
|
|
|
using __cub_parallel_unsequenced_policy =
|
|
::cuda::std::execution::__execution_policy_base<::cuda::std::execution::__with_backend<
|
|
static_cast<uint32_t>(::cuda::std::execution::__execution_policy::__parallel_unsequenced),
|
|
::cuda::std::execution::__execution_backend::__cuda>()>;
|
|
_CCCL_GLOBAL_CONSTANT __cub_parallel_unsequenced_policy gpu{};
|
|
|
|
_CCCL_END_NAMESPACE_CUDA_EXECUTION
|
|
|
|
# include <cuda/std/__cccl/epilogue.h>
|
|
|
|
#endif // _CCCL_HAS_BACKEND_CUDA()
|
|
|
|
#endif // _CUDA___EXECUTION_POLICY_H
|