diff options
Diffstat (limited to 'Eigen/src/Core/arch/NEON/PacketMath.h')
| -rw-r--r-- | Eigen/src/Core/arch/NEON/PacketMath.h | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/Eigen/src/Core/arch/NEON/PacketMath.h b/Eigen/src/Core/arch/NEON/PacketMath.h index 80ccd261b..2c4b5bfff 100644 --- a/Eigen/src/Core/arch/NEON/PacketMath.h +++ b/Eigen/src/Core/arch/NEON/PacketMath.h @@ -1023,6 +1023,8 @@ template<> EIGEN_STRONG_INLINE Packet2ul pdiv<Packet2ul>(const Packet2ul& /*a*/, // MLA: 10 GFlop/s ; FMA: 12 GFlops/s. template<> EIGEN_STRONG_INLINE Packet4f pmadd(const Packet4f& a, const Packet4f& b, const Packet4f& c) { return vfmaq_f32(c,a,b); } +template<> EIGEN_STRONG_INLINE Packet2f pmadd(const Packet2f& a, const Packet2f& b, const Packet2f& c) +{ return vfma_f32(c,a,b); } #else template<> EIGEN_STRONG_INLINE Packet4f pmadd(const Packet4f& a, const Packet4f& b, const Packet4f& c) { @@ -1046,6 +1048,10 @@ template<> EIGEN_STRONG_INLINE Packet4f pmadd(const Packet4f& a, const Packet4f& return vmlaq_f32(c,a,b); #endif } +template<> EIGEN_STRONG_INLINE Packet2f pmadd(const Packet2f& a, const Packet2f& b, const Packet2f& c) +{ + return vmla_f32(c,a,b); +} #endif // No FMA instruction for int, so use MLA unconditionally. |