potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-30 07:43:03 +04:00
Code Packages Releases Wiki Activity

Merge remote-tracking branch 'upstream/3.4' into merge-3.4

Browse Source
This commit is contained in:
Alexander Alekhin
2019-04-30 19:59:49 +00:00
parent 076ee65c85 163d5e4d39
commit e28e3c9491
37 changed files with 1159 additions and 439 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
@@ -1128,12 +1128,16 @@ 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)
{
modules/core/include/opencv2/core/hal/intrin_vsx.hpp
+1 -1
View File
@@ -763,7 +763,7 @@ inline unsigned v_reduce_sad(const v_int8x16& a, const v_int8x16& b)
inline unsigned v_reduce_sad(const v_uint16x8& a, const v_uint16x8& b)
{
vec_ushort8 ad = vec_absd(a.val, b.val);
VSX_UNUSED(vec_int4) sum = vec_sums(vec_int4_c(vec_unpackhu(ad)), vec_int4_c(vec_unpacklu(ad)));
VSX_UNUSED(vec_int4) sum = vec_sums(vec_int4_c(vec_unpackhu(ad)) + vec_int4_c(vec_unpacklu(ad)), vec_int4_z);
return (unsigned)vec_extract(sum, 3);
}
inline unsigned v_reduce_sad(const v_int16x8& a, const v_int16x8& b)
modules/core/include/opencv2/core/utility.hpp
+4
View File
@@ -118,7 +118,11 @@ CV_EXPORTS void setUseCollection(bool flag); // set implementation collection st
}
\endcode
*/
#ifdef OPENCV_ENABLE_MEMORY_SANITIZER
template<typename _Tp, size_t fixed_size = 0> class AutoBuffer
#else
template<typename _Tp, size_t fixed_size = 1024/sizeof(_Tp)+8> class AutoBuffer
#endif
{
public:
typedef _Tp value_type;
modules/core/test/test_intrin_utils.hpp
+16
View File
@@ -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()