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 pull request #13334 from terfendail:histogram_wintr

Browse Source 
* added performance test for compareHist

* compareHist reworked to use wide universal intrinsics

* Disabled vectorization for CV_COMP_CORREL and CV_COMP_BHATTACHARYYA if f64 is unsupported
This commit is contained in:
Vitaly Tuzov
2018-12-13 14:20:22 +03:00
committed by Alexander Alekhin
parent a9771078df
commit 3903174f7c
6 changed files with 155 additions and 94 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/core/include/opencv2/core/hal/intrin_avx.hpp
+6
View File
@@ -1125,6 +1125,12 @@ inline float v_reduce_sum(const v_float32x8& a)
return _mm_cvtss_f32(s1);
}
inline double v_reduce_sum(const v_float64x4& a)
{
__m256d s0 = _mm256_hadd_pd(a.val, a.val);
return _mm_cvtsd_f64(_mm_add_pd(_v256_extract_low(s0), _v256_extract_high(s0)));
}
inline v_float32x8 v_reduce_sum4(const v_float32x8& a, const v_float32x8& b,
const v_float32x8& c, const v_float32x8& d)
{
modules/core/include/opencv2/core/hal/intrin_neon.hpp
+7
View File
@@ -984,6 +984,13 @@ 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)
#if CV_SIMD128_64F
inline double v_reduce_sum(const v_float64x2& a)
{
return vgetq_lane_f64(a.val, 0) + vgetq_lane_f64(a.val, 1);
}
#endif
inline v_float32x4 v_reduce_sum4(const v_float32x4& a, const v_float32x4& b,
const v_float32x4& c, const v_float32x4& d)
{
modules/core/include/opencv2/core/hal/intrin_sse.hpp
+7
View File
@@ -1456,6 +1456,13 @@ OPENCV_HAL_IMPL_SSE_REDUCE_OP_4_SUM(v_uint32x4, unsigned, __m128i, epi32, OPENCV
OPENCV_HAL_IMPL_SSE_REDUCE_OP_4_SUM(v_int32x4, int, __m128i, epi32, OPENCV_HAL_NOP, OPENCV_HAL_NOP, si128_si32)
OPENCV_HAL_IMPL_SSE_REDUCE_OP_4_SUM(v_float32x4, float, __m128, ps, _mm_castps_si128, _mm_castsi128_ps, ss_f32)
inline double v_reduce_sum(const v_float64x2& a)
{
double CV_DECL_ALIGNED(32) idx[2];
v_store_aligned(idx, a);
return idx[0] + idx[1];
}
inline v_float32x4 v_reduce_sum4(const v_float32x4& a, const v_float32x4& b,
const v_float32x4& c, const v_float32x4& d)
{
modules/core/include/opencv2/core/hal/intrin_vsx.hpp
+5
View File
@@ -716,6 +716,11 @@ OPENCV_HAL_IMPL_VSX_REDUCE_OP_4(v_float32x4, vec_float4, float, sum, vec_add)
OPENCV_HAL_IMPL_VSX_REDUCE_OP_4(v_float32x4, vec_float4, float, max, vec_max)
OPENCV_HAL_IMPL_VSX_REDUCE_OP_4(v_float32x4, vec_float4, float, min, vec_min)
inline double v_reduce_sum(const v_float64x2& a)
{
return vec_extract(vec_add(a.val, vec_sld(a.val, a.val, 8)), 0);
}
#define OPENCV_HAL_IMPL_VSX_REDUCE_OP_8(_Tpvec, _Tpvec2, scalartype, suffix, func) \
inline scalartype v_reduce_##suffix(const _Tpvec& a) \
{ \