potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-29 15:23:05 +04:00
Code Packages Releases Wiki Activity

Merge branch 4.x

Browse Source
This commit is contained in:
Alexander Smorkalov
2023-09-11 13:22:22 +03:00
parent a6748df587 ee867ead1d
commit fdab565711
148 changed files with 2384 additions and 1876 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/core/src/arithm.cpp
+26 -26
View File
@@ -1335,7 +1335,7 @@ struct InRange_SIMD
}
};
#if CV_SIMD
#if (CV_SIMD || CV_SIMD_SCALABLE)
template <>
struct InRange_SIMD<uchar>
@@ -1344,7 +1344,7 @@ struct InRange_SIMD<uchar>
uchar * dst, int len) const
{
int x = 0;
const int width = v_uint8::nlanes;
const int width = VTraits<v_uint8>::vlanes();
for (; x <= len - width; x += width)
{
@@ -1352,7 +1352,7 @@ struct InRange_SIMD<uchar>
v_uint8 low = vx_load(src2 + x);
v_uint8 high = vx_load(src3 + x);
v_store(dst + x, (values >= low) & (high >= values));
v_store(dst + x, v_and(v_ge(values, low), v_ge(high, values)));
}
vx_cleanup();
return x;
@@ -1366,7 +1366,7 @@ struct InRange_SIMD<schar>
uchar * dst, int len) const
{
int x = 0;
const int width = v_int8::nlanes;
const int width = VTraits<v_int8>::vlanes();
for (; x <= len - width; x += width)
{
@@ -1374,7 +1374,7 @@ struct InRange_SIMD<schar>
v_int8 low = vx_load(src2 + x);
v_int8 high = vx_load(src3 + x);
v_store((schar*)(dst + x), (values >= low) & (high >= values));
v_store((schar*)(dst + x), v_and(v_ge(values, low), v_ge(high, values)));
}
vx_cleanup();
return x;
@@ -1388,7 +1388,7 @@ struct InRange_SIMD<ushort>
uchar * dst, int len) const
{
int x = 0;
const int width = v_uint16::nlanes * 2;
const int width = VTraits<v_uint16>::vlanes() * 2;
for (; x <= len - width; x += width)
{
@@ -1396,11 +1396,11 @@ struct InRange_SIMD<ushort>
v_uint16 low1 = vx_load(src2 + x);
v_uint16 high1 = vx_load(src3 + x);
v_uint16 values2 = vx_load(src1 + x + v_uint16::nlanes);
v_uint16 low2 = vx_load(src2 + x + v_uint16::nlanes);
v_uint16 high2 = vx_load(src3 + x + v_uint16::nlanes);
v_uint16 values2 = vx_load(src1 + x + VTraits<v_uint16>::vlanes());
v_uint16 low2 = vx_load(src2 + x + VTraits<v_uint16>::vlanes());
v_uint16 high2 = vx_load(src3 + x + VTraits<v_uint16>::vlanes());
v_store(dst + x, v_pack((values1 >= low1) & (high1 >= values1), (values2 >= low2) & (high2 >= values2)));
v_store(dst + x, v_pack(v_and(v_ge(values1, low1), v_ge(high1, values1)), v_and(v_ge(values2, low2), v_ge(high2, values2))));
}
vx_cleanup();
return x;
@@ -1414,7 +1414,7 @@ struct InRange_SIMD<short>
uchar * dst, int len) const
{
int x = 0;
const int width = (int)v_int16::nlanes * 2;
const int width = (int)VTraits<v_int16>::vlanes() * 2;
for (; x <= len - width; x += width)
{
@@ -1422,11 +1422,11 @@ struct InRange_SIMD<short>
v_int16 low1 = vx_load(src2 + x);
v_int16 high1 = vx_load(src3 + x);
v_int16 values2 = vx_load(src1 + x + v_int16::nlanes);
v_int16 low2 = vx_load(src2 + x + v_int16::nlanes);
v_int16 high2 = vx_load(src3 + x + v_int16::nlanes);
v_int16 values2 = vx_load(src1 + x + VTraits<v_int16>::vlanes());
v_int16 low2 = vx_load(src2 + x + VTraits<v_int16>::vlanes());
v_int16 high2 = vx_load(src3 + x + VTraits<v_int16>::vlanes());
v_store((schar*)(dst + x), v_pack((values1 >= low1) & (high1 >= values1), (values2 >= low2) & (high2 >= values2)));
v_store((schar*)(dst + x), v_pack(v_and(v_ge(values1, low1), v_ge(high1, values1)), v_and(v_ge(values2, low2), v_ge(high2, values2))));
}
vx_cleanup();
return x;
@@ -1440,7 +1440,7 @@ struct InRange_SIMD<int>
uchar * dst, int len) const
{
int x = 0;
const int width = (int)v_int32::nlanes * 2;
const int width = (int)VTraits<v_int32>::vlanes() * 2;
for (; x <= len - width; x += width)
{
@@ -1448,11 +1448,11 @@ struct InRange_SIMD<int>
v_int32 low1 = vx_load(src2 + x);
v_int32 high1 = vx_load(src3 + x);
v_int32 values2 = vx_load(src1 + x + v_int32::nlanes);
v_int32 low2 = vx_load(src2 + x + v_int32::nlanes);
v_int32 high2 = vx_load(src3 + x + v_int32::nlanes);
v_int32 values2 = vx_load(src1 + x + VTraits<v_int32>::vlanes());
v_int32 low2 = vx_load(src2 + x + VTraits<v_int32>::vlanes());
v_int32 high2 = vx_load(src3 + x + VTraits<v_int32>::vlanes());
v_pack_store(dst + x, v_reinterpret_as_u16(v_pack((values1 >= low1) & (high1 >= values1), (values2 >= low2) & (high2 >= values2))));
v_pack_store(dst + x, v_reinterpret_as_u16(v_pack(v_and(v_ge(values1, low1), v_ge(high1, values1)), v_and(v_ge(values2, low2), v_ge(high2, values2)))));
}
vx_cleanup();
return x;
@@ -1466,7 +1466,7 @@ struct InRange_SIMD<float>
uchar * dst, int len) const
{
int x = 0;
const int width = (int)v_float32::nlanes * 2;
const int width = (int)VTraits<v_float32>::vlanes() * 2;
for (; x <= len - width; x += width)
{
@@ -1474,12 +1474,12 @@ struct InRange_SIMD<float>
v_float32 low1 = vx_load(src2 + x);
v_float32 high1 = vx_load(src3 + x);
v_float32 values2 = vx_load(src1 + x + v_float32::nlanes);
v_float32 low2 = vx_load(src2 + x + v_float32::nlanes);
v_float32 high2 = vx_load(src3 + x + v_float32::nlanes);
v_float32 values2 = vx_load(src1 + x + VTraits<v_float32>::vlanes());
v_float32 low2 = vx_load(src2 + x + VTraits<v_float32>::vlanes());
v_float32 high2 = vx_load(src3 + x + VTraits<v_float32>::vlanes());
v_pack_store(dst + x, v_pack(v_reinterpret_as_u32(values1 >= low1) & v_reinterpret_as_u32(high1 >= values1),
v_reinterpret_as_u32(values2 >= low2) & v_reinterpret_as_u32(high2 >= values2)));
v_pack_store(dst + x, v_pack(v_and(v_reinterpret_as_u32(v_ge(values1, low1)), v_reinterpret_as_u32(v_ge(high1, values1))),
v_and(v_reinterpret_as_u32(v_ge(values2, low2)), v_reinterpret_as_u32(v_ge(high2, values2)))));
}
vx_cleanup();
return x;