aboutsummaryrefslogtreecommitdiffhomepage
path: root/Eigen/src/Core/arch/AVX
diff options
context:
space:
mode:
authorGravatar Gustavo Lima Chaves <gustavo.lima.chaves@intel.com>2018-12-19 14:24:44 -0800
committerGravatar Gustavo Lima Chaves <gustavo.lima.chaves@intel.com>2018-12-19 14:24:44 -0800
commite763fcd09e620300226ca22d152b94867123b603 (patch)
tree8f2546814d92e2f460e2b1abe385d96d50e1ef73 /Eigen/src/Core/arch/AVX
parentefa4c9c40fbed9506aaef6a5393d27713f161984 (diff)
Introducing "vectorized" byte on unpacket_traits structs
This is a preparation to a change on gebp_traits, where a new template argument will be introduced to dictate the packet size, so it won't be bound to the current/max packet size only anymore. By having packet types defined early on gebp_traits, one has now to act on packet types, not scalars anymore, for the enum values defined on that class. One approach for reaching the vectorizable/size properties one needs there could be getting the packet's scalar again with unpacket_traits<>, then the size/Vectorizable enum entries from packet_traits<>. It turns out guards like "#ifndef EIGEN_VECTORIZE_AVX512" at AVX/PacketMath.h will hide smaller packet variations of packet_traits<> for some types (and it makes sense to keep that). In other words, one can't go back to the scalar and create a new PacketType, as this will always lead to the maximum packet type for the architecture. The less costly/invasive solution for that, thus, is to add the vectorizable info on every unpacket_traits struct as well.
Diffstat (limited to 'Eigen/src/Core/arch/AVX')
-rw-r--r--Eigen/src/Core/arch/AVX/Complex.h4
-rw-r--r--Eigen/src/Core/arch/AVX/PacketMath.h6
2 files changed, 5 insertions, 5 deletions
diff --git a/Eigen/src/Core/arch/AVX/Complex.h b/Eigen/src/Core/arch/AVX/Complex.h
index 08d021b65..e7e2a1033 100644
--- a/Eigen/src/Core/arch/AVX/Complex.h
+++ b/Eigen/src/Core/arch/AVX/Complex.h
@@ -47,7 +47,7 @@ template<> struct packet_traits<std::complex<float> > : default_packet_traits
};
#endif
-template<> struct unpacket_traits<Packet4cf> { typedef std::complex<float> type; enum {size=4, alignment=Aligned32}; typedef Packet2cf half; };
+template<> struct unpacket_traits<Packet4cf> { typedef std::complex<float> type; enum {size=4, alignment=Aligned32, vectorizable=true}; typedef Packet2cf half; };
template<> EIGEN_STRONG_INLINE Packet4cf padd<Packet4cf>(const Packet4cf& a, const Packet4cf& b) { return Packet4cf(_mm256_add_ps(a.v,b.v)); }
template<> EIGEN_STRONG_INLINE Packet4cf psub<Packet4cf>(const Packet4cf& a, const Packet4cf& b) { return Packet4cf(_mm256_sub_ps(a.v,b.v)); }
@@ -255,7 +255,7 @@ template<> struct packet_traits<std::complex<double> > : default_packet_traits
};
#endif
-template<> struct unpacket_traits<Packet2cd> { typedef std::complex<double> type; enum {size=2, alignment=Aligned32}; typedef Packet1cd half; };
+template<> struct unpacket_traits<Packet2cd> { typedef std::complex<double> type; enum {size=2, alignment=Aligned32, vectorizable=true}; typedef Packet1cd half; };
template<> EIGEN_STRONG_INLINE Packet2cd padd<Packet2cd>(const Packet2cd& a, const Packet2cd& b) { return Packet2cd(_mm256_add_pd(a.v,b.v)); }
template<> EIGEN_STRONG_INLINE Packet2cd psub<Packet2cd>(const Packet2cd& a, const Packet2cd& b) { return Packet2cd(_mm256_sub_pd(a.v,b.v)); }
diff --git a/Eigen/src/Core/arch/AVX/PacketMath.h b/Eigen/src/Core/arch/AVX/PacketMath.h
index e5aeb6375..e771c0f25 100644
--- a/Eigen/src/Core/arch/AVX/PacketMath.h
+++ b/Eigen/src/Core/arch/AVX/PacketMath.h
@@ -117,14 +117,14 @@ template<> struct unpacket_traits<Packet8f> {
typedef float type;
typedef Packet4f half;
typedef Packet8i integer_packet;
- enum {size=8, alignment=Aligned32};
+ enum {size=8, alignment=Aligned32, vectorizable=true};
};
template<> struct unpacket_traits<Packet4d> {
typedef double type;
typedef Packet2d half;
- enum {size=4, alignment=Aligned32};
+ enum {size=4, alignment=Aligned32, vectorizable=true};
};
-template<> struct unpacket_traits<Packet8i> { typedef int type; typedef Packet4i half; enum {size=8, alignment=Aligned32}; };
+template<> struct unpacket_traits<Packet8i> { typedef int type; typedef Packet4i half; enum {size=8, alignment=Aligned32, vectorizable=false}; };
template<> EIGEN_STRONG_INLINE Packet8f pset1<Packet8f>(const float& from) { return _mm256_set1_ps(from); }
template<> EIGEN_STRONG_INLINE Packet4d pset1<Packet4d>(const double& from) { return _mm256_set1_pd(from); }