potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-30 15:53:03 +04:00
Code Packages Releases Wiki Activity

Fixed v_reduce_sad intrinsics implementation and added tests

Browse Source
This commit is contained in:
Vitaly Tuzov
2019-04-22 11:19:08 +03:00
parent 5c0a98cfb6
commit 18d10d6b86
3 changed files with 26 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/core/include/opencv2/core/hal/intrin_avx.hpp
+6 -2
View File
@@ -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
+4 -3
View File
@@ -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)
{