1
0
mirror of https://github.com/opencv/opencv.git synced 2026-07-29 23:33:05 +04:00

Merge pull request #26821 from fengyuentau:core/transform_simd

Core: vectorize cv::transform in terms of all data types #26821

## Performance

### i7-12700K

```
Geometric mean (ms)

                      Name of Test                       base  patch   patch
                                                                         vs
                                                                        base
                                                                     (x-factor)
Mat_Transform::Size_MatType::(127x61, 8SC3)              0.017 0.004    4.64
Mat_Transform::Size_MatType::(127x61, 16SC3)             0.015 0.004    3.78
Mat_Transform::Size_MatType::(127x61, 32SC3)             0.015 0.007    2.03
Mat_Transform::Size_MatType::(127x61, 64FC3)             0.007 0.004    1.78
Mat_Transform::Size_MatType::(640x480, 8SC3)             0.673 0.140    4.80
Mat_Transform::Size_MatType::(640x480, 16SC3)            0.618 0.158    3.90
Mat_Transform::Size_MatType::(640x480, 32SC3)            0.579 0.278    2.08
Mat_Transform::Size_MatType::(640x480, 64FC3)            0.290 0.266    1.09
Mat_Transform::Size_MatType::(1280x720, 8SC3)            1.919 0.414    4.63
Mat_Transform::Size_MatType::(1280x720, 16SC3)           1.811 0.488    3.71
Mat_Transform::Size_MatType::(1280x720, 32SC3)           1.736 0.917    1.89
Mat_Transform::Size_MatType::(1280x720, 64FC3)           2.310 2.030    1.14
Mat_Transform::Size_MatType::(1920x1080, 8SC3)           4.339 0.924    4.70
Mat_Transform::Size_MatType::(1920x1080, 16SC3)          4.095 1.288    3.18
Mat_Transform::Size_MatType::(1920x1080, 32SC3)          4.267 3.191    1.34
Mat_Transform::Size_MatType::(1920x1080, 64FC3)          6.641 5.481    1.21
Mat_Transform_Diagonal::Size_MatType::(640x480, 8SC3)    0.415 0.104    3.98
Mat_Transform_Diagonal::Size_MatType::(640x480, 16SC3)   0.385 0.128    3.00
Mat_Transform_Diagonal::Size_MatType::(640x480, 32SC3)   0.389 0.225    1.72
Mat_Transform_Diagonal::Size_MatType::(640x480, 64FC3)   0.279 0.275    1.01
Mat_Transform_Diagonal::Size_MatType::(1280x720, 8SC3)   1.223 0.313    3.91
Mat_Transform_Diagonal::Size_MatType::(1280x720, 16SC3)  1.118 0.387    2.89
Mat_Transform_Diagonal::Size_MatType::(1280x720, 32SC3)  1.215 0.801    1.52
Mat_Transform_Diagonal::Size_MatType::(1280x720, 64FC3)  2.198 1.900    1.16
Mat_Transform_Diagonal::Size_MatType::(1920x1080, 8SC3)  2.772 0.705    3.93
Mat_Transform_Diagonal::Size_MatType::(1920x1080, 16SC3) 2.572 1.134    2.27
Mat_Transform_Diagonal::Size_MatType::(1920x1080, 32SC3) 3.477 3.276    1.06
Mat_Transform_Diagonal::Size_MatType::(1920x1080, 64FC3) 5.984 5.186    1.15
```

### A311D

```
Geometric mean (ms)

                      Name of Test                        base  patch    patch
                                                                           vs
                                                                          base
                                                                       (x-factor)
Mat_Transform::Size_MatType::(127x61, 8SC3)              0.143  0.035     4.05
Mat_Transform::Size_MatType::(127x61, 16SC3)             0.135  0.037     3.67
Mat_Transform::Size_MatType::(127x61, 32SC3)             0.110  0.062     1.77
Mat_Transform::Size_MatType::(127x61, 64FC3)             0.034  0.039     0.89
Mat_Transform::Size_MatType::(640x480, 8SC3)             5.673  1.395     4.07
Mat_Transform::Size_MatType::(640x480, 16SC3)            5.331  1.439     3.70
Mat_Transform::Size_MatType::(640x480, 32SC3)            4.329  2.472     1.75
Mat_Transform::Size_MatType::(640x480, 64FC3)            1.560  2.316     0.67
Mat_Transform::Size_MatType::(1280x720, 8SC3)            17.002 4.139     4.11
Mat_Transform::Size_MatType::(1280x720, 16SC3)           15.996 4.308     3.71
Mat_Transform::Size_MatType::(1280x720, 32SC3)           12.948 7.241     1.79
Mat_Transform::Size_MatType::(1280x720, 64FC3)           4.742  7.376     0.64
Mat_Transform::Size_MatType::(1920x1080, 8SC3)           38.253 9.384     4.08
Mat_Transform::Size_MatType::(1920x1080, 16SC3)          35.913 9.750     3.68
Mat_Transform::Size_MatType::(1920x1080, 32SC3)          29.145 16.528    1.76
Mat_Transform::Size_MatType::(1920x1080, 64FC3)          10.606 20.968    0.51
Mat_Transform_Diagonal::Size_MatType::(640x480, 8SC3)    4.439  1.086     4.09
Mat_Transform_Diagonal::Size_MatType::(640x480, 16SC3)   4.251  1.136     3.74
Mat_Transform_Diagonal::Size_MatType::(640x480, 32SC3)   3.786  1.999     1.89
Mat_Transform_Diagonal::Size_MatType::(640x480, 64FC3)   1.555  1.551     1.00
Mat_Transform_Diagonal::Size_MatType::(1280x720, 8SC3)   13.319 3.243     4.11
Mat_Transform_Diagonal::Size_MatType::(1280x720, 16SC3)  12.828 3.398     3.78
Mat_Transform_Diagonal::Size_MatType::(1280x720, 32SC3)  11.336 5.989     1.89
Mat_Transform_Diagonal::Size_MatType::(1280x720, 64FC3)  4.707  4.690     1.00
Mat_Transform_Diagonal::Size_MatType::(1920x1080, 8SC3)  29.952 7.293     4.11
Mat_Transform_Diagonal::Size_MatType::(1920x1080, 16SC3) 28.817 7.656     3.76
Mat_Transform_Diagonal::Size_MatType::(1920x1080, 32SC3) 25.476 13.388    1.90
Mat_Transform_Diagonal::Size_MatType::(1920x1080, 64FC3) 10.533 10.509    1.00
```

### M2

```
Geometric mean (ms)

                      Name of Test                       base  patch   patch
                                                                         vs
                                                                        base
                                                                     (x-factor)
Mat_Transform::Size_MatType::(127x61, 8SC3)              0.020 0.004    4.45
Mat_Transform::Size_MatType::(127x61, 16SC3)             0.016 0.004    4.48
Mat_Transform::Size_MatType::(127x61, 32SC3)             0.016 0.007    2.23
Mat_Transform::Size_MatType::(127x61, 64FC3)             0.007 0.006    1.20
Mat_Transform::Size_MatType::(640x480, 8SC3)             0.793 0.197    4.03
Mat_Transform::Size_MatType::(640x480, 16SC3)            0.626 0.154    4.08
Mat_Transform::Size_MatType::(640x480, 32SC3)            0.627 0.306    2.05
Mat_Transform::Size_MatType::(640x480, 64FC3)            0.273 0.253    1.08
Mat_Transform::Size_MatType::(1280x720, 8SC3)            2.350 0.540    4.35
Mat_Transform::Size_MatType::(1280x720, 16SC3)           1.875 0.415    4.52
Mat_Transform::Size_MatType::(1280x720, 32SC3)           1.893 0.844    2.24
Mat_Transform::Size_MatType::(1280x720, 64FC3)           0.830 0.808    1.03
Mat_Transform::Size_MatType::(1920x1080, 8SC3)           5.302 1.178    4.50
Mat_Transform::Size_MatType::(1920x1080, 16SC3)          4.475 0.946    4.73
Mat_Transform::Size_MatType::(1920x1080, 32SC3)          4.409 1.864    2.37
Mat_Transform::Size_MatType::(1920x1080, 64FC3)          1.853 1.512    1.23
Mat_Transform_Diagonal::Size_MatType::(640x480, 8SC3)    0.586 0.110    5.32
Mat_Transform_Diagonal::Size_MatType::(640x480, 16SC3)   0.518 0.110    4.69
Mat_Transform_Diagonal::Size_MatType::(640x480, 32SC3)   0.430 0.220    1.95
Mat_Transform_Diagonal::Size_MatType::(640x480, 64FC3)   0.228 0.178    1.28
Mat_Transform_Diagonal::Size_MatType::(1280x720, 8SC3)   1.768 0.336    5.26
Mat_Transform_Diagonal::Size_MatType::(1280x720, 16SC3)  1.514 0.335    4.52
Mat_Transform_Diagonal::Size_MatType::(1280x720, 32SC3)  1.292 0.670    1.93
Mat_Transform_Diagonal::Size_MatType::(1280x720, 64FC3)  0.681 0.579    1.18
Mat_Transform_Diagonal::Size_MatType::(1920x1080, 8SC3)  3.998 0.747    5.35
Mat_Transform_Diagonal::Size_MatType::(1920x1080, 16SC3) 3.392 0.757    4.48
Mat_Transform_Diagonal::Size_MatType::(1920x1080, 32SC3) 2.956 1.491    1.98
Mat_Transform_Diagonal::Size_MatType::(1920x1080, 64FC3) 1.546 1.476    1.05
```


### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
This commit is contained in:
Yuantao Feng
2025-02-06 18:38:16 +08:00
committed by GitHub
parent 28deafcbd4
commit 603b1cafdf
2 changed files with 550 additions and 0 deletions
+26
View File
@@ -166,4 +166,30 @@ PERF_TEST_P(Size_MatType, Mat_Transform,
SANITY_CHECK(dst, 1e-6, ERROR_RELATIVE);
}
PERF_TEST_P(Size_MatType, Mat_Transform_Diagonal,
testing::Combine(testing::Values(szVGA, sz720p, sz1080p),
testing::Values(CV_8UC3, CV_8SC3, CV_16UC3, CV_16SC3, CV_32SC3, CV_32FC3, CV_64FC3))
)
{
const Size_MatType_t params = GetParam();
const Size srcSize0 = get<0>(params);
const Size srcSize = Size(1, srcSize0.width*srcSize0.height);
const int type = get<1>(params);
const float transform[] = { 0.5f, 0.f, 0.f, 128,
0.f, 0.86602540378f, 0.f, -64,
0.f, 0.f, 0.4330127019f, 32, };
Mat mtx(Size(4, 3), CV_32FC1, (void*)transform);
Mat src(srcSize, type), dst(srcSize, type);
randu(src, 0, 30);
declare.in(src).out(dst);
TEST_CYCLE()
{
cv::transform(src, dst, mtx);
}
SANITY_CHECK(dst, 1e-6, ERROR_RELATIVE);
}
} // namespace