Fixed v_reduce_sad intrinsics implementation and added tests

modules/core/include/opencv2/core/hal/intrin_avx.hpp

@@ -1141,12 +1141,16 @@ inline v_float32x8 v_reduce_sum4(const v_float32x8& a, const v_float32x8& b,
 
 inline unsigned v_reduce_sad(const v_uint8x32& a, const v_uint8x32& b)
 {
-    return (unsigned)_v_cvtsi256_si32(_mm256_sad_epu8(a.val, b.val));
+    __m256i half = _mm256_sad_epu8(a.val, b.val);
+    __m128i quarter = _mm_add_epi32(_v256_extract_low(half), _v256_extract_high(half));
+    return (unsigned)_mm_cvtsi128_si32(_mm_add_epi32(quarter, _mm_unpackhi_epi64(quarter, quarter)));
 }
 inline unsigned v_reduce_sad(const v_int8x32& a, const v_int8x32& b)
 {
     __m256i half = _mm256_set1_epi8(0x7f);
-    return (unsigned)_v_cvtsi256_si32(_mm256_sad_epu8(_mm256_add_epi8(a.val, half), _mm256_add_epi8(b.val, half)));
+    half = _mm256_sad_epu8(_mm256_add_epi8(a.val, half), _mm256_add_epi8(b.val, half));
+    __m128i quarter = _mm_add_epi32(_v256_extract_low(half), _v256_extract_high(half));
+    return (unsigned)_mm_cvtsi128_si32(_mm_add_epi32(quarter, _mm_unpackhi_epi64(quarter, quarter)));
 }
 inline unsigned v_reduce_sad(const v_uint16x16& a, const v_uint16x16& b)
 {

modules/core/include/opencv2/core/hal/intrin_sse.hpp

@@ -1486,13 +1486,14 @@ OPENCV_HAL_IMPL_SSE_REDUCE_OP_4(v_float32x4, float, min, std::min)
 
 inline unsigned v_reduce_sad(const v_uint8x16& a, const v_uint8x16& b)
 {
-    return (unsigned)_mm_cvtsi128_si32(_mm_sad_epu8(a.val, b.val));
+    __m128i half = _mm_sad_epu8(a.val, b.val);
+    return (unsigned)_mm_cvtsi128_si32(_mm_add_epi32(half, _mm_unpackhi_epi64(half, half)));
 }
 inline unsigned v_reduce_sad(const v_int8x16& a, const v_int8x16& b)
 {
     __m128i half = _mm_set1_epi8(0x7f);
-    return (unsigned)_mm_cvtsi128_si32(_mm_sad_epu8(_mm_add_epi8(a.val, half),
-                                                    _mm_add_epi8(b.val, half)));
+    half = _mm_sad_epu8(_mm_add_epi8(a.val, half), _mm_add_epi8(b.val, half));
+    return (unsigned)_mm_cvtsi128_si32(_mm_add_epi32(half, _mm_unpackhi_epi64(half, half)));
 }
 inline unsigned v_reduce_sad(const v_uint16x8& a, const v_uint16x8& b)
 {

modules/core/test/test_intrin_utils.hpp

@@ -770,6 +770,15 @@ template<typename R> struct TheTest
         return *this;
     }
 
+    TheTest & test_reduce_sad()
+    {
+        Data<R> dataA, dataB(R::nlanes/2);
+        R a = dataA;
+        R b = dataB;
+        EXPECT_EQ((unsigned)(R::nlanes*R::nlanes/4), v_reduce_sad(a, b));
+        return *this;
+    }
+
     TheTest & test_mask()
     {
         typedef typename V_RegTraits<R>::int_reg int_reg;
@@ -1320,6 +1329,7 @@ void test_hal_intrin_uint8()
         .test_logic()
         .test_min_max()
         .test_absdiff()
+        .test_reduce_sad()
         .test_mask()
         .test_popcount()
         .test_pack<1>().test_pack<2>().test_pack<3>().test_pack<8>()
@@ -1358,6 +1368,7 @@ void test_hal_intrin_int8()
         .test_absdiff()
         .test_absdiffs()
         .test_abs()
+        .test_reduce_sad()
         .test_mask()
         .test_popcount()
         .test_pack<1>().test_pack<2>().test_pack<3>().test_pack<8>()
@@ -1387,6 +1398,7 @@ void test_hal_intrin_uint16()
         .test_min_max()
         .test_absdiff()
         .test_reduce()
+        .test_reduce_sad()
         .test_mask()
         .test_popcount()
         .test_pack<1>().test_pack<2>().test_pack<7>().test_pack<16>()
@@ -1418,6 +1430,7 @@ void test_hal_intrin_int16()
         .test_absdiffs()
         .test_abs()
         .test_reduce()
+        .test_reduce_sad()
         .test_mask()
         .test_popcount()
         .test_pack<1>().test_pack<2>().test_pack<7>().test_pack<16>()
@@ -1446,6 +1459,7 @@ void test_hal_intrin_uint32()
         .test_min_max()
         .test_absdiff()
         .test_reduce()
+        .test_reduce_sad()
         .test_mask()
         .test_popcount()
         .test_pack<1>().test_pack<2>().test_pack<15>().test_pack<32>()
@@ -1473,6 +1487,7 @@ void test_hal_intrin_int32()
         .test_min_max()
         .test_absdiff()
         .test_reduce()
+        .test_reduce_sad()
         .test_mask()
         .test_pack<1>().test_pack<2>().test_pack<15>().test_pack<32>()
         .test_unpack()
@@ -1528,6 +1543,7 @@ void test_hal_intrin_float32()
         .test_min_max()
         .test_float_absdiff()
         .test_reduce()
+        .test_reduce_sad()
         .test_mask()
         .test_unpack()
         .test_float_math()