mirror/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2024-11-27 20:50:25 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Enable dynamic dispatching for Merge3

Browse Source
This commit is contained in:
Aleksei Trutnev 2022-01-27 16:12:53 +03:00
parent f4a7754cc0
commit c62367612d
4 changed files with 59 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
modules/gapi/src/backends/fluid/gfluidcore.cpp
View File

@ -2574,18 +2574,10 @@ GAPI_FLUID_KERNEL(GFluidMerge3, cv::gapi::core::GMerge3, false)
GAPI_Assert(3 == dst.meta().chan);
int width = dst.length();
int w = 0;
int w = 0; // cycle counter
#if CV_SIMD128
for (; w <= width-16; w+=16)
{
v_uint8x16 a, b, c;
a = v_load(&in1[w]);
b = v_load(&in2[w]);
c = v_load(&in3[w]);
v_store_interleave(&out[3*w], a, b, c);
}
#if CV_SIMD
w = merge3_simd(in1, in2, in3, out, width);
#endif
for (; w < width; w++)

7
modules/gapi/src/backends/fluid/gfluidcore_func.dispatch.cpp
View File

@ -221,6 +221,13 @@ int split4_simd(const uchar in[], uchar out1[], uchar out2[],
CV_CPU_DISPATCH_MODES_ALL);
}
int merge3_simd(const uchar in1[], const uchar in2[], const uchar in3[],
uchar out[], const int width)
{
CV_CPU_DISPATCH(merge3_simd, (in1, in2, in3, out, width),
CV_CPU_DISPATCH_MODES_ALL);
}
} // namespace fluid
} // namespace gapi
} // namespace cv

3
modules/gapi/src/backends/fluid/gfluidcore_func.hpp
View File

@ -169,6 +169,9 @@ int split3_simd(const uchar in[], uchar out1[], uchar out2[],
int split4_simd(const uchar in[], uchar out1[], uchar out2[],
uchar out3[], uchar out4[], const int width);
int merge3_simd(const uchar in1[], const uchar in2[], const uchar in3[],
uchar out[], const int width);
} // namespace fluid
} // namespace gapi
} // namespace cv

37
modules/gapi/src/backends/fluid/gfluidcore_func.simd.hpp
View File

@ -190,6 +190,9 @@ int split3_simd(const uchar in[], uchar out1[], uchar out2[],
int split4_simd(const uchar in[], uchar out1[], uchar out2[],
uchar out3[], uchar out4[], const int width);
int merge3_simd(const uchar in1[], const uchar in2[], const uchar in3[],
uchar out[], const int width);
#ifndef CV_CPU_OPTIMIZATION_DECLARATIONS_ONLY
struct scale_tag {};
@ -1643,6 +1646,40 @@ int split4_simd(const uchar in[], uchar out1[], uchar out2[],
return x;
}
//-------------------------
//
// Fluid kernels: Merge3
//
//-------------------------
int merge3_simd(const uchar in1[], const uchar in2[], const uchar in3[],
uchar out[], const int width)
{
constexpr int nlanes = v_uint8::nlanes;
if (width < nlanes)
return 0;
int x = 0;
for (;;)
{
for (; x <= width - nlanes; x += nlanes)
{
v_uint8 a, b, c;
a = vx_load(&in1[x]);
b = vx_load(&in2[x]);
c = vx_load(&in3[x]);
v_store_interleave(&out[3 * x], a, b, c);
}
if (x < width)
{
x = width - nlanes;
continue;
}
break;
}
return x;
}
#endif // CV_CPU_OPTIMIZATION_DECLARATIONS_ONLY
CV_CPU_OPTIMIZATION_NAMESPACE_END