opencv/modules/core/CMakeLists.txt

244 lines
9.7 KiB
CMake
Raw Normal View History

set(the_description "The Core Functionality")
ocv_add_dispatched_file(mathfuncs_core SSE2 AVX AVX2)
ocv_add_dispatched_file(stat SSE4_2 AVX2)
ocv_add_dispatched_file(arithm SSE2 SSE4_1 AVX2 VSX3)
ocv_add_dispatched_file(convert SSE2 AVX2 VSX3)
2019-02-08 22:56:25 +08:00
ocv_add_dispatched_file(convert_scale SSE2 AVX2)
2019-02-13 23:27:55 +08:00
ocv_add_dispatched_file(count_non_zero SSE2 AVX2)
Merge pull request #22947 from chacha21:hasNonZero Added cv::hasNonZero() #22947 `cv::hasNonZero()` is semantically equivalent to (`cv::countNonZero()>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()>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()>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()>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()>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 (<=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()>0) for different matrices sizes, types, strides... { cv::setRNGSeed(1234); const std::vector<cv::Size> sizes = {{32, 32}, {64, 64}, {128, 128}, {320, 240}, {512, 512}, {640, 480}, {1024, 768}, {2048, 2048}, {1031, 1000}}; const std::vector<int> types = {CV_8U, CV_16U, CV_32S, CV_32F, CV_64F}; const size_t iterations = 1000; for(const cv::Size& size : sizes) { for(const int type : types) { for(int c = 0 ; c<2 ; ++c) { const bool continuous = !c; for(int i = 0 ; i<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 <= 2); const unsigned int nzOffsetRange = 10; const unsigned int nzOffset = cv::randu<unsigned int>()%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 << "============================================================" << std::endl; std::cout << "size:" << size << " type:" << type << " continuous = " << (continuous ? "true" : "false") << " iterations:" << iterations << " nz=" << (nz ? "true" : "false"); std::cout << " pos=" << ((i == 0) ? "begin" : (i == 1) ? "middle" : (i == 2) ? "end" : "none"); std::cout << std::endl; cv::Mat mask = cv::Mat::zeros(size, CV_8UC1); mask.at<unsigned char>(pos) = 0xFF; m.setTo(cv::Scalar::all(0)); m.setTo(cv::Scalar::all(nz ? 1 : 0), mask); std::vector<bool> results; std::vector<double> timings; { bool res = false; auto ref = cv::getTickCount(); for(size_t k = 0 ; k<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<iterations ; ++k) res = (cv::countNonZero(m)>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(), [&](bool r) {return (r == nz);}) != results.end())) { std::cout << "cv::hasNonZero\t\t=>" << results[0] << ((results[0] != nz) ? " ERROR" : "") << " perf:" << timings[0] << "ms => " << (iterations/timings[0]*1000) << " im/s" << ((bestTimingIndex == 0) ? " * " : "") << std::endl; std::cout << "cv::countNonZero\t=>" << results[1] << ((results[1] != nz) ? " ERROR" : "") << " perf:" << timings[1] << "ms => " << (iterations/timings[1]*1000) << " im/s" << ((bestTimingIndex == 1) ? " * " : "") << 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 =>1 perf:0.353764ms => 2.82674e+06 im/s cv::countNonZero =>1 perf:0.282044ms => 3.54555e+06 im/s * ============================================================ size:[32 x 32] type:0 continuous = false iterations:1000 nz=true pos=end cv::hasNonZero =>1 perf:0.610478ms => 1.63806e+06 im/s cv::countNonZero =>1 perf:0.283182ms => 3.5313e+06 im/s * ============================================================ size:[32 x 32] type:0 continuous = false iterations:1000 nz=false pos=none cv::hasNonZero =>0 perf:0.630115ms => 1.58701e+06 im/s cv::countNonZero =>0 perf:0.282044ms => 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 =>1 perf:0.607347ms => 1.64651e+06 im/s cv::countNonZero =>1 perf:0.467037ms => 2.14116e+06 im/s * ============================================================ size:[32 x 32] type:5 continuous = false iterations:1000 nz=false pos=none cv::hasNonZero =>0 perf:0.618162ms => 1.6177e+06 im/s cv::countNonZero =>0 perf:0.468175ms => 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 =>1 perf:895.381ms => 1116.84 im/s cv::countNonZero =>1 perf:882.569ms => 1133.06 im/s * ============================================================ size:[2048 x 2048] type:4 continuous = true iterations:1000 nz=false pos=none cv::hasNonZero =>0 perf:899.53ms => 1111.69 im/s cv::countNonZero =>0 perf:870.894ms => 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 =>1 perf:2018.92ms => 495.313 im/s cv::countNonZero =>1 perf:1966.37ms => 508.552 im/s * ============================================================ size:[2048 x 2048] type:6 continuous = true iterations:1000 nz=false pos=none cv::hasNonZero =>0 perf:2005.87ms => 498.537 im/s cv::countNonZero =>0 perf:1992.78ms => 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 ```
2023-06-09 18:37:20 +08:00
ocv_add_dispatched_file(has_non_zero SSE2 AVX2)
ocv_add_dispatched_file(matmul SSE2 SSE4_1 AVX2 AVX512_SKX NEON_DOTPROD)
2019-02-19 21:58:32 +08:00
ocv_add_dispatched_file(mean SSE2 AVX2)
2019-02-22 19:17:18 +08:00
ocv_add_dispatched_file(merge SSE2 AVX2)
2019-02-22 17:35:32 +08:00
ocv_add_dispatched_file(split SSE2 AVX2)
2019-02-11 21:21:49 +08:00
ocv_add_dispatched_file(sum SSE2 AVX2)
# dispatching for accuracy tests
Merge pull request #14210 from terfendail:wui_512 AVX512 wide universal intrinsics (#14210) * Added implementation of 512-bit wide universal intrinsics(WIP) * Added implementation of 512-bit wide universal intrinsics: implemented WUI vector types(WIP) * Added implementation of 512-bit wide universal intrinsics(WIP): implemented load/store * Added implementation of 512-bit wide universal intrinsics(WIP): implemented fp16 load/store * Added implementation of 512-bit wide universal intrinsics(WIP): implemented recombine and zip, implemented non-saturating and saturating arithmetics * Added implementation of 512-bit wide universal intrinsics(WIP): implemented bit operations * Added implementation of 512-bit wide universal intrinsics(WIP): implemented comparisons * Added implementation of 512-bit wide universal intrinsics(WIP): implemented lane shifts and reduction * Added implementation of 512-bit wide universal intrinsics(WIP): implemented absolute values * Added implementation of 512-bit wide universal intrinsics(WIP): implemented rounding and cast to float * Added implementation of 512-bit wide universal intrinsics(WIP): implemented LUT * Added implementation of 512-bit wide universal intrinsics(WIP): implemented type extension/narrowing and matrix operations * Added implementation of 512-bit wide universal intrinsics(WIP): implemented load_deinterleave for 2 and 3 channels images * Added implementation of 512-bit wide universal intrinsics(WIP): reimplemented load_deinterleave for 2- and implemented for 4-channel images * Added implementation of 512-bit wide universal intrinsics(WIP): implemented store_interleave * Added implementation of 512-bit wide universal intrinsics(WIP): implemented signmask and checks * Added implementation of 512-bit wide universal intrinsics(WIP): build fixes * Added implementation of 512-bit wide universal intrinsics(WIP): reimplemented popcount in case AVX512_BITALG is unavailable * Added implementation of 512-bit wide universal intrinsics(WIP): reimplemented zip * Added implementation of 512-bit wide universal intrinsics(WIP): reimplemented rotate for s8 and s16 * Added implementation of 512-bit wide universal intrinsics(WIP): reimplemented interleave/deinterleave for s8 and s16 * Added implementation of 512-bit wide universal intrinsics(WIP): updated v512_set macros * Added implementation of 512-bit wide universal intrinsics(WIP): fix for GCC wrong _mm512_abs_pd definition * Added implementation of 512-bit wide universal intrinsics(WIP): reworked v_zip to avoid AVX512_VBMI intrinsics * Added implementation of 512-bit wide universal intrinsics(WIP): reworked v_invsqrt to avoid AVX512_ER intrinsics * Added implementation of 512-bit wide universal intrinsics(WIP): reworked v_rotate, v_popcount and interleave/deinterleave for U8 to avoid AVX512_VBMI intrinsics * Added implementation of 512-bit wide universal intrinsics(WIP): fixed integral image SIMD part * Added implementation of 512-bit wide universal intrinsics(WIP): fixed warnings * Added implementation of 512-bit wide universal intrinsics(WIP): fixed load_deinterleave for u8 and u16 * Added implementation of 512-bit wide universal intrinsics(WIP): fixed v_invsqrt accuracy for f64 * Added implementation of 512-bit wide universal intrinsics(WIP): fixed interleave/deinterleave for u32 and u64 * Added implementation of 512-bit wide universal intrinsics(WIP): fixed interleave_pairs, interleave_quads and pack_triplets * Added implementation of 512-bit wide universal intrinsics(WIP): fixed rotate_left * Added implementation of 512-bit wide universal intrinsics(WIP): fixed rotate_left/right, part 2 * Added implementation of 512-bit wide universal intrinsics(WIP): fixed 512-wide universal intrinsics based resize * Added implementation of 512-bit wide universal intrinsics(WIP): fixed findContours by avoiding use of uint64 dependent 512-wide v_signmask() * Added implementation of 512-bit wide universal intrinsics(WIP): fixed trailing whitespaces * Added implementation of 512-bit wide universal intrinsics(WIP): reworked specific intrinsic sets dependent parts to check availability of intrinsics based on CPU feature group defines * Added implementation of 512-bit wide universal intrinsics(WIP):Updated AVX512 implementation of v_popcount to avoid AVX512VPOPCNTDQ intrinsics if unavailable. * Added implementation of 512-bit wide universal intrinsics(WIP): Fixed universal intrinsics data initialisation, v_mul_wrap, v_floor, v_ceil and v_signmask. * Added implementation of 512-bit wide universal intrinsics(WIP): Removed hasSIMD512() * Added implementation of 512-bit wide universal intrinsics(WIP): Fixes for gcc build * Added implementation of 512-bit wide universal intrinsics(WIP): Reworked v_signmask, v_check_any() and v_check_all() implementation.
2019-06-03 23:05:35 +08:00
ocv_add_dispatched_file_force_all(test_intrin128 TEST SSE2 SSE3 SSSE3 SSE4_1 SSE4_2 AVX FP16 AVX2 AVX512_SKX)
ocv_add_dispatched_file_force_all(test_intrin256 TEST AVX2 AVX512_SKX)
ocv_add_dispatched_file_force_all(test_intrin512 TEST AVX512_SKX)
2021-02-04 06:04:35 +08:00
set(PARALLEL_ENABLE_PLUGINS_DEFAULT ON)
if(EMSCRIPTEN OR IOS OR WINRT)
set(PARALLEL_ENABLE_PLUGINS_DEFAULT OFF)
endif()
2021-02-04 06:04:35 +08:00
# parallel backends configuration
set(PARALLEL_ENABLE_PLUGINS "${PARALLEL_ENABLE_PLUGINS_DEFAULT}" CACHE BOOL "Allow building parallel plugin support")
2021-02-04 06:04:35 +08:00
# TODO building plugins with OpenCV is not supported yet
#set(PARALLEL_PLUGIN_LIST "" CACHE STRING "List of parallel backends to be compiled as plugins (tbb, openmp or special value 'all')")
#string(REPLACE "," ";" PARALLEL_PLUGIN_LIST "${PARALLEL_PLUGIN_LIST}") # support comma-separated list (,) too
#string(TOLOWER "${PARALLEL_PLUGIN_LIST}" PARALLEL_PLUGIN_LIST)
2021-02-04 06:04:35 +08:00
2015-06-05 21:24:38 +08:00
ocv_add_module(core
2015-02-19 21:17:19 +08:00
OPTIONAL opencv_cudev
WRAP java objc python js)
2012-02-03 19:54:16 +08:00
set(extra_libs "")
2019-07-18 18:22:02 +08:00
if(WINRT AND WINDOWS_STORE AND CMAKE_SYSTEM_VERSION MATCHES "8.0")
list(APPEND extra_libs ole32.lib)
endif()
2018-04-06 19:21:15 +08:00
if(HAVE_TBB)
list(APPEND extra_libs tbb)
endif()
if(DEFINED WINRT AND NOT DEFINED ENABLE_WINRT_MODE_NATIVE)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /ZW")
endif()
if(HAVE_CUDA)
2019-04-01 03:54:13 +08:00
if(NOT HAVE_opencv_cudev)
message(FATAL_ERROR "CUDA: OpenCV requires enabled 'cudev' module from 'opencv_contrib' repository: https://github.com/opencv/opencv_contrib")
endif()
ocv_warnings_disable(CMAKE_CXX_FLAGS -Wundef -Wenum-compare -Wunused-function -Wshadow)
endif()
2019-11-01 20:07:49 +08:00
if(CV_TRACE AND HAVE_ITT)
2017-05-25 23:59:01 +08:00
add_definitions(-DOPENCV_WITH_ITT=1)
endif()
# https://github.com/opencv/opencv/issues/24145
if(HAVE_IPP)
OCV_OPTION(OPENCV_IPP_ENABLE_ALL "Enable all OPENCV_IPP_ options at once" OFF)
OCV_OPTION(OPENCV_IPP_MEAN "Enable IPP optimizations for mean (+200Kb in binary size)" OPENCV_IPP_ENABLE_ALL)
OCV_OPTION(OPENCV_IPP_MINMAX "Enable IPP optimizations for minMaxLoc/minMaxIdx (+200Kb in binary size)" OPENCV_IPP_ENABLE_ALL)
OCV_OPTION(OPENCV_IPP_SUM "Enable IPP optimizations for sum (+100Kb in binary size)" OPENCV_IPP_ENABLE_ALL)
if(OPENCV_IPP_MEAN)
ocv_append_source_file_compile_definitions(${CMAKE_CURRENT_SOURCE_DIR}/src/mean.dispatch.cpp "OPENCV_IPP_MEAN=1")
endif()
if(OPENCV_IPP_MINMAX)
ocv_append_source_file_compile_definitions(${CMAKE_CURRENT_SOURCE_DIR}/src/minmax.cpp "OPENCV_IPP_MINMAX=1")
endif()
if(OPENCV_IPP_SUM)
ocv_append_source_file_compile_definitions(${CMAKE_CURRENT_SOURCE_DIR}/src/sum.dispatch.cpp "OPENCV_IPP_SUM=1")
endif()
endif()
file(GLOB lib_cuda_hdrs
"${CMAKE_CURRENT_LIST_DIR}/include/opencv2/${name}/cuda/*.hpp"
"${CMAKE_CURRENT_LIST_DIR}/include/opencv2/${name}/cuda/*.h")
file(GLOB lib_cuda_hdrs_detail
"${CMAKE_CURRENT_LIST_DIR}/include/opencv2/${name}/cuda/detail/*.hpp"
"${CMAKE_CURRENT_LIST_DIR}/include/opencv2/${name}/cuda/detail/*.h")
file(GLOB_RECURSE module_opencl_hdrs
"${CMAKE_CURRENT_LIST_DIR}/include/opencv2/${name}/opencl/*")
2013-04-05 00:54:35 +08:00
source_group("Include\\Cuda Headers" FILES ${lib_cuda_hdrs})
source_group("Include\\Cuda Headers\\Detail" FILES ${lib_cuda_hdrs_detail})
file(GLOB_RECURSE core_parallel_hdrs
"${CMAKE_CURRENT_LIST_DIR}/include/opencv2/${name}/parallel/*.hpp"
"${CMAKE_CURRENT_LIST_DIR}/include/opencv2/${name}/parallel/*.h")
ocv_source_group("Include" DIRBASE "${CMAKE_CURRENT_LIST_DIR}/include" FILES ${core_parallel_hdrs})
source_group("Src" FILES "${OPENCV_MODULE_opencv_core_BINARY_DIR}/version_string.inc")
2013-04-05 00:54:35 +08:00
2014-08-01 22:11:20 +08:00
ocv_glob_module_sources(SOURCES "${OPENCV_MODULE_opencv_core_BINARY_DIR}/version_string.inc"
HEADERS ${core_parallel_hdrs} ${module_opencl_hdrs} ${lib_cuda_hdrs} ${lib_cuda_hdrs_detail})
2013-03-31 18:54:23 +08:00
ocv_module_include_directories(${the_module} ${ZLIB_INCLUDE_DIRS} ${OPENCL_INCLUDE_DIRS})
if(ANDROID AND HAVE_CPUFEATURES)
ocv_append_source_file_compile_definitions(${CMAKE_CURRENT_SOURCE_DIR}/src/system.cpp "HAVE_CPUFEATURES=1")
ocv_module_include_directories(${CPUFEATURES_INCLUDE_DIRS})
endif()
2017-05-25 23:59:01 +08:00
if(ITT_INCLUDE_DIRS)
ocv_module_include_directories(${ITT_INCLUDE_DIRS})
endif()
if(HAVE_POSIX_MEMALIGN)
ocv_append_source_file_compile_definitions(${CMAKE_CURRENT_SOURCE_DIR}/src/alloc.cpp "HAVE_POSIX_MEMALIGN=1")
endif()
if(HAVE_MALLOC_H)
ocv_append_source_file_compile_definitions(${CMAKE_CURRENT_SOURCE_DIR}/src/alloc.cpp "HAVE_MALLOC_H=1")
endif()
if(HAVE_MEMALIGN)
ocv_append_source_file_compile_definitions(${CMAKE_CURRENT_SOURCE_DIR}/src/alloc.cpp "HAVE_MEMALIGN=1")
endif()
if(HAVE_WIN32_ALIGNED_MALLOC)
ocv_append_source_file_compile_definitions(${CMAKE_CURRENT_SOURCE_DIR}/src/alloc.cpp "HAVE_WIN32_ALIGNED_MALLOC=1")
endif()
if(HAVE_VA_INTEL_OLD_HEADER)
ocv_append_source_file_compile_definitions("${CMAKE_CURRENT_LIST_DIR}/src/va_intel.cpp" "HAVE_VA_INTEL_OLD_HEADER")
endif()
2021-02-18 21:36:07 +08:00
if(OPENCV_LIBVA_LINK)
ocv_append_source_file_compile_definitions("${CMAKE_CURRENT_LIST_DIR}/src/va_intel.cpp" "OPENCV_LIBVA_LINK=1")
endif()
option(OPENCV_ENABLE_ALLOCATOR_STATS "Enable Allocator metrics" ON)
if(NOT OPENCV_ENABLE_ALLOCATOR_STATS)
add_definitions(-DOPENCV_DISABLE_ALLOCATOR_STATS=1)
elseif(HAVE_CXX11 OR DEFINED OPENCV_ALLOCATOR_STATS_COUNTER_TYPE)
if(NOT DEFINED OPENCV_ALLOCATOR_STATS_COUNTER_TYPE)
if(HAVE_ATOMIC_LONG_LONG AND OPENCV_ENABLE_ATOMIC_LONG_LONG)
if(MINGW)
# command-line generation issue due to space in value, int/int64_t should be used instead
# https://github.com/opencv/opencv/issues/16990
message(STATUS "Consider adding OPENCV_ALLOCATOR_STATS_COUNTER_TYPE=int/int64_t according to your build configuration")
else()
set(OPENCV_ALLOCATOR_STATS_COUNTER_TYPE "long long")
endif()
else()
set(OPENCV_ALLOCATOR_STATS_COUNTER_TYPE "int")
endif()
endif()
if(DEFINED OPENCV_ALLOCATOR_STATS_COUNTER_TYPE)
message(STATUS "Allocator metrics storage type: '${OPENCV_ALLOCATOR_STATS_COUNTER_TYPE}'")
add_definitions("-DOPENCV_ALLOCATOR_STATS_COUNTER_TYPE=${OPENCV_ALLOCATOR_STATS_COUNTER_TYPE}")
endif()
endif()
2021-02-04 06:04:35 +08:00
if(PARALLEL_ENABLE_PLUGINS)
ocv_append_source_file_compile_definitions(${CMAKE_CURRENT_SOURCE_DIR}/src/parallel/parallel.cpp "PARALLEL_ENABLE_PLUGINS=1")
if(OPENCV_DEBUG_POSTFIX)
ocv_append_source_file_compile_definitions("${CMAKE_CURRENT_LIST_DIR}/src/parallel/parallel.cpp" "DEBUG_POSTFIX=${OPENCV_DEBUG_POSTFIX}")
endif()
endif()
ocv_create_module(${extra_libs})
ocv_target_link_libraries(${the_module} PRIVATE
2017-05-25 23:59:01 +08:00
"${ZLIB_LIBRARIES}" "${OPENCL_LIBRARIES}" "${VA_LIBRARIES}"
2021-12-07 13:47:54 +08:00
"${OPENGL_LIBRARIES}"
"${GLX_LIBRARIES}"
"${LAPACK_LIBRARIES}" "${CPUFEATURES_LIBRARIES}" "${HALIDE_LIBRARIES}"
2017-05-25 23:59:01 +08:00
"${ITT_LIBRARIES}"
2017-08-17 05:23:06 +08:00
"${OPENCV_HAL_LINKER_LIBS}"
2017-05-25 23:59:01 +08:00
)
if(OPENCV_CORE_EXCLUDE_C_API)
ocv_target_compile_definitions(${the_module} PRIVATE "OPENCV_EXCLUDE_C_API=1")
endif()
if(OPENCV_DISABLE_THREAD_SUPPORT)
ocv_target_compile_definitions(${the_module} PUBLIC "OPENCV_DISABLE_THREAD_SUPPORT=1")
endif()
Merge pull request #20392 from fpetrogalli:aarch64-semihosting AArch64 semihosting * [ts] Disable filesystem support in the TS module. Because of this change, all the tests loading data will file, but tat least the core module can be tested with the following line: opencv_test_core --gtest_filter=-"*Core_InputOutput*:*Core_globbing.accuracy*" * [aarch64] Build OpenCV for AArch64 semihosting. This patch provide a toolchain file that allows to build the library for semihosting applications [1]. Minimal changes have been applied to the code to be able to compile with a baremetal toolchain. [1] https://developer.arm.com/documentation/100863/latest The option `CV_SEMIHOSTING` is used to guard the bits in the code that are specific to the target. To build the code: cmake ../opencv/ \ -DCMAKE_TOOLCHAIN_FILE=../opencv/platforms/semihosting/aarch64-semihosting.toolchain.cmake \ -DSEMIHOSTING_TOOLCHAIN_PATH=/path/to/baremetal-toolchain/bin/ \ -DBUILD_EXAMPLES=ON -GNinja A barematel toolchain for targeting aarch64 semihosting can be found at [2], under `aarch64-none-elf`. [2] https://developer.arm.com/tools-and-software/open-source-software/developer-tools/gnu-toolchain/gnu-a/downloads The folder `samples/semihosting` provides two example semihosting applications. The two binaries can be executed on the host platform with: qemu-aarch64 ./bin/example_semihosting_histogram qemu-aarch64 ./bin/example_semihosting_norm Similarly, the test and perf executables of the modules can be run with: qemu-aarch64 ./bin/opecv_[test|perf]_<module> Notice that filesystem support is disabled by the toolchain file, hence some of the test that depend on filesystem support will fail. * [semihosting] Remove blank like at the end of file. [NFC] The spurious blankline was reported by https://pullrequest.opencv.org/buildbot/builders/precommit_docs/builds/31158. * [semihosting] Make the raw pixel file generation OS independent. Use the facilities provided by Cmake to generate the header file instead of a shell script, so that the build doesn't fail on systems that do not have a unix shell. * [semihosting] Rename variable for semihosting compilation. * [semihosting] Move the cmake configuration to a variable file. * [semihosting] Make the guard macro private for the core module. * [semihosting] Remove space. [NFC] * [semihosting] Improve comment with information about semihosting. [NFC] * [semihosting] Update license statement on top of sourvce file. [NFC] * [semihosting] Replace BM_SUFFIX with SEMIHOSTING_SUFFIX. [NFC] * [semihosting] Remove double space. [NFC] * [semihosting] Add some text output to the sample applications. * [semihosting] Remove duplicate entry in cmake configuration. [NFCI] * [semihosting] Replace `long` with `int` in sample apps. [NFCI] * [semihosting] Use `configure_file` to create the random pixels. [NFCI] * [semihosting][bugfix] Fix name of cmakedefine variable. * [semihosting][samples] Use CV_8UC1 for grayscale images. [NFCI] * [semihosting] Add readme file. * [semihosting] Remove blank like at the end of README. [NFC] This fixes the failure at https://pullrequest.opencv.org/buildbot/builders/precommit_docs/builds/31272.
2021-07-21 23:46:05 +08:00
if(OPENCV_SEMIHOSTING)
ocv_target_compile_definitions(${the_module} PRIVATE "-DOPENCV_SEMIHOSTING")
endif(OPENCV_SEMIHOSTING)
if(HAVE_HPX)
ocv_target_link_libraries(${the_module} LINK_PRIVATE "${HPX_LIBRARIES}")
endif()
if(HAVE_OPENMP AND DEFINED OpenMP_CXX_LIBRARIES AND OpenMP_CXX_LIBRARIES)
ocv_target_link_libraries(${the_module} LINK_PRIVATE "${OpenMP_CXX_LIBRARIES}")
endif()
ocv_add_accuracy_tests()
ocv_add_perf_tests()
ocv_install_3rdparty_licenses(SoftFloat "${CMAKE_CURRENT_SOURCE_DIR}/3rdparty/SoftFloat/COPYING.txt")
# generate data (samples data) config file
2023-02-03 18:02:45 +08:00
set(OPENCV_DATA_CONFIG_FILE "${OPENCV_CONFIG_FILE_INCLUDE_DIR}/opencv_data_config.hpp")
set(OPENCV_DATA_CONFIG_STR "")
if(CMAKE_INSTALL_PREFIX)
set(OPENCV_DATA_CONFIG_STR "${OPENCV_DATA_CONFIG_STR}
#define OPENCV_INSTALL_PREFIX \"${CMAKE_INSTALL_PREFIX}\"
")
endif()
if(OPENCV_OTHER_INSTALL_PATH)
set(OPENCV_DATA_CONFIG_STR "${OPENCV_DATA_CONFIG_STR}
#define OPENCV_DATA_INSTALL_PATH \"${OPENCV_OTHER_INSTALL_PATH}\"
")
endif()
set(OPENCV_DATA_CONFIG_STR "${OPENCV_DATA_CONFIG_STR}
#define OPENCV_BUILD_DIR \"${CMAKE_BINARY_DIR}\"
")
file(RELATIVE_PATH SOURCE_DIR_RELATIVE ${CMAKE_BINARY_DIR} ${CMAKE_SOURCE_DIR})
set(OPENCV_DATA_CONFIG_STR "${OPENCV_DATA_CONFIG_STR}
#define OPENCV_DATA_BUILD_DIR_SEARCH_PATHS \\
\"${SOURCE_DIR_RELATIVE}/\"
")
if(WIN32)
file(RELATIVE_PATH INSTALL_DATA_DIR_RELATIVE "${CMAKE_INSTALL_PREFIX}/${OPENCV_BIN_INSTALL_PATH}" "${CMAKE_INSTALL_PREFIX}/${OPENCV_OTHER_INSTALL_PATH}")
else()
file(RELATIVE_PATH INSTALL_DATA_DIR_RELATIVE "${CMAKE_INSTALL_PREFIX}/${OPENCV_LIB_INSTALL_PATH}" "${CMAKE_INSTALL_PREFIX}/${OPENCV_OTHER_INSTALL_PATH}")
endif()
list(APPEND OPENCV_INSTALL_DATA_DIR_RELATIVE "${INSTALL_DATA_DIR_RELATIVE}")
string(REPLACE ";" "\",\\\n \"" OPENCV_INSTALL_DATA_DIR_RELATIVE_STR "\"${OPENCV_INSTALL_DATA_DIR_RELATIVE}\"")
set(OPENCV_DATA_CONFIG_STR "${OPENCV_DATA_CONFIG_STR}
#define OPENCV_INSTALL_DATA_DIR_RELATIVE ${OPENCV_INSTALL_DATA_DIR_RELATIVE_STR}
")
if(EXISTS "${OPENCV_DATA_CONFIG_FILE}")
file(READ "${OPENCV_DATA_CONFIG_FILE}" __content)
endif()
if(NOT OPENCV_DATA_CONFIG_STR STREQUAL "${__content}")
file(WRITE "${OPENCV_DATA_CONFIG_FILE}" "${OPENCV_DATA_CONFIG_STR}")
endif()