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
112 lines
3.3 KiB
C++
112 lines
3.3 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_IPOW_H
|
|
#define _CUDA___CMATH_IPOW_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/__cmath/ilog.h>
|
|
#include <cuda/__cmath/neg.h>
|
|
#include <cuda/__cmath/pow2.h>
|
|
#include <cuda/__cmath/uabs.h>
|
|
#include <cuda/std/__bit/countl.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/is_unsigned.h>
|
|
#include <cuda/std/__type_traits/make_unsigned.h>
|
|
#include <cuda/std/__utility/cmp.h>
|
|
|
|
#include <cuda/std/__cccl/prologue.h>
|
|
|
|
_CCCL_BEGIN_NAMESPACE_CUDA
|
|
|
|
template <class _Tp, class _Ep>
|
|
[[nodiscard]] _CCCL_API constexpr _Tp __cccl_ipow_impl_base_pow2(_Tp __b, _Ep __e) noexcept
|
|
{
|
|
const auto __shift = static_cast<int>(__e - 1) * ::cuda::ilog2(__b);
|
|
const auto __lz = ::cuda::std::countl_zero(__b);
|
|
return (__shift >= __lz) ? _Tp{0} : (_Tp{__b} << __shift);
|
|
}
|
|
|
|
template <class _Tp, class _Ep>
|
|
[[nodiscard]] _CCCL_API constexpr _Tp __cccl_ipow_impl(_Tp __b, _Ep __e) noexcept
|
|
{
|
|
static_assert(::cuda::std::is_unsigned_v<_Tp>);
|
|
|
|
if (::cuda::is_power_of_two(__b))
|
|
{
|
|
return ::cuda::__cccl_ipow_impl_base_pow2(__b, __e);
|
|
}
|
|
|
|
auto __x = __b;
|
|
auto __y = _Tp{1};
|
|
|
|
while (__e > 1)
|
|
{
|
|
if (__e % 2 == 1)
|
|
{
|
|
__y *= __x;
|
|
--__e;
|
|
}
|
|
__x *= __x;
|
|
__e /= 2;
|
|
}
|
|
return __x * __y;
|
|
}
|
|
|
|
//! @brief Computes the integer power of a base to an exponent.
|
|
//! @param __b The base
|
|
//! @param __e The exponent
|
|
//! @pre \p __b must be an integer type
|
|
//! @pre \p __e must be an integer type
|
|
//! @return The result of raising \p __b to the power of \p __e
|
|
//! @note The result is undefined if \p __b is 0 and \p __e is negative.
|
|
_CCCL_TEMPLATE(class _Tp, class _Ep)
|
|
_CCCL_REQUIRES(::cuda::std::__cccl_is_integer_v<_Tp> _CCCL_AND ::cuda::std::__cccl_is_integer_v<_Ep>)
|
|
[[nodiscard]] _CCCL_API constexpr _Tp ipow(_Tp __b, _Ep __e) noexcept
|
|
{
|
|
_CCCL_ASSERT(__b != _Tp{0} || ::cuda::std::cmp_greater_equal(__e, _Ep{0}),
|
|
"cuda::ipow() requires non-negative exponent for base 0");
|
|
|
|
if (__e == _Ep{0} || __b == _Tp{1})
|
|
{
|
|
return _Tp{1};
|
|
}
|
|
else if (::cuda::std::cmp_less(__e, _Ep{0}) || __b == _Tp{0})
|
|
{
|
|
return _Tp{0};
|
|
}
|
|
auto __res = ::cuda::__cccl_ipow_impl(::cuda::uabs(__b), ::cuda::std::__to_unsigned_like(__e));
|
|
if constexpr (::cuda::std::is_signed_v<_Tp>)
|
|
{
|
|
if (__b < _Tp{0} && (__e % 2u == 1))
|
|
{
|
|
__res = cuda::neg(__res);
|
|
}
|
|
}
|
|
return static_cast<_Tp>(__res);
|
|
}
|
|
|
|
_CCCL_END_NAMESPACE_CUDA
|
|
|
|
#include <cuda/std/__cccl/epilogue.h>
|
|
|
|
#endif // _CUDA___CMATH_IPOW_H
|