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:
@@ -575,6 +575,16 @@ template<> EIGEN_STRONG_INLINE double predux_max<Packet4d>(const Packet4d& a)
|
||||
return pfirst(_mm256_max_pd(tmp, _mm256_shuffle_pd(tmp, tmp, 1)));
|
||||
}
|
||||
|
||||
// not needed yet
|
||||
// template<> EIGEN_STRONG_INLINE bool predux_all(const Packet8f& x)
|
||||
// {
|
||||
// return _mm256_movemask_ps(x)==0xFF;
|
||||
// }
|
||||
|
||||
template<> EIGEN_STRONG_INLINE bool predux_any(const Packet8f& x)
|
||||
{
|
||||
return _mm256_movemask_ps(x)!=0;
|
||||
}
|
||||
|
||||
template<int Offset>
|
||||
struct palign_impl<Offset,Packet8f>
|
||||
|
||||
Reference in New Issue
Block a user