diff --git a/CMakeLists.txt b/CMakeLists.txt
index 15dbbc4fa..6f027cb44 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -158,7 +158,7 @@ if(CMAKE_COMPILER_IS_GNUCXX)
 
   option(EIGEN_TEST_NEON "Enable/Disable Neon in tests/examples" OFF)
   if(EIGEN_TEST_NEON)
-    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mfloat-abi=hard -mfpu=neon -mcpu=cortex-a8")
+    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mfloat-abi=softfp -mfpu=neon -mcpu=cortex-a8")
     message("Enabling NEON in tests/examples")
   endif()
 
diff --git a/Eigen/src/Core/arch/NEON/Complex.h b/Eigen/src/Core/arch/NEON/Complex.h
index d1943ba3b..7d9e1fc7f 100644
--- a/Eigen/src/Core/arch/NEON/Complex.h
+++ b/Eigen/src/Core/arch/NEON/Complex.h
@@ -73,7 +73,8 @@ template<> EIGEN_STRONG_INLINE Packet2cf psub<Packet2cf>(const Packet2cf& a, con
 template<> EIGEN_STRONG_INLINE Packet2cf pnegate(const Packet2cf& a) { return Packet2cf(pnegate<Packet4f>(a.v)); }
 template<> EIGEN_STRONG_INLINE Packet2cf pconj(const Packet2cf& a)
 {
-  return Packet2cf(vreinterpretq_f32_u32(veorq_u32(vreinterpretq_u32_f32(a.v), p4ui_CONJ_XOR)));
+  Packet4ui b = vreinterpretq_u32_f32(a.v);
+  return Packet2cf(vreinterpretq_f32_u32(veorq_u32(b, p4ui_CONJ_XOR)));
 }
 
 template<> EIGEN_STRONG_INLINE Packet2cf pmul<Packet2cf>(const Packet2cf& a, const Packet2cf& b)
@@ -116,8 +117,8 @@ template<> EIGEN_STRONG_INLINE Packet2cf pandnot<Packet2cf>(const Packet2cf& a,
   return Packet2cf(vreinterpretq_f32_u32(vbicq_u32(vreinterpretq_u32_f32(a.v),vreinterpretq_u32_f32(b.v))));
 }
 
-template<> EIGEN_STRONG_INLINE Packet2cf pload <std::complex<float> >(const std::complex<float>* from) { EIGEN_DEBUG_ALIGNED_LOAD return Packet2cf(pload((const float*)from)); }
-template<> EIGEN_STRONG_INLINE Packet2cf ploadu<std::complex<float> >(const std::complex<float>* from) { EIGEN_DEBUG_UNALIGNED_LOAD return Packet2cf(ploadu((const float*)from)); }
+template<> EIGEN_STRONG_INLINE Packet2cf pload<Packet2cf>(const std::complex<float>* from) { EIGEN_DEBUG_ALIGNED_LOAD return Packet2cf(pload<Packet4f>((const float*)from)); }
+template<> EIGEN_STRONG_INLINE Packet2cf ploadu<Packet2cf>(const std::complex<float>* from) { EIGEN_DEBUG_UNALIGNED_LOAD return Packet2cf(ploadu<Packet4f>((const float*)from)); }
 
 template<> EIGEN_STRONG_INLINE void pstore <std::complex<float> >(std::complex<float> *   to, const Packet2cf& from) { EIGEN_DEBUG_ALIGNED_STORE pstore((float*)to, from.v); }
 template<> EIGEN_STRONG_INLINE void pstoreu<std::complex<float> >(std::complex<float> *   to, const Packet2cf& from) { EIGEN_DEBUG_UNALIGNED_STORE pstoreu((float*)to, from.v); }
@@ -143,7 +144,7 @@ template<> EIGEN_STRONG_INLINE Packet2cf preverse(const Packet2cf& a)
   return Packet2cf(a_r128);
 }
 
-EIGEN_STRONG_INLINE Packet2cf pcplxflip/*<Packet2cf>*/(const Packet2cf& x)
+EIGEN_STRONG_INLINE Packet2cf pcplxflip(const Packet2cf& a)
 {
   return Packet2cf(vrev64q_f32(a.v));
 }
diff --git a/Eigen/src/Core/arch/NEON/PacketMath.h b/Eigen/src/Core/arch/NEON/PacketMath.h
index cae35d737..c09a5a885 100644
--- a/Eigen/src/Core/arch/NEON/PacketMath.h
+++ b/Eigen/src/Core/arch/NEON/PacketMath.h
@@ -45,6 +45,7 @@ namespace internal {
 
 typedef float32x4_t Packet4f;
 typedef int32x4_t   Packet4i;
+typedef uint32x4_t   Packet4ui;
 
 #define _EIGEN_DECLARE_CONST_Packet4f(NAME,X) \
   const Packet4f p4f_##NAME = pset1<Packet4f>(X)
@@ -176,22 +177,22 @@ template<> EIGEN_STRONG_INLINE Packet4f pandnot<Packet4f>(const Packet4f& a, con
 }
 template<> EIGEN_STRONG_INLINE Packet4i pandnot<Packet4i>(const Packet4i& a, const Packet4i& b) { return vbicq_s32(a,b); }
 
-template<> EIGEN_STRONG_INLINE Packet4f pload<float>(const float* from) { EIGEN_DEBUG_ALIGNED_LOAD return vld1q_f32(from); }
-template<> EIGEN_STRONG_INLINE Packet4i pload<int>(const int*     from) { EIGEN_DEBUG_ALIGNED_LOAD return vld1q_s32(from); }
+template<> EIGEN_STRONG_INLINE Packet4f pload<Packet4f>(const float* from) { EIGEN_DEBUG_ALIGNED_LOAD return vld1q_f32(from); }
+template<> EIGEN_STRONG_INLINE Packet4i pload<Packet4i>(const int*   from) { EIGEN_DEBUG_ALIGNED_LOAD return vld1q_s32(from); }
 
-template<> EIGEN_STRONG_INLINE Packet4f ploadu(const float* from) { EIGEN_DEBUG_UNALIGNED_LOAD return vld1q_f32(from); }
-template<> EIGEN_STRONG_INLINE Packet4i ploadu(const int* from)   { EIGEN_DEBUG_UNALIGNED_LOAD return vld1q_s32(from); }
+template<> EIGEN_STRONG_INLINE Packet4f ploadu<Packet4f>(const float* from) { EIGEN_DEBUG_UNALIGNED_LOAD return vld1q_f32(from); }
+template<> EIGEN_STRONG_INLINE Packet4i ploadu<Packet4i>(const int* from)   { EIGEN_DEBUG_UNALIGNED_LOAD return vld1q_s32(from); }
 
-template<> EIGEN_STRONG_INLINE Packet4f ploaddup<Packet4f>(const float* from)
+template<> EIGEN_STRONG_INLINE Packet4f ploaddup<Packet4f>(const float*   from)
 {
-  float32x2_t lo, ho;
+  float32x2_t lo, hi;
   lo = vdup_n_f32(*from);
   hi = vdup_n_f32(*from);
   return vcombine_f32(lo, hi);
 }
-template<> EIGEN_STRONG_INLINE Packet4i ploaddup<Packet4i>(const float* from)
+template<> EIGEN_STRONG_INLINE Packet4i ploaddup<Packet4i>(const int*     from)
 {
-  int32x2_t lo, ho;
+  int32x2_t lo, hi;
   lo = vdup_n_s32(*from);
   hi = vdup_n_s32(*from);
   return vcombine_s32(lo, hi);