devtools/eigen
1
0
Fork 0
mirror of https://gitlab.com/libeigen/eigen.git synced 2026-04-10 11:34:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

Switch to truncated casting when converting floating point types to integer. This ensures that vectorized casts are consistent with scalar casts

Browse Source
This commit is contained in:
Benoit Steiner
2015-02-27 09:27:30 -08:00
parent 573b377110
commit 05089aba75
2 changed files with 21 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
Eigen/src/Core/arch/SSE/TypeCasting.h
View File

@@ -24,7 +24,7 @@ struct type_casting_traits<float, int> {
};
template<> EIGEN_STRONG_INLINE Packet4i pcast<Packet4f, Packet4i>(const Packet4f& a) {
return _mm_cvtps_epi32(a);
return _mm_cvttps_epi32(a);
}