Files
eigen/Eigen/src/Core/arch/Default/GenericPacketMathFunctionsFwd.h

121 lines
4.0 KiB
C
Raw Normal View History

// This file is part of Eigen, a lightweight C++ template library
// for linear algebra.
//
// Copyright (C) 2019 Gael Guennebaud <gael.guennebaud@inria.fr>
//
// This Source Code Form is subject to the terms of the Mozilla
// Public License v. 2.0. If a copy of the MPL was not distributed
// with this file, You can obtain one at http://mozilla.org/MPL/2.0/.
#ifndef EIGEN_ARCH_GENERIC_PACKET_MATH_FUNCTIONS_FWD_H
#define EIGEN_ARCH_GENERIC_PACKET_MATH_FUNCTIONS_FWD_H
namespace Eigen {
namespace internal {
// Forward declarations of the generic math functions
// implemented in GenericPacketMathFunctions.h
// This is needed to workaround a circular dependency.
/** \internal \returns a packet with constant coefficients \a a, e.g.: (a[N-1],...,a[0]) */
template<typename Packet, int N> EIGEN_DEVICE_FUNC inline Packet
pset(const typename unpacket_traits<Packet>::type (&a)[N] /* a */);
/***************************************************************************
* Some generic implementations to be used by implementors
***************************************************************************/
/** Default implementation of pfrexp for float.
* It is expected to be called by implementers of template<> pfrexp.
*/
template<typename Packet> EIGEN_STRONG_INLINE Packet
pfrexp_float(const Packet& a, Packet& exponent);
/** Default implementation of pfrexp for double.
* It is expected to be called by implementers of template<> pfrexp.
*/
2020-09-15 17:10:35 +00:00
template<typename Packet> EIGEN_STRONG_INLINE Packet
pfrexp_double(const Packet& a, Packet& exponent);
/** Default implementation of pldexp for float.
* It is expected to be called by implementers of template<> pldexp.
*/
template<typename Packet> EIGEN_STRONG_INLINE Packet
pldexp_float(const Packet& a, const Packet& exponent);
/** Default implementation of pldexp for double.
* It is expected to be called by implementers of template<> pldexp.
*/
template<typename Packet> EIGEN_STRONG_INLINE Packet
pldexp_double(const Packet& a, const Packet& exponent);
/** \internal \returns log(x) for single precision float */
template <typename Packet>
EIGEN_DEFINE_FUNCTION_ALLOWING_MULTIPLE_DEFINITIONS
EIGEN_UNUSED
Packet plog_float(const Packet _x);
2020-12-04 21:45:09 +00:00
/** \internal \returns log2(x) for single precision float */
template <typename Packet>
EIGEN_DEFINE_FUNCTION_ALLOWING_MULTIPLE_DEFINITIONS
EIGEN_UNUSED
Packet plog2_float(const Packet _x);
2020-09-15 17:10:35 +00:00
/** \internal \returns log(x) for single precision float */
template <typename Packet>
EIGEN_DEFINE_FUNCTION_ALLOWING_MULTIPLE_DEFINITIONS
EIGEN_UNUSED
Packet plog_double(const Packet _x);
2020-12-04 21:45:09 +00:00
/** \internal \returns log2(x) for single precision float */
template <typename Packet>
EIGEN_DEFINE_FUNCTION_ALLOWING_MULTIPLE_DEFINITIONS
EIGEN_UNUSED
Packet plog2_double(const Packet _x);
/** \internal \returns log(1 + x) */
template<typename Packet>
Packet generic_plog1p(const Packet& x);
/** \internal \returns exp(x)-1 */
template<typename Packet>
Packet generic_expm1(const Packet& x);
/** \internal \returns exp(x) for single precision float */
template <typename Packet>
EIGEN_DEFINE_FUNCTION_ALLOWING_MULTIPLE_DEFINITIONS
EIGEN_UNUSED
Packet pexp_float(const Packet _x);
/** \internal \returns exp(x) for double precision real numbers */
template <typename Packet>
EIGEN_DEFINE_FUNCTION_ALLOWING_MULTIPLE_DEFINITIONS
EIGEN_UNUSED
Packet pexp_double(const Packet _x);
/** \internal \returns sin(x) for single precision float */
template<typename Packet>
EIGEN_DEFINE_FUNCTION_ALLOWING_MULTIPLE_DEFINITIONS
EIGEN_UNUSED
Packet psin_float(const Packet& x);
/** \internal \returns cos(x) for single precision float */
template<typename Packet>
EIGEN_DEFINE_FUNCTION_ALLOWING_MULTIPLE_DEFINITIONS
EIGEN_UNUSED
Packet pcos_float(const Packet& x);
Implement vectorized complex square root. Closes #1905 Measured speedup for sqrt of `complex<float>` on Skylake: SSE: ``` name old time/op new time/op delta BM_eigen_sqrt_ctype/1 49.4ns ± 0% 54.3ns ± 0% +10.01% BM_eigen_sqrt_ctype/8 332ns ± 0% 50ns ± 1% -84.97% BM_eigen_sqrt_ctype/64 2.81µs ± 1% 0.38µs ± 0% -86.49% BM_eigen_sqrt_ctype/512 23.8µs ± 0% 3.0µs ± 0% -87.32% BM_eigen_sqrt_ctype/4k 202µs ± 0% 24µs ± 2% -88.03% BM_eigen_sqrt_ctype/32k 1.63ms ± 0% 0.19ms ± 0% -88.18% BM_eigen_sqrt_ctype/256k 13.0ms ± 0% 1.5ms ± 1% -88.20% BM_eigen_sqrt_ctype/1M 52.1ms ± 0% 6.2ms ± 0% -88.18% ``` AVX2: ``` name old cpu/op new cpu/op delta BM_eigen_sqrt_ctype/1 53.6ns ± 0% 55.6ns ± 0% +3.71% BM_eigen_sqrt_ctype/8 334ns ± 0% 27ns ± 0% -91.86% BM_eigen_sqrt_ctype/64 2.79µs ± 0% 0.22µs ± 2% -92.28% BM_eigen_sqrt_ctype/512 23.8µs ± 1% 1.7µs ± 1% -92.81% BM_eigen_sqrt_ctype/4k 201µs ± 0% 14µs ± 1% -93.24% BM_eigen_sqrt_ctype/32k 1.62ms ± 0% 0.11ms ± 1% -93.29% BM_eigen_sqrt_ctype/256k 13.0ms ± 0% 0.9ms ± 1% -93.31% BM_eigen_sqrt_ctype/1M 52.0ms ± 0% 3.5ms ± 1% -93.31% ``` AVX512: ``` name old cpu/op new cpu/op delta BM_eigen_sqrt_ctype/1 53.7ns ± 0% 56.2ns ± 1% +4.75% BM_eigen_sqrt_ctype/8 334ns ± 0% 18ns ± 2% -94.63% BM_eigen_sqrt_ctype/64 2.79µs ± 0% 0.12µs ± 1% -95.54% BM_eigen_sqrt_ctype/512 23.9µs ± 1% 1.0µs ± 1% -95.89% BM_eigen_sqrt_ctype/4k 202µs ± 0% 8µs ± 1% -96.13% BM_eigen_sqrt_ctype/32k 1.63ms ± 0% 0.06ms ± 1% -96.15% BM_eigen_sqrt_ctype/256k 13.0ms ± 0% 0.5ms ± 4% -96.11% BM_eigen_sqrt_ctype/1M 52.1ms ± 0% 2.0ms ± 1% -96.13% ```
2020-12-08 18:13:35 -08:00
/** \internal \returns sqrt(x) for complex types */
template<typename Packet>
EIGEN_DEFINE_FUNCTION_ALLOWING_MULTIPLE_DEFINITIONS
EIGEN_UNUSED
Packet psqrt_complex(const Packet& a);
template <typename Packet, int N> struct ppolevl;
Implement vectorized complex square root. Closes #1905 Measured speedup for sqrt of `complex<float>` on Skylake: SSE: ``` name old time/op new time/op delta BM_eigen_sqrt_ctype/1 49.4ns ± 0% 54.3ns ± 0% +10.01% BM_eigen_sqrt_ctype/8 332ns ± 0% 50ns ± 1% -84.97% BM_eigen_sqrt_ctype/64 2.81µs ± 1% 0.38µs ± 0% -86.49% BM_eigen_sqrt_ctype/512 23.8µs ± 0% 3.0µs ± 0% -87.32% BM_eigen_sqrt_ctype/4k 202µs ± 0% 24µs ± 2% -88.03% BM_eigen_sqrt_ctype/32k 1.63ms ± 0% 0.19ms ± 0% -88.18% BM_eigen_sqrt_ctype/256k 13.0ms ± 0% 1.5ms ± 1% -88.20% BM_eigen_sqrt_ctype/1M 52.1ms ± 0% 6.2ms ± 0% -88.18% ``` AVX2: ``` name old cpu/op new cpu/op delta BM_eigen_sqrt_ctype/1 53.6ns ± 0% 55.6ns ± 0% +3.71% BM_eigen_sqrt_ctype/8 334ns ± 0% 27ns ± 0% -91.86% BM_eigen_sqrt_ctype/64 2.79µs ± 0% 0.22µs ± 2% -92.28% BM_eigen_sqrt_ctype/512 23.8µs ± 1% 1.7µs ± 1% -92.81% BM_eigen_sqrt_ctype/4k 201µs ± 0% 14µs ± 1% -93.24% BM_eigen_sqrt_ctype/32k 1.62ms ± 0% 0.11ms ± 1% -93.29% BM_eigen_sqrt_ctype/256k 13.0ms ± 0% 0.9ms ± 1% -93.31% BM_eigen_sqrt_ctype/1M 52.0ms ± 0% 3.5ms ± 1% -93.31% ``` AVX512: ``` name old cpu/op new cpu/op delta BM_eigen_sqrt_ctype/1 53.7ns ± 0% 56.2ns ± 1% +4.75% BM_eigen_sqrt_ctype/8 334ns ± 0% 18ns ± 2% -94.63% BM_eigen_sqrt_ctype/64 2.79µs ± 0% 0.12µs ± 1% -95.54% BM_eigen_sqrt_ctype/512 23.9µs ± 1% 1.0µs ± 1% -95.89% BM_eigen_sqrt_ctype/4k 202µs ± 0% 8µs ± 1% -96.13% BM_eigen_sqrt_ctype/32k 1.63ms ± 0% 0.06ms ± 1% -96.15% BM_eigen_sqrt_ctype/256k 13.0ms ± 0% 0.5ms ± 4% -96.11% BM_eigen_sqrt_ctype/1M 52.1ms ± 0% 2.0ms ± 1% -96.13% ```
2020-12-08 18:13:35 -08:00
} // end namespace internal
} // end namespace Eigen
#endif // EIGEN_ARCH_GENERIC_PACKET_MATH_FUNCTIONS_FWD_H