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

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

Browse Source
This commit is contained in:
Alexander Alekhin
2020-03-04 20:49:09 +00:00
parent bc036e1e86 4f288a1e28
commit d4a17da7b2
47 changed files with 750 additions and 353 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/imgproc/src/sumpixels.simd.hpp
+15 -3
View File
@@ -237,7 +237,11 @@ struct Integral_SIMD<uchar, int, double>
v_int32 prev_1 = vx_setzero_s32(), prev_2 = vx_setzero_s32(),
prev_3 = vx_setzero_s32();
int j = 0;
for ( ; j + v_uint16::nlanes * cn <= width; j += v_uint16::nlanes * cn)
const int j_max =
((_srcstep * i + (width - v_uint16::nlanes * cn + v_uint8::nlanes * cn)) >= _srcstep * height)
? width - v_uint8::nlanes * cn // uint8 in v_load_deinterleave()
: width - v_uint16::nlanes * cn; // v_expand_low
for ( ; j <= j_max; j += v_uint16::nlanes * cn)
{
v_uint8 v_src_row_1, v_src_row_2, v_src_row_3;
v_load_deinterleave(src_row + j, v_src_row_1, v_src_row_2, v_src_row_3);
@@ -546,7 +550,11 @@ struct Integral_SIMD<uchar, float, double>
v_float32 prev_1 = vx_setzero_f32(), prev_2 = vx_setzero_f32(),
prev_3 = vx_setzero_f32();
int j = 0;
for (; j + v_uint16::nlanes * cn <= width; j += v_uint16::nlanes * cn)
const int j_max =
((_srcstep * i + (width - v_uint16::nlanes * cn + v_uint8::nlanes * cn)) >= _srcstep * height)
? width - v_uint8::nlanes * cn // uint8 in v_load_deinterleave()
: width - v_uint16::nlanes * cn; // v_expand_low
for ( ; j <= j_max; j += v_uint16::nlanes * cn)
{
v_uint8 v_src_row_1, v_src_row_2, v_src_row_3;
v_load_deinterleave(src_row + j, v_src_row_1, v_src_row_2, v_src_row_3);
@@ -896,7 +904,11 @@ struct Integral_SIMD<uchar, double, double>
v_float64 prev_1 = vx_setzero_f64(), prev_2 = vx_setzero_f64(),
prev_3 = vx_setzero_f64();
int j = 0;
for (; j + v_uint16::nlanes * cn <= width; j += v_uint16::nlanes * cn)
const int j_max =
((_srcstep * i + (width - v_uint16::nlanes * cn + v_uint8::nlanes * cn)) >= _srcstep * height)
? width - v_uint8::nlanes * cn // uint8 in v_load_deinterleave()
: width - v_uint16::nlanes * cn; // v_expand_low
for ( ; j <= j_max; j += v_uint16::nlanes * cn)
{
v_uint8 v_src_row_1, v_src_row_2, v_src_row_3;
v_load_deinterleave(src_row + j, v_src_row_1, v_src_row_2, v_src_row_3);