Merge pull request #22947 from chacha21:hasNonZero

chacha21 · web-flow · commit 60b806f9b858 · 2023-06-09T13:37:20.000+03:00
Added cv::hasNonZero() #22947 

`cv::hasNonZero()` is semantically equivalent to (`cv::countNonZero()&gt;0`) but stops parsing the image when a non-zero value is found, for a performance gain

- [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
- [ ] 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 pull request might be refused, but I submit it to know if further work is needed or if I just stop working on it.
The idea is only a performance gain vs `countNonZero()&gt;0` at the cost of more code.

Reasons why it might be refused :

- this is just more code
- the execution time is "unfair"/"unpredictable" since it depends on the position of the first non-zero value
- the user must be aware that default search is from first row/col to last row/col and has no way to customize that, even if his use case lets him know where a non zero could be found
- the PR in its current state is using, for the ocl implementation, a mere `countNonZero()&gt;0` ; there is not much sense in trying to break early the ocl kernel call when non-zero is encountered. So the ocl implementation does not bring any improvement.
- there is no IPP function that can help (`countNonZero()` is based in `ippCountInRange`)
- the PR in its current state might be slower than a call to `countNonZero()&gt;0` in some cases (see "challenges" below)

Reasons why it might be accepted :

- the performance gain is huge on average, if we consider that "on average" means "non zero in the middle of the image"
- the "missing" IPP implementation is replaced by an "Open-CV universal intrinsics" implementation
- the PR in its current state is almost always faster than a call to `countNonZero()&gt;0`, is only slightly slower in the worst cases, and not even for all matrices

**Challenges**
The worst case is either an all-zero matrix, or a non-zero at the very last position.  In such a case, the `hasNonZero()` implementation will parse the whole matrix like `countNonZero()` would do. But we expect the performance to be the same in this case. And `ippCountInRange` is hard to beat !
There is also the case of very small matrices (&lt;=32x32...) in 8b, where the SIMD can be hard to feed.

For all cases but the worse, my custom `hasNonZero()` performs better than `ippCountInRange()`
For the worst case, my custom `hasNonZero()` performs better than `ippCountInRange()` *except for large matrices of type CV_32S or CV_64F* (but surprisingly, not CV_32F).
The difference is small, but it exists (and I don't understand why).
For very small CV_8U matrices `ippCountInRange()` seems unbeatable.

Here is the code that I use to check timings

```

  //test cv::hasNonZero() vs (cv::countNonZero()&gt;0) for different matrices sizes, types, strides...
  {
    cv::setRNGSeed(1234);
    const std::vector&lt;cv::Size&gt; sizes = {{32, 32}, {64, 64}, {128, 128}, {320, 240}, {512, 512}, {640, 480}, {1024, 768}, {2048, 2048}, {1031, 1000}};
    const std::vector&lt;int&gt; types = {CV_8U, CV_16U, CV_32S, CV_32F, CV_64F};
    const size_t iterations = 1000;
    for(const cv::Size&amp; size : sizes)
    {
      for(const int type : types)
      {
        for(int c = 0 ; c&lt;2 ; ++c)
        {
          const bool continuous = !c;
          for(int i = 0 ; i&lt;4 ; ++i)
          {
            cv::Mat m = continuous ? cv::Mat::zeros(size, type) : cv::Mat(cv::Mat::zeros(cv::Size(2*size.width, size.height), type), cv::Rect(cv::Point(0, 0), size));
            const bool nz = (i &lt;= 2);
            const unsigned int nzOffsetRange = 10;
            const unsigned int nzOffset = cv::randu&lt;unsigned int&gt;()%nzOffsetRange;
            const cv::Point pos = 
              (i == 0) ? cv::Point(nzOffset, 0) :
              (i == 1) ? cv::Point(size.width/2-nzOffsetRange/2+nzOffset, size.height/2) :
              (i == 2) ? cv::Point(size.width-1-nzOffset, size.height-1) :
              cv::Point(0, 0);
            std::cout &lt;&lt; "============================================================" &lt;&lt; std::endl;
            std::cout &lt;&lt; "size:" &lt;&lt; size &lt;&lt; "  type:" &lt;&lt; type &lt;&lt; "  continuous = " &lt;&lt; (continuous ? "true" : "false") &lt;&lt; "  iterations:" &lt;&lt; iterations &lt;&lt; "  nz=" &lt;&lt; (nz ? "true" : "false");
            std::cout &lt;&lt; "  pos=" &lt;&lt; ((i == 0) ? "begin" : (i == 1) ? "middle" : (i == 2) ? "end" : "none");
            std::cout &lt;&lt; std::endl;
            cv::Mat mask = cv::Mat::zeros(size, CV_8UC1);
            mask.at&lt;unsigned char&gt;(pos) = 0xFF;
            m.setTo(cv::Scalar::all(0));
            m.setTo(cv::Scalar::all(nz ? 1 : 0), mask);
            std::vector&lt;bool&gt; results;
            std::vector&lt;double&gt; timings;

            {
              bool res = false;
              auto ref = cv::getTickCount();
              for(size_t k = 0 ; k&lt;iterations ; ++k)
                res = cv::hasNonZero(m);
              auto now = cv::getTickCount();
              const bool error = (res != nz);
              if (error)
                printf("!!ERROR!!\r\n");
              results.push_back(res);
              timings.push_back(1000.*(now-ref)/cv::getTickFrequency());
            }
            {
              bool res = false;
              auto ref = cv::getTickCount();
              for(size_t k = 0 ; k&lt;iterations ; ++k)
                res = (cv::countNonZero(m)&gt;0);
              auto now = cv::getTickCount();
              const bool error = (res != nz);
              if (error)
                printf("!!ERROR!!\r\n");
              results.push_back(res);
              timings.push_back(1000.*(now-ref)/cv::getTickFrequency());
            }

            const size_t bestTimingIndex = (std::min_element(timings.begin(), timings.end())-timings.begin());
            if ((bestTimingIndex != 0) || (std::find_if_not(results.begin(), results.end(), [&amp;](bool r) {return (r == nz);}) != results.end()))
            {
              std::cout &lt;&lt; "cv::hasNonZero\t\t=&gt;" &lt;&lt; results[0] &lt;&lt; ((results[0] != nz) ? "  ERROR" : "") &lt;&lt; "   perf:" &lt;&lt; timings[0] &lt;&lt; "ms =&gt; " &lt;&lt; (iterations/timings[0]*1000) &lt;&lt; " im/s" &lt;&lt; ((bestTimingIndex == 0) ? " * " : "") &lt;&lt; std::endl;
              std::cout &lt;&lt; "cv::countNonZero\t=&gt;" &lt;&lt; results[1] &lt;&lt; ((results[1] != nz) ? "  ERROR" : "") &lt;&lt; "   perf:" &lt;&lt; timings[1] &lt;&lt; "ms =&gt; " &lt;&lt; (iterations/timings[1]*1000) &lt;&lt; " im/s" &lt;&lt; ((bestTimingIndex == 1) ? " * " : "") &lt;&lt; std::endl;
            }
          }
        }
      }
    }
  }

```

Here is a report of this benchmark (it only reports timings when `cv::countNonZero()` is faster)
My CPU is an Intel Core I7 4790 @ 3.60Ghz

```

============================================================
size:[32 x 32]  type:0  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[32 x 32]  type:0  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[32 x 32]  type:0  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[32 x 32]  type:0  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[32 x 32]  type:0  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[32 x 32]  type:0  continuous = false  iterations:1000  nz=true  pos=middle
cv::hasNonZero          =&gt;1   perf:0.353764ms =&gt; 2.82674e+06 im/s
cv::countNonZero        =&gt;1   perf:0.282044ms =&gt; 3.54555e+06 im/s *
============================================================
size:[32 x 32]  type:0  continuous = false  iterations:1000  nz=true  pos=end
cv::hasNonZero          =&gt;1   perf:0.610478ms =&gt; 1.63806e+06 im/s
cv::countNonZero        =&gt;1   perf:0.283182ms =&gt; 3.5313e+06 im/s *
============================================================
size:[32 x 32]  type:0  continuous = false  iterations:1000  nz=false  pos=none
cv::hasNonZero          =&gt;0   perf:0.630115ms =&gt; 1.58701e+06 im/s
cv::countNonZero        =&gt;0   perf:0.282044ms =&gt; 3.54555e+06 im/s *
============================================================
size:[32 x 32]  type:2  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[32 x 32]  type:2  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[32 x 32]  type:2  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[32 x 32]  type:2  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[32 x 32]  type:2  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[32 x 32]  type:2  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[32 x 32]  type:2  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[32 x 32]  type:2  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[32 x 32]  type:4  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[32 x 32]  type:4  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[32 x 32]  type:4  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[32 x 32]  type:4  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[32 x 32]  type:4  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[32 x 32]  type:4  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[32 x 32]  type:4  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[32 x 32]  type:4  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[32 x 32]  type:5  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[32 x 32]  type:5  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[32 x 32]  type:5  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[32 x 32]  type:5  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[32 x 32]  type:5  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[32 x 32]  type:5  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[32 x 32]  type:5  continuous = false  iterations:1000  nz=true  pos=end
cv::hasNonZero          =&gt;1   perf:0.607347ms =&gt; 1.64651e+06 im/s
cv::countNonZero        =&gt;1   perf:0.467037ms =&gt; 2.14116e+06 im/s *
============================================================
size:[32 x 32]  type:5  continuous = false  iterations:1000  nz=false  pos=none
cv::hasNonZero          =&gt;0   perf:0.618162ms =&gt; 1.6177e+06 im/s
cv::countNonZero        =&gt;0   perf:0.468175ms =&gt; 2.13595e+06 im/s *
============================================================
size:[32 x 32]  type:6  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[32 x 32]  type:6  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[32 x 32]  type:6  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[32 x 32]  type:6  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[32 x 32]  type:6  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[32 x 32]  type:6  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[32 x 32]  type:6  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[32 x 32]  type:6  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[64 x 64]  type:0  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[64 x 64]  type:0  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[64 x 64]  type:0  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[64 x 64]  type:0  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[64 x 64]  type:0  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[64 x 64]  type:0  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[64 x 64]  type:0  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[64 x 64]  type:0  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[64 x 64]  type:2  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[64 x 64]  type:2  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[64 x 64]  type:2  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[64 x 64]  type:2  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[64 x 64]  type:2  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[64 x 64]  type:2  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[64 x 64]  type:2  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[64 x 64]  type:2  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[64 x 64]  type:4  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[64 x 64]  type:4  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[64 x 64]  type:4  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[64 x 64]  type:4  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[64 x 64]  type:4  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[64 x 64]  type:4  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[64 x 64]  type:4  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[64 x 64]  type:4  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[64 x 64]  type:5  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[64 x 64]  type:5  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[64 x 64]  type:5  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[64 x 64]  type:5  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[64 x 64]  type:5  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[64 x 64]  type:5  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[64 x 64]  type:5  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[64 x 64]  type:5  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[64 x 64]  type:6  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[64 x 64]  type:6  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[64 x 64]  type:6  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[64 x 64]  type:6  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[64 x 64]  type:6  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[64 x 64]  type:6  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[64 x 64]  type:6  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[64 x 64]  type:6  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[128 x 128]  type:0  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[128 x 128]  type:0  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[128 x 128]  type:0  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[128 x 128]  type:0  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[128 x 128]  type:0  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[128 x 128]  type:0  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[128 x 128]  type:0  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[128 x 128]  type:0  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[128 x 128]  type:2  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[128 x 128]  type:2  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[128 x 128]  type:2  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[128 x 128]  type:2  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[128 x 128]  type:2  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[128 x 128]  type:2  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[128 x 128]  type:2  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[128 x 128]  type:2  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[128 x 128]  type:4  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[128 x 128]  type:4  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[128 x 128]  type:4  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[128 x 128]  type:4  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[128 x 128]  type:4  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[128 x 128]  type:4  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[128 x 128]  type:4  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[128 x 128]  type:4  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[128 x 128]  type:5  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[128 x 128]  type:5  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[128 x 128]  type:5  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[128 x 128]  type:5  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[128 x 128]  type:5  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[128 x 128]  type:5  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[128 x 128]  type:5  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[128 x 128]  type:5  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[128 x 128]  type:6  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[128 x 128]  type:6  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[128 x 128]  type:6  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[128 x 128]  type:6  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[128 x 128]  type:6  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[128 x 128]  type:6  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[128 x 128]  type:6  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[128 x 128]  type:6  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[320 x 240]  type:0  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[320 x 240]  type:0  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[320 x 240]  type:0  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[320 x 240]  type:0  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[320 x 240]  type:0  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[320 x 240]  type:0  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[320 x 240]  type:0  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[320 x 240]  type:0  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[320 x 240]  type:2  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[320 x 240]  type:2  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[320 x 240]  type:2  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[320 x 240]  type:2  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[320 x 240]  type:2  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[320 x 240]  type:2  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[320 x 240]  type:2  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[320 x 240]  type:2  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[320 x 240]  type:4  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[320 x 240]  type:4  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[320 x 240]  type:4  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[320 x 240]  type:4  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[320 x 240]  type:4  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[320 x 240]  type:4  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[320 x 240]  type:4  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[320 x 240]  type:4  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[320 x 240]  type:5  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[320 x 240]  type:5  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[320 x 240]  type:5  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[320 x 240]  type:5  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[320 x 240]  type:5  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[320 x 240]  type:5  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[320 x 240]  type:5  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[320 x 240]  type:5  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[320 x 240]  type:6  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[320 x 240]  type:6  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[320 x 240]  type:6  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[320 x 240]  type:6  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[320 x 240]  type:6  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[320 x 240]  type:6  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[320 x 240]  type:6  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[320 x 240]  type:6  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[512 x 512]  type:0  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[512 x 512]  type:0  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[512 x 512]  type:0  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[512 x 512]  type:0  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[512 x 512]  type:0  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[512 x 512]  type:0  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[512 x 512]  type:0  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[512 x 512]  type:0  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[512 x 512]  type:2  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[512 x 512]  type:2  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[512 x 512]  type:2  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[512 x 512]  type:2  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[512 x 512]  type:2  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[512 x 512]  type:2  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[512 x 512]  type:2  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[512 x 512]  type:2  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[512 x 512]  type:4  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[512 x 512]  type:4  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[512 x 512]  type:4  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[512 x 512]  type:4  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[512 x 512]  type:4  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[512 x 512]  type:4  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[512 x 512]  type:4  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[512 x 512]  type:4  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[512 x 512]  type:5  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[512 x 512]  type:5  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[512 x 512]  type:5  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[512 x 512]  type:5  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[512 x 512]  type:5  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[512 x 512]  type:5  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[512 x 512]  type:5  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[512 x 512]  type:5  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[512 x 512]  type:6  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[512 x 512]  type:6  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[512 x 512]  type:6  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[512 x 512]  type:6  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[512 x 512]  type:6  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[512 x 512]  type:6  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[512 x 512]  type:6  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[512 x 512]  type:6  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[640 x 480]  type:0  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[640 x 480]  type:0  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[640 x 480]  type:0  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[640 x 480]  type:0  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[640 x 480]  type:0  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[640 x 480]  type:0  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[640 x 480]  type:0  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[640 x 480]  type:0  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[640 x 480]  type:2  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[640 x 480]  type:2  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[640 x 480]  type:2  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[640 x 480]  type:2  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[640 x 480]  type:2  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[640 x 480]  type:2  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[640 x 480]  type:2  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[640 x 480]  type:2  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[640 x 480]  type:4  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[640 x 480]  type:4  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[640 x 480]  type:4  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[640 x 480]  type:4  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[640 x 480]  type:4  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[640 x 480]  type:4  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[640 x 480]  type:4  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[640 x 480]  type:4  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[640 x 480]  type:5  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[640 x 480]  type:5  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[640 x 480]  type:5  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[640 x 480]  type:5  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[640 x 480]  type:5  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[640 x 480]  type:5  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[640 x 480]  type:5  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[640 x 480]  type:5  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[640 x 480]  type:6  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[640 x 480]  type:6  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[640 x 480]  type:6  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[640 x 480]  type:6  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[640 x 480]  type:6  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[640 x 480]  type:6  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[640 x 480]  type:6  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[640 x 480]  type:6  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[1024 x 768]  type:0  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[1024 x 768]  type:0  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[1024 x 768]  type:0  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[1024 x 768]  type:0  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[1024 x 768]  type:0  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[1024 x 768]  type:0  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[1024 x 768]  type:0  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[1024 x 768]  type:0  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[1024 x 768]  type:2  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[1024 x 768]  type:2  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[1024 x 768]  type:2  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[1024 x 768]  type:2  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[1024 x 768]  type:2  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[1024 x 768]  type:2  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[1024 x 768]  type:2  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[1024 x 768]  type:2  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[1024 x 768]  type:4  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[1024 x 768]  type:4  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[1024 x 768]  type:4  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[1024 x 768]  type:4  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[1024 x 768]  type:4  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[1024 x 768]  type:4  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[1024 x 768]  type:4  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[1024 x 768]  type:4  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[1024 x 768]  type:5  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[1024 x 768]  type:5  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[1024 x 768]  type:5  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[1024 x 768]  type:5  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[1024 x 768]  type:5  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[1024 x 768]  type:5  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[1024 x 768]  type:5  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[1024 x 768]  type:5  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[1024 x 768]  type:6  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[1024 x 768]  type:6  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[1024 x 768]  type:6  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[1024 x 768]  type:6  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[1024 x 768]  type:6  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[1024 x 768]  type:6  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[1024 x 768]  type:6  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[1024 x 768]  type:6  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[2048 x 2048]  type:0  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[2048 x 2048]  type:0  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[2048 x 2048]  type:0  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[2048 x 2048]  type:0  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[2048 x 2048]  type:0  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[2048 x 2048]  type:0  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[2048 x 2048]  type:0  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[2048 x 2048]  type:0  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[2048 x 2048]  type:2  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[2048 x 2048]  type:2  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[2048 x 2048]  type:2  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[2048 x 2048]  type:2  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[2048 x 2048]  type:2  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[2048 x 2048]  type:2  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[2048 x 2048]  type:2  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[2048 x 2048]  type:2  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[2048 x 2048]  type:4  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[2048 x 2048]  type:4  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[2048 x 2048]  type:4  continuous = true  iterations:1000  nz=true  pos=end
cv::hasNonZero          =&gt;1   perf:895.381ms =&gt; 1116.84 im/s
cv::countNonZero        =&gt;1   perf:882.569ms =&gt; 1133.06 im/s *
============================================================
size:[2048 x 2048]  type:4  continuous = true  iterations:1000  nz=false  pos=none
cv::hasNonZero          =&gt;0   perf:899.53ms =&gt; 1111.69 im/s
cv::countNonZero        =&gt;0   perf:870.894ms =&gt; 1148.24 im/s *
============================================================
size:[2048 x 2048]  type:4  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[2048 x 2048]  type:4  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[2048 x 2048]  type:4  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[2048 x 2048]  type:4  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[2048 x 2048]  type:5  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[2048 x 2048]  type:5  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[2048 x 2048]  type:5  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[2048 x 2048]  type:5  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[2048 x 2048]  type:5  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[2048 x 2048]  type:5  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[2048 x 2048]  type:5  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[2048 x 2048]  type:5  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[2048 x 2048]  type:6  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[2048 x 2048]  type:6  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[2048 x 2048]  type:6  continuous = true  iterations:1000  nz=true  pos=end
cv::hasNonZero          =&gt;1   perf:2018.92ms =&gt; 495.313 im/s
cv::countNonZero        =&gt;1   perf:1966.37ms =&gt; 508.552 im/s *
============================================================
size:[2048 x 2048]  type:6  continuous = true  iterations:1000  nz=false  pos=none
cv::hasNonZero          =&gt;0   perf:2005.87ms =&gt; 498.537 im/s
cv::countNonZero        =&gt;0   perf:1992.78ms =&gt; 501.812 im/s *
============================================================
size:[2048 x 2048]  type:6  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[2048 x 2048]  type:6  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[2048 x 2048]  type:6  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[2048 x 2048]  type:6  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[1031 x 1000]  type:0  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[1031 x 1000]  type:0  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[1031 x 1000]  type:0  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[1031 x 1000]  type:0  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[1031 x 1000]  type:0  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[1031 x 1000]  type:0  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[1031 x 1000]  type:0  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[1031 x 1000]  type:0  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[1031 x 1000]  type:2  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[1031 x 1000]  type:2  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[1031 x 1000]  type:2  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[1031 x 1000]  type:2  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[1031 x 1000]  type:2  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[1031 x 1000]  type:2  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[1031 x 1000]  type:2  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[1031 x 1000]  type:2  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[1031 x 1000]  type:4  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[1031 x 1000]  type:4  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[1031 x 1000]  type:4  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[1031 x 1000]  type:4  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[1031 x 1000]  type:4  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[1031 x 1000]  type:4  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[1031 x 1000]  type:4  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[1031 x 1000]  type:4  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[1031 x 1000]  type:5  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[1031 x 1000]  type:5  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[1031 x 1000]  type:5  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[1031 x 1000]  type:5  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[1031 x 1000]  type:5  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[1031 x 1000]  type:5  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[1031 x 1000]  type:5  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[1031 x 1000]  type:5  continuous = false  iterations:1000  nz=false  pos=none
============================================================
size:[1031 x 1000]  type:6  continuous = true  iterations:1000  nz=true  pos=begin
============================================================
size:[1031 x 1000]  type:6  continuous = true  iterations:1000  nz=true  pos=middle
============================================================
size:[1031 x 1000]  type:6  continuous = true  iterations:1000  nz=true  pos=end
============================================================
size:[1031 x 1000]  type:6  continuous = true  iterations:1000  nz=false  pos=none
============================================================
size:[1031 x 1000]  type:6  continuous = false  iterations:1000  nz=true  pos=begin
============================================================
size:[1031 x 1000]  type:6  continuous = false  iterations:1000  nz=true  pos=middle
============================================================
size:[1031 x 1000]  type:6  continuous = false  iterations:1000  nz=true  pos=end
============================================================
size:[1031 x 1000]  type:6  continuous = false  iterations:1000  nz=false  pos=none
done

```
diff --git a/modules/core/CMakeLists.txt b/modules/core/CMakeLists.txt
@@ -6,6 +6,7 @@ ocv_add_dispatched_file(arithm SSE2 SSE4_1 AVX2 VSX3)
 ocv_add_dispatched_file(convert SSE2 AVX2 VSX3)
 ocv_add_dispatched_file(convert_scale SSE2 AVX2)
 ocv_add_dispatched_file(count_non_zero SSE2 AVX2)
+ocv_add_dispatched_file(has_non_zero SSE2 AVX2)
 ocv_add_dispatched_file(matmul SSE2 SSE4_1 AVX2 AVX512_SKX NEON_DOTPROD)
 ocv_add_dispatched_file(mean SSE2 AVX2)
 ocv_add_dispatched_file(merge SSE2 AVX2)
diff --git a/modules/core/include/opencv2/core.hpp b/modules/core/include/opencv2/core.hpp
@@ -572,6 +572,14 @@ independently for each channel.
 */
 CV_EXPORTS_AS(sumElems) Scalar sum(InputArray src);
 
+/** @brief Checks for the presence of at least one non-zero array element.
+
+The function returns whether there are non-zero elements in src
+@param src single-channel array.
+@sa  mean, meanStdDev, norm, minMaxLoc, calcCovarMatrix
+*/
+CV_EXPORTS_W bool hasNonZero( InputArray src );
+
 /** @brief Counts non-zero array elements.
 
 The function returns the number of non-zero elements in src :
diff --git a/modules/core/perf/opencl/perf_arithm.cpp b/modules/core/perf/opencl/perf_arithm.cpp
@@ -460,6 +460,30 @@ OCL_PERF_TEST_P(CountNonZeroFixture, CountNonZero,
     SANITY_CHECK(result);
 }
 
+///////////// countNonZero ////////////////////////
+
+typedef Size_MatType HasNonZeroFixture;
+
+OCL_PERF_TEST_P(HasNonZeroFixture, HasNonZero,
+    ::testing::Combine(OCL_TEST_SIZES,
+        OCL_PERF_ENUM(CV_8UC1, CV_32FC1)))
+{
+    const Size_MatType_t params = GetParam();
+    const Size srcSize = get<0>(params);
+    const int type = get<1>(params);
+
+    checkDeviceMaxMemoryAllocSize(srcSize, type);
+
+    UMat src(srcSize, type);
+    /*bool result = false;*/
+    randu(src, 0, 10);
+    declare.in(src);
+
+    OCL_TEST_CYCLE() /*result =*/ cv::hasNonZero(src);
+
+    SANITY_CHECK_NOTHING();
+}
+
 ///////////// Phase ////////////////////////
 
 typedef Size_MatType PhaseFixture;
diff --git a/modules/core/perf/perf_stat.cpp b/modules/core/perf/perf_stat.cpp
@@ -101,4 +101,20 @@ PERF_TEST_P(Size_MatType, countNonZero, testing::Combine( testing::Values( TYPIC
     SANITY_CHECK(cnt);
 }
 
+PERF_TEST_P(Size_MatType, hasNonZero, testing::Combine( testing::Values( TYPICAL_MAT_SIZES ), testing::Values( CV_8UC1, CV_8SC1, CV_16UC1, CV_16SC1, CV_32SC1, CV_32FC1, CV_64FC1 ) ))
+{
+    Size sz = get<0>(GetParam());
+    int matType = get<1>(GetParam());
+
+    Mat src(sz, matType);
+    /*bool hnz = false;*/
+
+    declare.in(src, WARMUP_RNG);
+
+    int runs = (sz.width <= 640) ? 8 : 1;
+    TEST_CYCLE_MULTIRUN(runs) /*hnz =*/ hasNonZero(src);
+
+    SANITY_CHECK_NOTHING();
+}
+
 } // namespace
diff --git a/modules/core/src/has_non_zero.dispatch.cpp b/modules/core/src/has_non_zero.dispatch.cpp
@@ -0,0 +1,107 @@
+// This file is part of OpenCV project.
+// It is subject to the license terms in the LICENSE file found in the top-level directory
+// of this distribution and at https://opencv.org/license.html
+
+
+#include "precomp.hpp"
+#include "opencl_kernels_core.hpp"
+#include "stat.hpp"
+
+#include "has_non_zero.simd.hpp"
+#include "has_non_zero.simd_declarations.hpp" // defines CV_CPU_DISPATCH_MODES_ALL=AVX2,...,BASELINE based on CMakeLists.txt content
+
+namespace cv {
+
+static HasNonZeroFunc getHasNonZeroTab(int depth)
+{
+    CV_INSTRUMENT_REGION();
+    CV_CPU_DISPATCH(getHasNonZeroTab, (depth),
+        CV_CPU_DISPATCH_MODES_ALL);
+}
+
+#ifdef HAVE_OPENCL
+static bool ocl_hasNonZero( InputArray _src, bool & res )
+{
+    int type = _src.type(), depth = CV_MAT_DEPTH(type), kercn = ocl::predictOptimalVectorWidth(_src);
+    bool doubleSupport = ocl::Device::getDefault().doubleFPConfig() > 0;
+
+    if (depth == CV_64F && !doubleSupport)
+        return false;
+
+    int dbsize = ocl::Device::getDefault().maxComputeUnits();
+    size_t wgs = ocl::Device::getDefault().maxWorkGroupSize();
+
+    int wgs2_aligned = 1;
+    while (wgs2_aligned < (int)wgs)
+        wgs2_aligned <<= 1;
+    wgs2_aligned >>= 1;
+
+    ocl::Kernel k("reduce", ocl::core::reduce_oclsrc,
+                  format("-D srcT=%s -D srcT1=%s -D cn=1 -D OP_COUNT_NON_ZERO"
+                         " -D WGS=%d -D kercn=%d -D WGS2_ALIGNED=%d%s%s",
+                         ocl::typeToStr(CV_MAKE_TYPE(depth, kercn)),
+                         ocl::typeToStr(depth), (int)wgs, kercn,
+                         wgs2_aligned, doubleSupport ? " -D DOUBLE_SUPPORT" : "",
+                         _src.isContinuous() ? " -D HAVE_SRC_CONT" : ""));
+    if (k.empty())
+        return false;
+
+    UMat src = _src.getUMat(), db(1, dbsize, CV_32SC1);
+    k.args(ocl::KernelArg::ReadOnlyNoSize(src), src.cols, (int)src.total(),
+           dbsize, ocl::KernelArg::PtrWriteOnly(db));
+
+    size_t globalsize = dbsize * wgs;
+    if (k.run(1, &globalsize, &wgs, true))
+        return res = (saturate_cast<int>(cv::sum(db.getMat(ACCESS_READ))[0])>0), true;
+    return false;
+}
+#endif
+
+bool hasNonZero(InputArray _src)
+{
+    CV_INSTRUMENT_REGION();
+
+    int type = _src.type(), cn = CV_MAT_CN(type);
+    CV_Assert( cn == 1 );
+
+    bool res = false;
+
+#ifdef HAVE_OPENCL
+    CV_OCL_RUN_(OCL_PERFORMANCE_CHECK(_src.isUMat()) && _src.dims() <= 2,
+                ocl_hasNonZero(_src, res),
+                res)
+#endif
+
+    Mat src = _src.getMat();
+
+    HasNonZeroFunc func = getHasNonZeroTab(src.depth());
+    CV_Assert( func != 0 );
+
+    if (src.dims == 2)//fast path to avoid creating planes of single rows
+    {
+        if (src.isContinuous())
+            res |= func(src.ptr<uchar>(0), src.total());
+        else
+            for(int row = 0, rowsCount = src.rows ; !res && (row<rowsCount) ; ++row)
+                res |= func(src.ptr<uchar>(row), src.cols);
+    }
+    else//if (src.dims != 2)
+    {
+        const Mat* arrays[] = {&src, nullptr};
+        Mat planes[1];
+        NAryMatIterator itNAry(arrays, planes, 1);
+        for(size_t p = 0 ; !res && (p<itNAry.nplanes) ; ++p, ++itNAry)
+        {
+            const Mat& plane = itNAry.planes[0];
+            if (plane.isContinuous())
+                res |= func(plane.ptr<uchar>(0), plane.total());
+            else
+              for(int row = 0, rowsCount = plane.rows ; !res && (row<rowsCount) ; ++row)
+                  res |= func(plane.ptr<uchar>(row), plane.cols);
+        }
+    }
+
+    return res;
+}
+
+} // namespace
diff --git a/modules/core/src/has_non_zero.simd.hpp b/modules/core/src/has_non_zero.simd.hpp
diff --git a/modules/core/test/test_hasnonzero.cpp b/modules/core/test/test_hasnonzero.cpp
