GitHub-Proxy/eigen
1
0
Fork 0
mirror of https://gitlab.com/libeigen/eigen.git synced 2025-08-12 03:39:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix alignment in ploadquad

Browse Source
This commit is contained in:
Gael Guennebaud 2019-02-22 21:39:36 +01:00
parent 0cb4ba98e7
commit 0b25a5c431
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Eigen/src/Core/arch/AVX512/PacketMath.h
View File

@ -526,7 +526,7 @@ EIGEN_STRONG_INLINE Packet8d ploaddup<Packet8d>(const double* from) {
// {a0, a0 a0, a0, a1, a1, a1, a1, a2, a2, a2, a2, a3, a3, a3, a3} // {a0, a0 a0, a0, a1, a1, a1, a1, a2, a2, a2, a2, a3, a3, a3, a3}
template <> template <>
EIGEN_STRONG_INLINE Packet16f ploadquad<Packet16f>(const float* from) { EIGEN_STRONG_INLINE Packet16f ploadquad<Packet16f>(const float* from) {
Packet16f tmp = _mm512_castps128_ps512(pload<Packet4f>(from)); Packet16f tmp = _mm512_castps128_ps512(ploadu<Packet4f>(from));
const Packet16i scatter_mask = _mm512_set_epi32(3,3,3,3, 2,2,2,2, 1,1,1,1, 0,0,0,0); const Packet16i scatter_mask = _mm512_set_epi32(3,3,3,3, 2,2,2,2, 1,1,1,1, 0,0,0,0);
return _mm512_permutexvar_ps(scatter_mask, tmp); return _mm512_permutexvar_ps(scatter_mask, tmp);
} }