mirror/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2025-08-04 13:16:26 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #11341 from alalek:v_min_max_sse41

Browse Source
This commit is contained in:
Vadim Pisarevsky 2018-04-19 12:21:50 +00:00
commit 4e31015715
1 changed files with 32 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
modules/core/include/opencv2/core/hal/intrin_sse.hpp
View File

@ -796,43 +796,75 @@ OPENCV_HAL_IMPL_SSE_BIN_FUNC(v_float64x2, v_max, _mm_max_pd)
inline v_int8x16 v_min(const v_int8x16& a, const v_int8x16& b) inline v_int8x16 v_min(const v_int8x16& a, const v_int8x16& b)
{ {
#if CV_SSE4_1
return v_int8x16(_mm_min_epi8(a.val, b.val));
#else
__m128i delta = _mm_set1_epi8((char)-128); __m128i delta = _mm_set1_epi8((char)-128);
return v_int8x16(_mm_xor_si128(delta, _mm_min_epu8(_mm_xor_si128(a.val, delta), return v_int8x16(_mm_xor_si128(delta, _mm_min_epu8(_mm_xor_si128(a.val, delta),
_mm_xor_si128(b.val, delta)))); _mm_xor_si128(b.val, delta))));
#endif
} }
inline v_int8x16 v_max(const v_int8x16& a, const v_int8x16& b) inline v_int8x16 v_max(const v_int8x16& a, const v_int8x16& b)
{ {
#if CV_SSE4_1
return v_int8x16(_mm_max_epi8(a.val, b.val));
#else
__m128i delta = _mm_set1_epi8((char)-128); __m128i delta = _mm_set1_epi8((char)-128);
return v_int8x16(_mm_xor_si128(delta, _mm_max_epu8(_mm_xor_si128(a.val, delta), return v_int8x16(_mm_xor_si128(delta, _mm_max_epu8(_mm_xor_si128(a.val, delta),
_mm_xor_si128(b.val, delta)))); _mm_xor_si128(b.val, delta))));
#endif
} }
inline v_uint16x8 v_min(const v_uint16x8& a, const v_uint16x8& b) inline v_uint16x8 v_min(const v_uint16x8& a, const v_uint16x8& b)
{ {
#if CV_SSE4_1
return v_uint16x8(_mm_min_epu16(a.val, b.val));
#else
return v_uint16x8(_mm_subs_epu16(a.val, _mm_subs_epu16(a.val, b.val))); return v_uint16x8(_mm_subs_epu16(a.val, _mm_subs_epu16(a.val, b.val)));
#endif
} }
inline v_uint16x8 v_max(const v_uint16x8& a, const v_uint16x8& b) inline v_uint16x8 v_max(const v_uint16x8& a, const v_uint16x8& b)
{ {
#if CV_SSE4_1
return v_uint16x8(_mm_max_epu16(a.val, b.val));
#else
return v_uint16x8(_mm_adds_epu16(_mm_subs_epu16(a.val, b.val), b.val)); return v_uint16x8(_mm_adds_epu16(_mm_subs_epu16(a.val, b.val), b.val));
#endif
} }
inline v_uint32x4 v_min(const v_uint32x4& a, const v_uint32x4& b) inline v_uint32x4 v_min(const v_uint32x4& a, const v_uint32x4& b)
{ {
#if CV_SSE4_1
return v_uint32x4(_mm_min_epu32(a.val, b.val));
#else
__m128i delta = _mm_set1_epi32((int)0x80000000); __m128i delta = _mm_set1_epi32((int)0x80000000);
__m128i mask = _mm_cmpgt_epi32(_mm_xor_si128(a.val, delta), _mm_xor_si128(b.val, delta)); __m128i mask = _mm_cmpgt_epi32(_mm_xor_si128(a.val, delta), _mm_xor_si128(b.val, delta));
return v_uint32x4(v_select_si128(mask, b.val, a.val)); return v_uint32x4(v_select_si128(mask, b.val, a.val));
#endif
} }
inline v_uint32x4 v_max(const v_uint32x4& a, const v_uint32x4& b) inline v_uint32x4 v_max(const v_uint32x4& a, const v_uint32x4& b)
{ {
#if CV_SSE4_1
return v_uint32x4(_mm_max_epu32(a.val, b.val));
#else
__m128i delta = _mm_set1_epi32((int)0x80000000); __m128i delta = _mm_set1_epi32((int)0x80000000);
__m128i mask = _mm_cmpgt_epi32(_mm_xor_si128(a.val, delta), _mm_xor_si128(b.val, delta)); __m128i mask = _mm_cmpgt_epi32(_mm_xor_si128(a.val, delta), _mm_xor_si128(b.val, delta));
return v_uint32x4(v_select_si128(mask, a.val, b.val)); return v_uint32x4(v_select_si128(mask, a.val, b.val));
#endif
} }
inline v_int32x4 v_min(const v_int32x4& a, const v_int32x4& b) inline v_int32x4 v_min(const v_int32x4& a, const v_int32x4& b)
{ {
#if CV_SSE4_1
return v_int32x4(_mm_min_epi32(a.val, b.val));
#else
return v_int32x4(v_select_si128(_mm_cmpgt_epi32(a.val, b.val), b.val, a.val)); return v_int32x4(v_select_si128(_mm_cmpgt_epi32(a.val, b.val), b.val, a.val));
#endif
} }
inline v_int32x4 v_max(const v_int32x4& a, const v_int32x4& b) inline v_int32x4 v_max(const v_int32x4& a, const v_int32x4& b)
{ {
#if CV_SSE4_1
return v_int32x4(_mm_max_epi32(a.val, b.val));
#else
return v_int32x4(v_select_si128(_mm_cmpgt_epi32(a.val, b.val), a.val, b.val)); return v_int32x4(v_select_si128(_mm_cmpgt_epi32(a.val, b.val), a.val, b.val));
#endif
} }
#define OPENCV_HAL_IMPL_SSE_INT_CMP_OP(_Tpuvec, _Tpsvec, suffix, sbit) \ #define OPENCV_HAL_IMPL_SSE_INT_CMP_OP(_Tpuvec, _Tpsvec, suffix, sbit) \