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
81 lines
2.2 KiB
C++
81 lines
2.2 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_ISQRT_H
|
|
#define _CUDA___CMATH_ISQRT_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/integral.h>
|
|
#include <cuda/std/__concepts/concept_macros.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
|
|
|
|
//! @brief Returns the square root of the given non-negative integer rounded down
|
|
//! @param __v The input number
|
|
//! @pre \p __v must be an integer type
|
|
//! @pre \p __v must be non-negative
|
|
//! @return The square root of \p __v rounded down
|
|
//! @warning If \p __v is negative, the behavior is undefined
|
|
_CCCL_TEMPLATE(class _Tp)
|
|
_CCCL_REQUIRES(::cuda::std::__cccl_is_integer_v<_Tp>)
|
|
[[nodiscard]] _CCCL_API constexpr _Tp isqrt(_Tp __v) noexcept
|
|
{
|
|
if constexpr (::cuda::std::is_signed_v<_Tp>)
|
|
{
|
|
_CCCL_ASSERT(__v >= _Tp{0}, "cuda::isqrt requires non-negative input");
|
|
}
|
|
|
|
if (__v <= 1)
|
|
{
|
|
return __v;
|
|
}
|
|
|
|
using _Up = ::cuda::std::make_unsigned_t<_Tp>;
|
|
|
|
_Up __uv = static_cast<_Up>(__v);
|
|
_Up __ret{};
|
|
_Up __bit = static_cast<_Up>(_Up{1} << ((::cuda::std::bit_width(__uv) - 1) & (~1)));
|
|
|
|
while (__bit != 0)
|
|
{
|
|
if (__uv >= __ret + __bit)
|
|
{
|
|
__uv -= __ret + __bit;
|
|
__ret = (__ret >> 1) + __bit;
|
|
}
|
|
else
|
|
{
|
|
__ret >>= 1;
|
|
}
|
|
__bit >>= 2;
|
|
}
|
|
return static_cast<_Tp>(__ret);
|
|
}
|
|
|
|
_CCCL_END_NAMESPACE_CUDA
|
|
|
|
#include <cuda/std/__cccl/epilogue.h>
|
|
|
|
#endif // _CUDA___CMATH_ISQRT_H
|