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

New gebp kernel handling up to 3 packets x 4 register-level blocks. Huge speeup on Haswell.

Browse Source 
This changeset also introduce new vector functions: ploadquad and predux4.
This commit is contained in:
Gael Guennebaud
2014-04-16 17:05:11 +02:00
parent feaf7c7e6d
commit d5a795f673
12 changed files with 1064 additions and 633 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
Eigen/src/Core/arch/SSE/Complex.h
View File

@@ -49,7 +49,7 @@ template<> struct packet_traits<std::complex<float> > : default_packet_traits
};
#endif
template<> struct unpacket_traits<Packet2cf> { typedef std::complex<float> type; enum {size=2}; };
template<> struct unpacket_traits<Packet2cf> { typedef std::complex<float> type; enum {size=2}; typedef Packet2cf half; };
template<> EIGEN_STRONG_INLINE Packet2cf padd<Packet2cf>(const Packet2cf& a, const Packet2cf& b) { return Packet2cf(_mm_add_ps(a.v,b.v)); }
template<> EIGEN_STRONG_INLINE Packet2cf psub<Packet2cf>(const Packet2cf& a, const Packet2cf& b) { return Packet2cf(_mm_sub_ps(a.v,b.v)); }
@@ -296,7 +296,7 @@ template<> struct packet_traits<std::complex<double> > : default_packet_traits
};
#endif
template<> struct unpacket_traits<Packet1cd> { typedef std::complex<double> type; enum {size=1}; };
template<> struct unpacket_traits<Packet1cd> { typedef std::complex<double> type; enum {size=1}; typedef Packet1cd half; };
template<> EIGEN_STRONG_INLINE Packet1cd padd<Packet1cd>(const Packet1cd& a, const Packet1cd& b) { return Packet1cd(_mm_add_pd(a.v,b.v)); }
template<> EIGEN_STRONG_INLINE Packet1cd psub<Packet1cd>(const Packet1cd& a, const Packet1cd& b) { return Packet1cd(_mm_sub_pd(a.v,b.v)); }

6
Eigen/src/Core/arch/SSE/PacketMath.h
View File

@@ -107,9 +107,9 @@ template<> struct packet_traits<int> : default_packet_traits
};
};
template<> struct unpacket_traits<Packet4f> { typedef float type; enum {size=4}; };
template<> struct unpacket_traits<Packet2d> { typedef double type; enum {size=2}; };
template<> struct unpacket_traits<Packet4i> { typedef int type; enum {size=4}; };
template<> struct unpacket_traits<Packet4f> { typedef float type; enum {size=4}; typedef Packet4f half; };
template<> struct unpacket_traits<Packet2d> { typedef double type; enum {size=2}; typedef Packet2d half; };
template<> struct unpacket_traits<Packet4i> { typedef int type; enum {size=4}; typedef Packet4i half; };
#if defined(_MSC_VER) && (_MSC_VER==1500)
// Workaround MSVC 9 internal compiler error.