project_6/cccl_upstream/thrust/examples/include/host_device.h

// SPDX-FileCopyrightText: Copyright (c) 2008-2009, NVIDIA Corporation. All rights reserved.
// SPDX-License-Identifier: Apache-2.0

#pragma once

#include <cuda/__cccl_config>

#if !_CCCL_CUDA_COMPILATION()

#  ifndef __host__
#    define __host__
#  endif

#  ifndef __device__
#    define __device__
#  endif

#endif
[INFRA] Import NVIDIA/CCCL upstream as optimization reference library 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 2026-07-30 09:35:51 +00:00			`// SPDX-FileCopyrightText: Copyright (c) 2008-2009, NVIDIA Corporation. All rights reserved.`
			`// SPDX-License-Identifier: Apache-2.0`

			`#pragma once`

			`#include <cuda/__cccl_config>`

			`#if !_CCCL_CUDA_COMPILATION()`

			`# ifndef __host__`
			`# define __host__`
			`# endif`

			`# ifndef __device__`
			`# define __device__`
			`# endif`

			`#endif`