diff --git a/modules/core/include/opencv2/core/hal/intrin.hpp b/modules/core/include/opencv2/core/hal/intrin.hpp
index 5a105a7a41872cf15991c00c9abfdc66ce9c18c5..52f6b5d55200debeda848c81845ba88299eb2078 100644
--- a/modules/core/include/opencv2/core/hal/intrin.hpp
+++ b/modules/core/include/opencv2/core/hal/intrin.hpp
@@ -99,6 +99,7 @@ enum StoreMode
 
 }
 
+// TODO FIXIT: Don't use "God" traits. Split on separate cases.
 template<typename _Tp> struct V_TypeTraits
 {
 };
@@ -130,21 +131,51 @@ template<typename _Tp> struct V_TypeTraits
         } \
     }
 
+#define CV_INTRIN_DEF_TYPE_TRAITS_NO_Q_TYPE(type, int_type_, uint_type_, abs_type_, w_type_, sum_type_, nlanes128_) \
+    template<> struct V_TypeTraits<type> \
+    { \
+        typedef type value_type; \
+        typedef int_type_ int_type; \
+        typedef abs_type_ abs_type; \
+        typedef uint_type_ uint_type; \
+        typedef w_type_ w_type; \
+        typedef sum_type_ sum_type; \
+        enum { nlanes128 = nlanes128_ }; \
+    \
+        static inline int_type reinterpret_int(type x) \
+        { \
+            union { type l; int_type i; } v; \
+            v.l = x; \
+            return v.i; \
+        } \
+    \
+        static inline type reinterpret_from_int(int_type x) \
+        { \
+            union { type l; int_type i; } v; \
+            v.i = x; \
+            return v.l; \
+        } \
+    }
+
 CV_INTRIN_DEF_TYPE_TRAITS(uchar, schar, uchar, uchar, ushort, unsigned, unsigned, 16);
 CV_INTRIN_DEF_TYPE_TRAITS(schar, schar, uchar, uchar, short, int, int, 16);
 CV_INTRIN_DEF_TYPE_TRAITS(ushort, short, ushort, ushort, unsigned, uint64, unsigned, 8);
 CV_INTRIN_DEF_TYPE_TRAITS(short, short, ushort, ushort, int, int64, int, 8);
-CV_INTRIN_DEF_TYPE_TRAITS(unsigned, int, unsigned, unsigned, uint64, void, unsigned, 4);
-CV_INTRIN_DEF_TYPE_TRAITS(int, int, unsigned, unsigned, int64, void, int, 4);
-CV_INTRIN_DEF_TYPE_TRAITS(float, int, unsigned, float, double, void, float, 4);
-CV_INTRIN_DEF_TYPE_TRAITS(uint64, int64, uint64, uint64, void, void, uint64, 2);
-CV_INTRIN_DEF_TYPE_TRAITS(int64, int64, uint64, uint64, void, void, int64, 2);
-CV_INTRIN_DEF_TYPE_TRAITS(double, int64, uint64, double, void, void, double, 2);
+CV_INTRIN_DEF_TYPE_TRAITS_NO_Q_TYPE(unsigned, int, unsigned, unsigned, uint64, unsigned, 4);
+CV_INTRIN_DEF_TYPE_TRAITS_NO_Q_TYPE(int, int, unsigned, unsigned, int64, int, 4);
+CV_INTRIN_DEF_TYPE_TRAITS_NO_Q_TYPE(float, int, unsigned, float, double, float, 4);
+CV_INTRIN_DEF_TYPE_TRAITS_NO_Q_TYPE(uint64, int64, uint64, uint64, void, uint64, 2);
+CV_INTRIN_DEF_TYPE_TRAITS_NO_Q_TYPE(int64, int64, uint64, uint64, void, int64, 2);
+CV_INTRIN_DEF_TYPE_TRAITS_NO_Q_TYPE(double, int64, uint64, double, void, double, 2);
 
 #ifndef CV_DOXYGEN
 
 #ifndef CV_CPU_OPTIMIZATION_HAL_NAMESPACE
-#ifdef CV_CPU_DISPATCH_MODE
+#ifdef CV_FORCE_SIMD128_CPP
+    #define CV_CPU_OPTIMIZATION_HAL_NAMESPACE hal_EMULATOR_CPP
+    #define CV_CPU_OPTIMIZATION_HAL_NAMESPACE_BEGIN namespace hal_EMULATOR_CPP {
+    #define CV_CPU_OPTIMIZATION_HAL_NAMESPACE_END }
+#elif defined(CV_CPU_DISPATCH_MODE)
     #define CV_CPU_OPTIMIZATION_HAL_NAMESPACE __CV_CAT(hal_, CV_CPU_DISPATCH_MODE)
     #define CV_CPU_OPTIMIZATION_HAL_NAMESPACE_BEGIN namespace __CV_CAT(hal_, CV_CPU_DISPATCH_MODE) {
     #define CV_CPU_OPTIMIZATION_HAL_NAMESPACE_END }
@@ -197,7 +228,6 @@ using namespace CV_CPU_OPTIMIZATION_HAL_NAMESPACE;
 
 #else
 
-#define CV_SIMD128_CPP 1
 #include "opencv2/core/hal/intrin_cpp.hpp"
 
 #endif
@@ -242,6 +272,10 @@ CV_CPU_OPTIMIZATION_HAL_NAMESPACE_BEGIN
 #define CV_SIMD128 0
 #endif
 
+#ifndef CV_SIMD128_CPP
+#define CV_SIMD128_CPP 0
+#endif
+
 #ifndef CV_SIMD128_64F
 #define CV_SIMD128_64F 0
 #endif
@@ -346,7 +380,7 @@ template<typename _Tp> struct V_RegTraits
     CV_DEF_REG_TRAITS(v, v_int16x8, short, s16, v_uint16x8, v_int32x4, v_int64x2, v_int16x8, void);
     CV_DEF_REG_TRAITS(v, v_uint32x4, unsigned, u32, v_uint32x4, v_uint64x2, void, v_int32x4, void);
     CV_DEF_REG_TRAITS(v, v_int32x4, int, s32, v_uint32x4, v_int64x2, void, v_int32x4, void);
-#if CV_SIMD128_64F
+#if CV_SIMD128_64F || CV_SIMD128_CPP
     CV_DEF_REG_TRAITS(v, v_float32x4, float, f32, v_float32x4, v_float64x2, void, v_int32x4, v_int32x4);
 #else
     CV_DEF_REG_TRAITS(v, v_float32x4, float, f32, v_float32x4, void, void, v_int32x4, v_int32x4);
@@ -433,7 +467,11 @@ namespace CV__SIMD_NAMESPACE {
 } // namespace
 using namespace CV__SIMD_NAMESPACE;
 #elif (CV_SIMD128 || CV_SIMD128_CPP) && (!defined(CV__SIMD_FORCE_WIDTH) || CV__SIMD_FORCE_WIDTH == 128)
+#if defined CV_SIMD128_CPP
+#define CV__SIMD_NAMESPACE simd128_cpp
+#else
 #define CV__SIMD_NAMESPACE simd128
+#endif
 namespace CV__SIMD_NAMESPACE {
     #define CV_SIMD CV_SIMD128
     #define CV_SIMD_64F CV_SIMD128_64F
diff --git a/modules/core/include/opencv2/core/hal/intrin_cpp.hpp b/modules/core/include/opencv2/core/hal/intrin_cpp.hpp
index 15ae380e65f05fd2843c2218768919920d5510cc..d9719b7fa0bbd4a64585cca298cc2a2f7716d627 100644
--- a/modules/core/include/opencv2/core/hal/intrin_cpp.hpp
+++ b/modules/core/include/opencv2/core/hal/intrin_cpp.hpp
@@ -50,6 +50,14 @@
 #include <algorithm>
 #include "opencv2/core/saturate.hpp"
 
+//! @cond IGNORED
+#define CV_SIMD128_CPP 1
+#if defined(CV_FORCE_SIMD128_CPP) || defined(CV_DOXYGEN)
+#define CV_SIMD128 1
+#define CV_SIMD128_64F 1
+#endif
+//! @endcond
+
 namespace cv
 {
 
@@ -135,7 +143,7 @@ Element-wise binary and unary operations.
 @ref v_shl, @ref v_shr
 
 - Bitwise logic:
-@ref operator&(const v_reg &a, const v_reg &b) "&",
+@ref operator &(const v_reg &a, const v_reg &b) "&",
 @ref operator |(const v_reg &a, const v_reg &b) "|",
 @ref operator ^(const v_reg &a, const v_reg &b) "^",
 @ref operator ~(const v_reg &a) "~"
@@ -402,50 +410,102 @@ typedef v_reg<uint64, 2> v_uint64x2;
 /** @brief Two 64-bit signed integer values */
 typedef v_reg<int64, 2> v_int64x2;
 
-//! @brief Helper macro
-//! @ingroup core_hal_intrin_impl
-#define OPENCV_HAL_IMPL_BIN_OP(bin_op) \
-template<typename _Tp, int n> inline v_reg<_Tp, n> \
-    operator bin_op (const v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b) \
-{ \
-    v_reg<_Tp, n> c; \
-    for( int i = 0; i < n; i++ ) \
-        c.s[i] = saturate_cast<_Tp>(a.s[i] bin_op b.s[i]); \
-    return c; \
-} \
-template<typename _Tp, int n> inline v_reg<_Tp, n>& \
-    operator bin_op##= (v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b) \
-{ \
-    for( int i = 0; i < n; i++ ) \
-        a.s[i] = saturate_cast<_Tp>(a.s[i] bin_op b.s[i]); \
-    return a; \
-}
-
 /** @brief Add values
 
 For all types. */
-OPENCV_HAL_IMPL_BIN_OP(+)
+template<typename _Tp, int n> CV_INLINE v_reg<_Tp, n> operator+(const v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b);
+template<typename _Tp, int n> CV_INLINE v_reg<_Tp, n>& operator+=(v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b);
 
 /** @brief Subtract values
 
 For all types. */
-OPENCV_HAL_IMPL_BIN_OP(-)
+template<typename _Tp, int n> CV_INLINE v_reg<_Tp, n> operator-(const v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b);
+template<typename _Tp, int n> CV_INLINE v_reg<_Tp, n>& operator-=(v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b);
 
 /** @brief Multiply values
 
 For 16- and 32-bit integer types and floating types. */
-OPENCV_HAL_IMPL_BIN_OP(*)
+template<typename _Tp, int n> CV_INLINE v_reg<_Tp, n> operator*(const v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b);
+template<typename _Tp, int n> CV_INLINE v_reg<_Tp, n>& operator*=(v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b);
 
 /** @brief Divide values
 
 For floating types only. */
-OPENCV_HAL_IMPL_BIN_OP(/)
+template<typename _Tp, int n> CV_INLINE v_reg<_Tp, n> operator/(const v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b);
+template<typename _Tp, int n> CV_INLINE v_reg<_Tp, n>& operator/=(v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b);
 
-//! @brief Helper macro
-//! @ingroup core_hal_intrin_impl
-#define OPENCV_HAL_IMPL_BIT_OP(bit_op) \
-template<typename _Tp, int n> inline v_reg<_Tp, n> operator bit_op \
-    (const v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b) \
+
+/** @brief Bitwise AND
+
+Only for integer types. */
+template<typename _Tp, int n> CV_INLINE v_reg<_Tp, n> operator&(const v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b);
+template<typename _Tp, int n> CV_INLINE v_reg<_Tp, n>& operator&=(v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b);
+
+/** @brief Bitwise OR
+
+Only for integer types. */
+template<typename _Tp, int n> CV_INLINE v_reg<_Tp, n> operator|(const v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b);
+template<typename _Tp, int n> CV_INLINE v_reg<_Tp, n>& operator|=(v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b);
+
+/** @brief Bitwise XOR
+
+Only for integer types.*/
+template<typename _Tp, int n> CV_INLINE v_reg<_Tp, n> operator^(const v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b);
+template<typename _Tp, int n> CV_INLINE v_reg<_Tp, n>& operator^=(v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b);
+
+/** @brief Bitwise NOT
+
+Only for integer types.*/
+template<typename _Tp, int n> CV_INLINE v_reg<_Tp, n> operator~(const v_reg<_Tp, n>& a);
+
+
+#ifndef CV_DOXYGEN
+
+#define CV__HAL_INTRIN_EXPAND_WITH_INTEGER_TYPES(macro_name, ...) \
+__CV_EXPAND(macro_name(uchar, __VA_ARGS__)) \
+__CV_EXPAND(macro_name(schar, __VA_ARGS__)) \
+__CV_EXPAND(macro_name(ushort, __VA_ARGS__)) \
+__CV_EXPAND(macro_name(short, __VA_ARGS__)) \
+__CV_EXPAND(macro_name(unsigned, __VA_ARGS__)) \
+__CV_EXPAND(macro_name(int, __VA_ARGS__)) \
+__CV_EXPAND(macro_name(uint64, __VA_ARGS__)) \
+__CV_EXPAND(macro_name(int64, __VA_ARGS__)) \
+
+#define CV__HAL_INTRIN_EXPAND_WITH_FP_TYPES(macro_name, ...) \
+__CV_EXPAND(macro_name(float, __VA_ARGS__)) \
+__CV_EXPAND(macro_name(double, __VA_ARGS__)) \
+
+#define CV__HAL_INTRIN_EXPAND_WITH_ALL_TYPES(macro_name, ...) \
+CV__HAL_INTRIN_EXPAND_WITH_INTEGER_TYPES(macro_name, __VA_ARGS__) \
+CV__HAL_INTRIN_EXPAND_WITH_FP_TYPES(macro_name, __VA_ARGS__) \
+
+#define CV__HAL_INTRIN_IMPL_BIN_OP_(_Tp, bin_op) \
+template<int n> inline \
+v_reg<_Tp, n> operator bin_op (const v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b) \
+{ \
+    v_reg<_Tp, n> c; \
+    for( int i = 0; i < n; i++ ) \
+        c.s[i] = saturate_cast<_Tp>(a.s[i] bin_op b.s[i]); \
+    return c; \
+} \
+template<int n> inline \
+v_reg<_Tp, n>& operator bin_op##= (v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b) \
+{ \
+    for( int i = 0; i < n; i++ ) \
+        a.s[i] = saturate_cast<_Tp>(a.s[i] bin_op b.s[i]); \
+    return a; \
+}
+
+#define CV__HAL_INTRIN_IMPL_BIN_OP(bin_op) CV__HAL_INTRIN_EXPAND_WITH_ALL_TYPES(CV__HAL_INTRIN_IMPL_BIN_OP_, bin_op)
+
+CV__HAL_INTRIN_IMPL_BIN_OP(+)
+CV__HAL_INTRIN_IMPL_BIN_OP(-)
+CV__HAL_INTRIN_IMPL_BIN_OP(*)
+CV__HAL_INTRIN_EXPAND_WITH_FP_TYPES(CV__HAL_INTRIN_IMPL_BIN_OP_, /)
+
+#define CV__HAL_INTRIN_IMPL_BIT_OP_(_Tp, bit_op) \
+template<int n> CV_INLINE \
+v_reg<_Tp, n> operator bit_op (const v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b) \
 { \
     v_reg<_Tp, n> c; \
     typedef typename V_TypeTraits<_Tp>::int_type itype; \
@@ -454,8 +514,8 @@ template<typename _Tp, int n> inline v_reg<_Tp, n> operator bit_op \
                                                         V_TypeTraits<_Tp>::reinterpret_int(b.s[i]))); \
     return c; \
 } \
-template<typename _Tp, int n> inline v_reg<_Tp, n>& operator \
-    bit_op##= (v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b) \
+template<int n> CV_INLINE \
+v_reg<_Tp, n>& operator bit_op##= (v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b) \
 { \
     typedef typename V_TypeTraits<_Tp>::int_type itype; \
     for( int i = 0; i < n; i++ ) \
@@ -464,33 +524,29 @@ template<typename _Tp, int n> inline v_reg<_Tp, n>& operator \
     return a; \
 }
 
-/** @brief Bitwise AND
+#define CV__HAL_INTRIN_IMPL_BIT_OP(bit_op) \
+CV__HAL_INTRIN_EXPAND_WITH_INTEGER_TYPES(CV__HAL_INTRIN_IMPL_BIT_OP_, bit_op) \
+CV__HAL_INTRIN_EXPAND_WITH_FP_TYPES(CV__HAL_INTRIN_IMPL_BIT_OP_, bit_op) /* TODO: FIXIT remove this after masks refactoring */
 
-Only for integer types. */
-OPENCV_HAL_IMPL_BIT_OP(&)
 
-/** @brief Bitwise OR
-
-Only for integer types. */
-OPENCV_HAL_IMPL_BIT_OP(|)
+CV__HAL_INTRIN_IMPL_BIT_OP(&)
+CV__HAL_INTRIN_IMPL_BIT_OP(|)
+CV__HAL_INTRIN_IMPL_BIT_OP(^)
 
-/** @brief Bitwise XOR
+#define CV__HAL_INTRIN_IMPL_BITWISE_NOT_(_Tp, dummy) \
+template<int n> CV_INLINE \
+v_reg<_Tp, n> operator ~ (const v_reg<_Tp, n>& a) \
+{ \
+    v_reg<_Tp, n> c; \
+    for( int i = 0; i < n; i++ ) \
+        c.s[i] = V_TypeTraits<_Tp>::reinterpret_from_int(~V_TypeTraits<_Tp>::reinterpret_int(a.s[i])); \
+    return c; \
+} \
 
-Only for integer types.*/
-OPENCV_HAL_IMPL_BIT_OP(^)
+CV__HAL_INTRIN_EXPAND_WITH_INTEGER_TYPES(CV__HAL_INTRIN_IMPL_BITWISE_NOT_, ~)
 
-/** @brief Bitwise NOT
+#endif  // !CV_DOXYGEN
 
-Only for integer types.*/
-template<typename _Tp, int n> inline v_reg<_Tp, n> operator ~ (const v_reg<_Tp, n>& a)
-{
-    v_reg<_Tp, n> c;
-    for( int i = 0; i < n; i++ )
-    {
-        c.s[i] = V_TypeTraits<_Tp>::reinterpret_from_int(~V_TypeTraits<_Tp>::reinterpret_int(a.s[i]));
-    }
-    return c;
-}
 
 //! @brief Helper macro
 //! @ingroup core_hal_intrin_impl
@@ -503,6 +559,27 @@ template<typename _Tp, int n> inline v_reg<_Tp2, n> func(const v_reg<_Tp, n>& a)
     return c; \
 }
 
+//! @brief Helper macro
+//! @ingroup core_hal_intrin_impl
+#define OPENCV_HAL_IMPL_MATH_FUNC_FLOAT(func, cfunc) \
+inline v_reg<int, 4> func(const v_reg<float, 4>& a) \
+{ \
+    v_reg<int, 4> c; \
+    for( int i = 0; i < 4; i++ ) \
+        c.s[i] = cfunc(a.s[i]); \
+    return c; \
+} \
+inline v_reg<int, 4> func(const v_reg<double, 2>& a) \
+{ \
+    v_reg<int, 4> c; \
+    for( int i = 0; i < 2; i++ ) \
+    { \
+        c.s[i] = cfunc(a.s[i]); \
+        c.s[i + 2] = 0; \
+    } \
+    return c; \
+}
+
 /** @brief Square root of elements
 
 Only for floating point types.*/
@@ -524,22 +601,22 @@ OPENCV_HAL_IMPL_MATH_FUNC(v_abs, (typename V_TypeTraits<_Tp>::abs_type)std::abs,
 /** @brief Round elements
 
 Only for floating point types.*/
-OPENCV_HAL_IMPL_MATH_FUNC(v_round, cvRound, int)
+OPENCV_HAL_IMPL_MATH_FUNC_FLOAT(v_round, cvRound)
 
 /** @brief Floor elements
 
 Only for floating point types.*/
-OPENCV_HAL_IMPL_MATH_FUNC(v_floor, cvFloor, int)
+OPENCV_HAL_IMPL_MATH_FUNC_FLOAT(v_floor, cvFloor)
 
 /** @brief Ceil elements
 
 Only for floating point types.*/
-OPENCV_HAL_IMPL_MATH_FUNC(v_ceil, cvCeil, int)
+OPENCV_HAL_IMPL_MATH_FUNC_FLOAT(v_ceil, cvCeil)
 
 /** @brief Truncate elements
 
 Only for floating point types.*/
-OPENCV_HAL_IMPL_MATH_FUNC(v_trunc, int, int)
+OPENCV_HAL_IMPL_MATH_FUNC_FLOAT(v_trunc, int)
 
 //! @brief Helper macro
 //! @ingroup core_hal_intrin_impl
@@ -1083,9 +1160,8 @@ OPENCV_HAL_IMPL_SHIFT_OP(<< )
 For 16-, 32- and 64-bit integer values. */
 OPENCV_HAL_IMPL_SHIFT_OP(>> )
 
-/** @brief Element shift left among vector
-
-For all type */
+//! @brief Helper macro
+//! @ingroup core_hal_intrin_impl
 #define OPENCV_HAL_IMPL_ROTATE_SHIFT_OP(suffix,opA,opB) \
 template<int imm, typename _Tp, int n> inline v_reg<_Tp, n> v_rotate_##suffix(const v_reg<_Tp, n>& a) \
 { \
@@ -1127,7 +1203,14 @@ template<int imm, typename _Tp, int n> inline v_reg<_Tp, n> v_rotate_##suffix(co
     return c; \
 }
 
+/** @brief Element shift left among vector
+
+For all type */
 OPENCV_HAL_IMPL_ROTATE_SHIFT_OP(left,  -, +)
+
+/** @brief Element shift right among vector
+
+For all type */
 OPENCV_HAL_IMPL_ROTATE_SHIFT_OP(right, +, -)
 
 /** @brief Sum packed values
@@ -1389,6 +1472,7 @@ similar to cv::v_load, but source memory block should be aligned (to 16-byte bou
 template<typename _Tp>
 inline v_reg<_Tp, V_TypeTraits<_Tp>::nlanes128> v_load_aligned(const _Tp* ptr)
 {
+    CV_Assert(isAligned<sizeof(v_reg<_Tp, V_TypeTraits<_Tp>::nlanes128>)>(ptr));
     return v_reg<_Tp, V_TypeTraits<_Tp>::nlanes128>(ptr);
 }
 
@@ -1620,6 +1704,12 @@ inline void v_store(_Tp* ptr, const v_reg<_Tp, n>& a)
         ptr[i] = a.s[i];
 }
 
+template<typename _Tp, int n>
+inline void v_store(_Tp* ptr, const v_reg<_Tp, n>& a, hal::StoreMode /*mode*/)
+{
+    v_store(ptr, a);
+}
+
 /** @brief Store data to memory (lower half)
 
 Store lower half of register contents to memory.
@@ -1659,22 +1749,22 @@ Pointer __should__ be aligned by 16-byte boundary. */
 template<typename _Tp, int n>
 inline void v_store_aligned(_Tp* ptr, const v_reg<_Tp, n>& a)
 {
-    for( int i = 0; i < n; i++ )
-        ptr[i] = a.s[i];
+    CV_Assert(isAligned<sizeof(v_reg<_Tp, n>)>(ptr));
+    v_store(ptr, a);
 }
 
 template<typename _Tp, int n>
 inline void v_store_aligned_nocache(_Tp* ptr, const v_reg<_Tp, n>& a)
 {
-    for( int i = 0; i < n; i++ )
-        ptr[i] = a.s[i];
+    CV_Assert(isAligned<sizeof(v_reg<_Tp, n>)>(ptr));
+    v_store(ptr, a);
 }
 
 template<typename _Tp, int n>
 inline void v_store_aligned(_Tp* ptr, const v_reg<_Tp, n>& a, hal::StoreMode /*mode*/)
 {
-    for( int i = 0; i < n; i++ )
-        ptr[i] = a.s[i];
+    CV_Assert(isAligned<sizeof(v_reg<_Tp, n>)>(ptr));
+    v_store(ptr, a);
 }
 
 /** @brief Combine vector from first elements of two vectors
@@ -1940,6 +2030,17 @@ template<int n> inline v_reg<float, n> v_cvt_f32(const v_reg<int, n>& a)
     return c;
 }
 
+template<int n> inline v_reg<float, n*2> v_cvt_f32(const v_reg<double, n>& a)
+{
+    v_reg<float, n*2> c;
+    for( int i = 0; i < n; i++ )
+    {
+        c.s[i] = (float)a.s[i];
+        c.s[i+n] = 0;
+    }
+    return c;
+}
+
 template<int n> inline v_reg<float, n*2> v_cvt_f32(const v_reg<double, n>& a, const v_reg<double, n>& b)
 {
     v_reg<float, n*2> c;
@@ -1954,36 +2055,76 @@ template<int n> inline v_reg<float, n*2> v_cvt_f32(const v_reg<double, n>& a, co
 /** @brief Convert to double
 
 Supported input type is cv::v_int32x4. */
-template<int n> inline v_reg<double, n> v_cvt_f64(const v_reg<int, n*2>& a)
+CV_INLINE v_reg<double, 2> v_cvt_f64(const v_reg<int, 4>& a)
 {
+    enum { n = 2 };
     v_reg<double, n> c;
     for( int i = 0; i < n; i++ )
         c.s[i] = (double)a.s[i];
     return c;
 }
 
+/** @brief Convert to double high part of vector
+
+Supported input type is cv::v_int32x4. */
+CV_INLINE v_reg<double, 2> v_cvt_f64_high(const v_reg<int, 4>& a)
+{
+    enum { n = 2 };
+    v_reg<double, n> c;
+    for( int i = 0; i < n; i++ )
+        c.s[i] = (double)a.s[i + 2];
+    return c;
+}
+
 /** @brief Convert to double
 
 Supported input type is cv::v_float32x4. */
-template<int n> inline v_reg<double, n> v_cvt_f64(const v_reg<float, n*2>& a)
+CV_INLINE v_reg<double, 2> v_cvt_f64(const v_reg<float, 4>& a)
 {
+    enum { n = 2 };
     v_reg<double, n> c;
     for( int i = 0; i < n; i++ )
         c.s[i] = (double)a.s[i];
     return c;
 }
 
+/** @brief Convert to double high part of vector
+
+Supported input type is cv::v_float32x4. */
+CV_INLINE v_reg<double, 2> v_cvt_f64_high(const v_reg<float, 4>& a)
+{
+    enum { n = 2 };
+    v_reg<double, n> c;
+    for( int i = 0; i < n; i++ )
+        c.s[i] = (double)a.s[i + 2];
+    return c;
+}
+
 /** @brief Convert to double
 
 Supported input type is cv::v_int64x2. */
-template<int n> inline v_reg<double, n> v_cvt_f64(const v_reg<int64, n>& a)
+CV_INLINE v_reg<double, 2> v_cvt_f64(const v_reg<int64, 2>& a)
 {
+    enum { n = 2 };
     v_reg<double, n> c;
     for( int i = 0; i < n; i++ )
         c.s[i] = (double)a.s[i];
     return c;
 }
 
+/** @brief Convert to double high part of vector
+
+Supported input type is cv::v_int64x2. */
+CV_INLINE v_reg<double, 2> v_cvt_f64_high(const v_reg<int64, 2>& a)
+{
+    enum { n = 2 };
+    v_reg<double, n> c;
+    for( int i = 0; i < n; i++ )
+        c.s[i] = (double)a.s[i];
+    return c;
+}
+
+
 template<typename _Tp> inline v_reg<_Tp, V_TypeTraits<_Tp>::nlanes128> v_lut(const _Tp* tab, const int* idx)
 {
     v_reg<_Tp, V_TypeTraits<_Tp>::nlanes128> c;
@@ -2038,6 +2179,28 @@ template<int n> inline v_reg<double, n> v_lut(const double* tab, const v_reg<int
     return c;
 }
 
+
+inline v_int32x4 v_lut(const int* tab, const v_int32x4& idxvec)
+{
+    return v_lut(tab, idxvec.s);
+}
+
+inline v_uint32x4 v_lut(const unsigned* tab, const v_int32x4& idxvec)
+{
+    return v_lut(tab, idxvec.s);
+}
+
+inline v_float32x4 v_lut(const float* tab, const v_int32x4& idxvec)
+{
+    return v_lut(tab, idxvec.s);
+}
+
+inline v_float64x2 v_lut(const double* tab, const v_int32x4& idxvec)
+{
+    return v_lut(tab, idxvec.s);
+}
+
+
 template<int n> inline void v_lut_deinterleave(const float* tab, const v_reg<int, n>& idx,
                                                v_reg<float, n>& x, v_reg<float, n>& y)
 {
@@ -2062,7 +2225,7 @@ template<int n> inline void v_lut_deinterleave(const double* tab, const v_reg<in
 
 template<typename _Tp, int n> inline v_reg<_Tp, n> v_interleave_pairs(const v_reg<_Tp, n>& vec)
 {
-    v_reg<float, n> c;
+    v_reg<_Tp, n> c;
     for (int i = 0; i < n/4; i++)
     {
         c.s[4*i  ] = vec.s[4*i  ];
@@ -2075,7 +2238,7 @@ template<typename _Tp, int n> inline v_reg<_Tp, n> v_interleave_pairs(const v_re
 
 template<typename _Tp, int n> inline v_reg<_Tp, n> v_interleave_quads(const v_reg<_Tp, n>& vec)
 {
-    v_reg<float, n> c;
+    v_reg<_Tp, n> c;
     for (int i = 0; i < n/8; i++)
     {
         c.s[8*i  ] = vec.s[8*i  ];
@@ -2092,7 +2255,7 @@ template<typename _Tp, int n> inline v_reg<_Tp, n> v_interleave_quads(const v_re
 
 template<typename _Tp, int n> inline v_reg<_Tp, n> v_pack_triplets(const v_reg<_Tp, n>& vec)
 {
-    v_reg<float, n> c;
+    v_reg<_Tp, n> c;
     for (int i = 0; i < n/4; i++)
     {
         c.s[3*i  ] = vec.s[4*i  ];
@@ -2523,6 +2686,17 @@ inline v_float32x4 v_matmuladd(const v_float32x4& v, const v_float32x4& m0,
                        v.s[0]*m0.s[3] + v.s[1]*m1.s[3] + v.s[2]*m2.s[3] + m3.s[3]);
 }
 
+
+inline v_float64x2 v_dotprod_expand(const v_int32x4& a, const v_int32x4& b)
+{ return v_fma(v_cvt_f64(a), v_cvt_f64(b), v_cvt_f64_high(a) * v_cvt_f64_high(b)); }
+inline v_float64x2 v_dotprod_expand(const v_int32x4& a, const v_int32x4& b, const v_float64x2& c)
+{ return v_fma(v_cvt_f64(a), v_cvt_f64(b), v_fma(v_cvt_f64_high(a), v_cvt_f64_high(b), c)); }
+
+inline v_float64x2 v_dotprod_expand_fast(const v_int32x4& a, const v_int32x4& b)
+{ return v_dotprod_expand(a, b); }
+inline v_float64x2 v_dotprod_expand_fast(const v_int32x4& a, const v_int32x4& b, const v_float64x2& c)
+{ return v_dotprod_expand(a, b, c); }
+
 ////// FP16 support ///////
 
 inline v_reg<float, V_TypeTraits<float>::nlanes128>
@@ -2537,7 +2711,7 @@ v_load_expand(const float16_t* ptr)
 }
 
 inline void
-v_pack_store(float16_t* ptr, v_reg<float, V_TypeTraits<float>::nlanes128>& v)
+v_pack_store(float16_t* ptr, const v_reg<float, V_TypeTraits<float>::nlanes128>& v)
 {
     for( int i = 0; i < v.nlanes; i++ )
     {
diff --git a/modules/core/src/arithm.cpp b/modules/core/src/arithm.cpp
index 3d1376dc8b2ba9f6002e61a7ae65b1696d49bc1d..760bbcb088dce362523d67c5e51c2c860c88b2c0 100644
--- a/modules/core/src/arithm.cpp
+++ b/modules/core/src/arithm.cpp
@@ -1522,7 +1522,8 @@ struct InRange_SIMD<float>
             v_float32 low2 = vx_load(src2 + x + v_float32::nlanes);
             v_float32 high2 = vx_load(src3 + x + v_float32::nlanes);
 
-            v_pack_store(dst + x, v_pack(v_reinterpret_as_u32((values1 >= low1) & (high1 >= values1)), v_reinterpret_as_u32((values2 >= low2) & (high2 >= values2))));
+            v_pack_store(dst + x, v_pack(v_reinterpret_as_u32(values1 >= low1) & v_reinterpret_as_u32(high1 >= values1),
+                                         v_reinterpret_as_u32(values2 >= low2) & v_reinterpret_as_u32(high2 >= values2)));
         }
         vx_cleanup();
         return x;
diff --git a/modules/core/src/arithm.simd.hpp b/modules/core/src/arithm.simd.hpp
index cd41237efdbb552b03de5070767c9cd2ac32c65e..addd5a3b5e9a58d20b1044f6968fda730f0724fd 100644
--- a/modules/core/src/arithm.simd.hpp
+++ b/modules/core/src/arithm.simd.hpp
@@ -1593,7 +1593,7 @@ struct op_div_f
 {
     static inline Tvec r(const Tvec& a, const Tvec& b)
     {
-        const Tvec v_zero = Tvec();
+        const Tvec v_zero = vx_setall<typename Tvec::lane_type>(0);
         return v_select(b == v_zero, v_zero, a / b);
     }
     static inline T1 r(T1 a, T1 b)
@@ -1620,7 +1620,7 @@ struct op_div_scale
     }
     static inline Tvec pre(const Tvec& denom, const Tvec& res)
     {
-        const Tvec v_zero = Tvec();
+        const Tvec v_zero = vx_setall<typename Tvec::lane_type>(0);
         return v_select(denom == v_zero, v_zero, res);
     }
     static inline T1 r(T1 a, T1 denom, const T2* scalar)
@@ -1860,7 +1860,7 @@ struct op_recip
     }
     static inline Tvec pre(const Tvec& denom, const Tvec& res)
     {
-        const Tvec v_zero = Tvec();
+        const Tvec v_zero = vx_setall<typename Tvec::lane_type>(0);
         return v_select(denom == v_zero, v_zero, res);
     }
     static inline T1 r(T1 denom, const T2* scalar)
diff --git a/modules/core/src/lapack.cpp b/modules/core/src/lapack.cpp
index 649f6baac533d14f9a4b1b586542886429375a1b..486b7a5aba14e05b6c78558e9742cbc8b7dd9a9c 100644
--- a/modules/core/src/lapack.cpp
+++ b/modules/core/src/lapack.cpp
@@ -916,8 +916,9 @@ double cv::invert( InputArray _src, OutputArray _dst, int method )
                     result = true;
                     d = 1./d;
                 #if CV_SIMD128
-                    static const float CV_DECL_ALIGNED(16) inv[4] = { 0.f,-0.f,-0.f,0.f };
-                    v_float32x4 s0 = (v_load_halves((const float*)srcdata, (const float*)(srcdata + srcstep)) * v_setall_f32((float)d)) ^ v_load((const float *)inv);//0123//3120
+                    const float d_32f = (float)d;
+                    const v_float32x4 d_vec(d_32f, -d_32f, -d_32f, d_32f);
+                    v_float32x4 s0 = v_load_halves((const float*)srcdata, (const float*)(srcdata + srcstep)) * d_vec;//0123//3120
                     s0 = v_extract<3>(s0, v_combine_low(v_rotate_right<1>(s0), s0));
                     v_store_low((float*)dstdata, s0);
                     v_store_high((float*)(dstdata + dststep), s0);
@@ -946,7 +947,7 @@ double cv::invert( InputArray _src, OutputArray _dst, int method )
                     v_float64x2 s0 = v_load((const double*)srcdata) * det;
                     v_float64x2 s1 = v_load((const double*)(srcdata+srcstep)) * det;
                     v_float64x2 sm = v_extract<1>(s1, s0);//30
-                    v_float64x2 ss = v_extract<1>(s0, s1) ^ v_setall_f64(-0.);//12
+                    v_float64x2 ss = v_setall<double>(0) - v_extract<1>(s0, s1);//12
                     v_store((double*)dstdata, v_combine_low(sm, ss));//31
                     v_store((double*)(dstdata + dststep), v_combine_high(ss, sm));//20
                 #else
diff --git a/modules/core/src/mathfuncs_core.simd.hpp b/modules/core/src/mathfuncs_core.simd.hpp
index ba8a5477de94a60088f311bae93832f6ce9d28c4..1bf36bb17407ab4a3947a7aba5d5814c17579a03 100644
--- a/modules/core/src/mathfuncs_core.simd.hpp
+++ b/modules/core/src/mathfuncs_core.simd.hpp
@@ -725,7 +725,7 @@ void log32f( const float *_x, float *y, int n )
 
         yf0 = v_fma(v_cvt_f32(yi0), vln2, yf0);
 
-        v_float32 delta = v_reinterpret_as_f32(h0 == vx_setall_s32(510)) & vshift;
+        v_float32 delta = v_select(v_reinterpret_as_f32(h0 == vx_setall_s32(510)), vshift, vx_setall<float>(0));
         xf0 = v_fma((v_reinterpret_as_f32(xi0) - v1), xf0, delta);
 
         v_float32 zf0 = v_fma(xf0, vA0, vA1);
diff --git a/modules/core/test/test_intrin_emulator.cpp b/modules/core/test/test_intrin_emulator.cpp
index 0ae3c02b86efeb4c1b3951b9533634333c2eac89..347bc8fee1147a7125f1452dc8dfe61a56a23182 100644
--- a/modules/core/test/test_intrin_emulator.cpp
+++ b/modules/core/test/test_intrin_emulator.cpp
@@ -3,22 +3,14 @@
 // of this distribution and at http://opencv.org/license.html.
 #include "test_precomp.hpp"
 
-// see "opencv2/core/hal/intrin.hpp"
-#define CV_CPU_OPTIMIZATION_HAL_NAMESPACE hal_EMULATOR_CPP
-#define CV_CPU_OPTIMIZATION_HAL_NAMESPACE_BEGIN namespace hal_EMULATOR_CPP {
-#define CV_CPU_OPTIMIZATION_HAL_NAMESPACE_END }
-
 // see "opencv2/core/private/cv_cpu_include_simd_declarations.hpp"
 //#define CV_CPU_OPTIMIZATION_DECLARATIONS_ONLY
-#define CV_FORCE_SIMD128_CPP
+#undef CV_FORCE_SIMD128_CPP
+#define CV_FORCE_SIMD128_CPP 1
 #undef CV_CPU_OPTIMIZATION_NAMESPACE_BEGIN
 #undef CV_CPU_OPTIMIZATION_NAMESPACE_END
 #define CV_CPU_OPTIMIZATION_NAMESPACE_BEGIN namespace opt_EMULATOR_CPP {
 #define CV_CPU_OPTIMIZATION_NAMESPACE_END }
 #include "test_intrin128.simd.hpp"
-#undef CV_CPU_OPTIMIZATION_NAMESPACE_BEGIN
-#undef CV_CPU_OPTIMIZATION_NAMESPACE_END
-#undef CV_CPU_DISPATCH_MODE
-#undef CV_FORCE_SIMD128_CPP
 
 // tests implementation is in test_intrin_utils.hpp
diff --git a/modules/core/test/test_intrin_utils.hpp b/modules/core/test/test_intrin_utils.hpp
index 4d2bd467371075bfb1bcebcea9a855124037088f..d8d94fdb0da4ed835f73b8d84927f0a35d18eecf 100644
--- a/modules/core/test/test_intrin_utils.hpp
+++ b/modules/core/test/test_intrin_utils.hpp
@@ -222,7 +222,10 @@ template <typename R> std::ostream & operator<<(std::ostream & out, const Data<R
     return out;
 }
 
-template<typename T> static inline void EXPECT_COMPARE_EQ_(const T a, const T b);
+template<typename T> static inline void EXPECT_COMPARE_EQ_(const T a, const T b)
+{
+    EXPECT_EQ(a, b);
+}
 template<> inline void EXPECT_COMPARE_EQ_<float>(const float a, const float b)
 {
     EXPECT_FLOAT_EQ( a, b );
@@ -742,12 +745,12 @@ template<typename R> struct TheTest
         for (int i = 0; i < n; ++i)
         {
             SCOPED_TRACE(cv::format("i=%d", i));
-            EXPECT_EQ((double)dataA[i*2]     * (double)dataA[i*2] +
-                      (double)dataA[i*2 + 1] * (double)dataA[i*2  + 1], resA[i]);
-            EXPECT_EQ((double)dataB[i*2]     * (double)dataB[i*2] +
-                      (double)dataB[i*2 + 1] * (double)dataB[i*2  + 1], resB[i]);
-            EXPECT_EQ((double)dataA[i*2]     * (double)dataB[i*2] +
-                      (double)dataA[i*2 + 1] * (double)dataB[i*2  + 1] + dataC[i], resC[i]);
+            EXPECT_COMPARE_EQ((double)dataA[i*2]     * (double)dataA[i*2] +
+                              (double)dataA[i*2 + 1] * (double)dataA[i*2  + 1], resA[i]);
+            EXPECT_COMPARE_EQ((double)dataB[i*2]     * (double)dataB[i*2] +
+                              (double)dataB[i*2 + 1] * (double)dataB[i*2  + 1], resB[i]);
+            EXPECT_COMPARE_EQ((double)dataA[i*2]     * (double)dataB[i*2] +
+                              (double)dataA[i*2 + 1] * (double)dataB[i*2  + 1] + dataC[i], resC[i]);
         }
     #endif
         return *this;
diff --git a/modules/features2d/src/fast_score.cpp b/modules/features2d/src/fast_score.cpp
index 73126e647b2727bc0dddeb85f4d5fa17cd3506cf..0bc011af491f4ec545ea1a7cbba21eae408966b9 100644
--- a/modules/features2d/src/fast_score.cpp
+++ b/modules/features2d/src/fast_score.cpp
@@ -303,7 +303,8 @@ int cornerScore<8>(const uchar* ptr, const int pixel[], int threshold)
     for (k = 0; k < N; k++)
         d[k] = (short)(v - ptr[pixel[k]]);
 
-#if CV_SIMD128
+#if CV_SIMD128 \
+    && (!defined(CV_SIMD128_CPP) || (!defined(__GNUC__) || __GNUC__ != 5))  // "movdqa" bug on "v_load(d + 1)" line (Ubuntu 16.04 + GCC 5.4)
     if (true)
     {
         v_int16x8 v0 = v_load(d + 1);
diff --git a/modules/imgproc/src/corner.avx.cpp b/modules/imgproc/src/corner.avx.cpp
index 1a62db3074818975d5a471b2ec0786526f965ad6..8d8083eee5994b25e10f5e0091f1a51ae11bc8df 100644
--- a/modules/imgproc/src/corner.avx.cpp
+++ b/modules/imgproc/src/corner.avx.cpp
@@ -42,6 +42,7 @@
 //M*/
 
 #include "precomp.hpp"
+#undef CV_FORCE_SIMD128_CPP  // expected AVX implementation only
 #include "opencv2/core/hal/intrin.hpp"
 #include "corner.hpp"