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
75 lines
2.4 KiB
C++
75 lines
2.4 KiB
C++
//===----------------------------------------------------------------------===//
|
|
//
|
|
// 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___CMATH_POW2_H
|
|
#define _CUDA___CMATH_POW2_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
|
|
|
|
#include <cuda/std/__bit/has_single_bit.h>
|
|
#include <cuda/std/__bit/integral.h>
|
|
#include <cuda/std/__type_traits/is_integer.h>
|
|
#include <cuda/std/__type_traits/is_signed.h>
|
|
#include <cuda/std/__type_traits/make_unsigned.h>
|
|
|
|
#include <cuda/std/__cccl/prologue.h>
|
|
|
|
_CCCL_BEGIN_NAMESPACE_CUDA
|
|
|
|
_CCCL_TEMPLATE(typename _Tp)
|
|
_CCCL_REQUIRES(::cuda::std::__cccl_is_integer_v<_Tp>)
|
|
[[nodiscard]] _CCCL_API constexpr bool is_power_of_two(_Tp __t) noexcept
|
|
{
|
|
if constexpr (::cuda::std::is_signed_v<_Tp>)
|
|
{
|
|
_CCCL_ASSERT(__t >= _Tp{0}, "cuda::is_power_of_two requires non-negative input");
|
|
}
|
|
using _Up = ::cuda::std::make_unsigned_t<_Tp>;
|
|
return ::cuda::std::has_single_bit(static_cast<_Up>(__t));
|
|
}
|
|
|
|
_CCCL_TEMPLATE(typename _Tp)
|
|
_CCCL_REQUIRES(::cuda::std::__cccl_is_integer_v<_Tp>)
|
|
[[nodiscard]] _CCCL_API constexpr _Tp next_power_of_two(_Tp __t) noexcept
|
|
{
|
|
if constexpr (::cuda::std::is_signed_v<_Tp>)
|
|
{
|
|
_CCCL_ASSERT(__t >= _Tp{0}, "cuda::is_power_of_two requires non-negative input");
|
|
}
|
|
using _Up = ::cuda::std::make_unsigned_t<_Tp>;
|
|
return ::cuda::std::bit_ceil(static_cast<_Up>(__t));
|
|
}
|
|
|
|
_CCCL_TEMPLATE(typename _Tp)
|
|
_CCCL_REQUIRES(::cuda::std::__cccl_is_integer_v<_Tp>)
|
|
[[nodiscard]] _CCCL_API constexpr _Tp prev_power_of_two(_Tp __t) noexcept
|
|
{
|
|
if constexpr (::cuda::std::is_signed_v<_Tp>)
|
|
{
|
|
_CCCL_ASSERT(__t >= _Tp{0}, "cuda::is_power_of_two requires non-negative input");
|
|
}
|
|
using _Up = ::cuda::std::make_unsigned_t<_Tp>;
|
|
return ::cuda::std::bit_floor(static_cast<_Up>(__t));
|
|
}
|
|
|
|
_CCCL_END_NAMESPACE_CUDA
|
|
|
|
#include <cuda/std/__cccl/epilogue.h>
|
|
|
|
#endif // _CUDA___CMATH_POW2_H
|