mirror of
https://gitlab.com/libeigen/eigen.git
synced 2026-04-10 11:34:33 +08:00
bug #1652: implements a much more accurate version of vectorized sin/cos. This new version achieve same speed for SSE/AVX, and is slightly faster with FMA. Guarantees are as follows:
- no FMA: 1ULP up to 3pi, 2ULP up to sin(25966) and cos(18838), fallback to std::sin/cos for larger inputs - FMA: 1ULP up to sin(117435.992) and cos(71476.0625), fallback to std::sin/cos for larger inputs
This commit is contained in:
@@ -812,6 +812,17 @@ template<> EIGEN_STRONG_INLINE int predux_max<Packet4i>(const Packet4i& a)
|
||||
#endif // EIGEN_VECTORIZE_SSE4_1
|
||||
}
|
||||
|
||||
// not needed yet
|
||||
// template<> EIGEN_STRONG_INLINE bool predux_all(const Packet4f& x)
|
||||
// {
|
||||
// return _mm_movemask_ps(x) == 0xF;
|
||||
// }
|
||||
|
||||
template<> EIGEN_STRONG_INLINE bool predux_any(const Packet4f& x)
|
||||
{
|
||||
return _mm_movemask_ps(x) != 0x0;
|
||||
}
|
||||
|
||||
#if EIGEN_COMP_GNUC
|
||||
// template <> EIGEN_STRONG_INLINE Packet4f pmadd(const Packet4f& a, const Packet4f& b, const Packet4f& c)
|
||||
// {
|
||||
|
||||
Reference in New Issue
Block a user