potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-31 08:13:04 +04:00
Code Packages Releases Wiki Activity

use universal intrinsic and SSE4 popcount instruction in normHamming

Browse Source 
- add v_popcount in universal intrinsic
 - add test for v_popcount
 - add wrapper of popcount for both MSVC and GCC
This commit is contained in:
Tomoaki Teshima
2017-01-12 08:47:28 +09:00
parent c0cde75d54
commit 8b22099da2
6 changed files with 177 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/core/include/opencv2/core/cvdef.h
+8
View File
@@ -188,8 +188,16 @@ enum CpuFeatures {
# if defined __POPCNT__ || (defined _MSC_VER && _MSC_VER >= 1500)
# ifdef _MSC_VER
# include <nmmintrin.h>
# if defined(_M_X64)
# define CV_POPCNT_U64 _mm_popcnt_u64
# endif
# define CV_POPCNT_U32 _mm_popcnt_u32
# else
# include <popcntintrin.h>
# if defined(__x86_64__)
# define CV_POPCNT_U64 __builtin_popcountll
# endif
# define CV_POPCNT_U32 __builtin_popcount
# endif
# define CV_POPCNT 1
# endif
modules/core/include/opencv2/core/hal/intrin_cpp.hpp
+44 -1
View File
@@ -149,7 +149,7 @@ Element-wise binary and unary operations.
Most of these operations return only one value.
- Reduce: @ref v_reduce_min, @ref v_reduce_max, @ref v_reduce_sum
- Reduce: @ref v_reduce_min, @ref v_reduce_max, @ref v_reduce_sum, @ref v_popcount
- Mask: @ref v_signmask, @ref v_check_all, @ref v_check_any, @ref v_select
### Other math
@@ -574,6 +574,49 @@ Scheme:
For 32-bit integer and 32-bit floating point types. */
OPENCV_HAL_IMPL_REDUCE_MINMAX_FUNC(v_reduce_max, std::max)
static const unsigned char popCountTable[] =
{
0, 1, 1, 2, 1, 2, 2, 3, 1, 2, 2, 3, 2, 3, 3, 4,
1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
4, 5, 5, 6, 5, 6, 6, 7, 5, 6, 6, 7, 6, 7, 7, 8,
};
/** @brief Count the 1 bits in the vector and return 4 values
Scheme:
@code
{A1 A2 A3 ...} => popcount(A1)
@endcode
Any types but result will be in v_uint32x4*/
template<typename _Tp, int n> inline v_uint32x4 v_popcount(const v_reg<_Tp, n>& a)
{
v_uint8x16 b;
b = v_reinterpret_as_u8(a);
for( int i = 0; i < v_uint8x16::nlanes; i++ )
{
b.s[i] = popCountTable[b.s[i]];
}
v_uint32x4 c;
for( int i = 0; i < v_uint32x4::nlanes; i++ )
{
c.s[i] = b.s[i*4] + b.s[i*4+1] + b.s[i*4+2] + b.s[i*4+3];
}
return c;
}
//! @cond IGNORED
template<typename _Tp, int n>
inline void v_minmax( const v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b,
modules/core/include/opencv2/core/hal/intrin_neon.hpp
+16
View File
@@ -813,6 +813,22 @@ OPENCV_HAL_IMPL_NEON_REDUCE_OP_4(v_float32x4, float32x2, float, sum, add, f32)
OPENCV_HAL_IMPL_NEON_REDUCE_OP_4(v_float32x4, float32x2, float, max, max, f32)
OPENCV_HAL_IMPL_NEON_REDUCE_OP_4(v_float32x4, float32x2, float, min, min, f32)
#define OPENCV_HAL_IMPL_NEON_POPCOUNT(_Tpvec, cast) \
inline v_uint32x4 v_popcount(const _Tpvec& a) \
{ \
uint8x16_t t = vcntq_u8(cast(a.val)); \
uint16x8_t t0 = vpaddlq_u8(t); /* 16 -> 8 */ \
uint32x4_t t1 = vpaddlq_u16(t0); /* 8 -> 4 */ \
return v_uint32x4(t1); \
}
OPENCV_HAL_IMPL_NEON_POPCOUNT(v_uint8x16, OPENCV_HAL_NOP)
OPENCV_HAL_IMPL_NEON_POPCOUNT(v_uint16x8, vreinterpretq_u8_u16)
OPENCV_HAL_IMPL_NEON_POPCOUNT(v_uint32x4, vreinterpretq_u8_u32)
OPENCV_HAL_IMPL_NEON_POPCOUNT(v_int8x16, vreinterpretq_u8_s8)
OPENCV_HAL_IMPL_NEON_POPCOUNT(v_int16x8, vreinterpretq_u8_s16)
OPENCV_HAL_IMPL_NEON_POPCOUNT(v_int32x4, vreinterpretq_u8_s32)
inline int v_signmask(const v_uint8x16& a)
{
int8x8_t m0 = vcreate_s8(CV_BIG_UINT(0x0706050403020100));
modules/core/include/opencv2/core/hal/intrin_sse.hpp
+22
View File
@@ -1121,6 +1121,28 @@ OPENCV_HAL_IMPL_SSE_REDUCE_OP_4(v_float32x4, float, sum, OPENCV_HAL_ADD)
OPENCV_HAL_IMPL_SSE_REDUCE_OP_4(v_float32x4, float, max, std::max)
OPENCV_HAL_IMPL_SSE_REDUCE_OP_4(v_float32x4, float, min, std::min)
#define OPENCV_HAL_IMPL_SSE_POPCOUNT(_Tpvec) \
inline v_uint32x4 v_popcount(const _Tpvec& a) \
{ \
__m128i m1 = _mm_set1_epi32(0x55555555); \
__m128i m2 = _mm_set1_epi32(0x33333333); \
__m128i m4 = _mm_set1_epi32(0x0f0f0f0f); \
__m128i p = a.val; \
p = _mm_add_epi32(_mm_and_si128(_mm_srli_epi32(p, 1), m1), _mm_and_si128(p, m1)); \
p = _mm_add_epi32(_mm_and_si128(_mm_srli_epi32(p, 2), m2), _mm_and_si128(p, m2)); \
p = _mm_add_epi32(_mm_and_si128(_mm_srli_epi32(p, 4), m4), _mm_and_si128(p, m4)); \
p = _mm_adds_epi8(p, _mm_srli_si128(p, 1)); \
p = _mm_adds_epi8(p, _mm_srli_si128(p, 2)); \
return v_uint32x4(_mm_and_si128(p, _mm_set1_epi32(0x000000ff))); \
}
OPENCV_HAL_IMPL_SSE_POPCOUNT(v_uint8x16)
OPENCV_HAL_IMPL_SSE_POPCOUNT(v_uint16x8)
OPENCV_HAL_IMPL_SSE_POPCOUNT(v_uint32x4)
OPENCV_HAL_IMPL_SSE_POPCOUNT(v_int8x16)
OPENCV_HAL_IMPL_SSE_POPCOUNT(v_int16x8)
OPENCV_HAL_IMPL_SSE_POPCOUNT(v_int32x4)
#define OPENCV_HAL_IMPL_SSE_CHECK_SIGNS(_Tpvec, suffix, pack_op, and_op, signmask, allmask) \
inline int v_signmask(const _Tpvec& a) \
{ \