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
32 lines
863 B
C++
32 lines
863 B
C++
// SPDX-FileCopyrightText: Copyright (c) 2025, NVIDIA Corporation. All rights reserved.
|
|
// SPDX-License-Identifier: Apache-2.0
|
|
|
|
#pragma once
|
|
|
|
#include <thrust/detail/config.h>
|
|
|
|
#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/__iterator/distance.h>
|
|
#include <cuda/std/__iterator/iterator_traits.h>
|
|
|
|
THRUST_NAMESPACE_BEGIN
|
|
|
|
//! deprecated [since 3.1]
|
|
|
|
template <class InputIter>
|
|
[[nodiscard]] CCCL_DEPRECATED_BECAUSE("Use cuda::std::distance instead")
|
|
_CCCL_HOST_DEVICE_API constexpr ::cuda::std::iter_difference_t<InputIter>
|
|
distance(InputIter first, InputIter last)
|
|
{
|
|
return ::cuda::std::distance(first, last);
|
|
}
|
|
|
|
THRUST_NAMESPACE_END
|