- calculate ticksTotal instead of ticksMean
- local / global width is based on ticksTotal value
- added instrumentation for OpenCL program compilation
- added instrumentation for OpenCL kernel execution
Minor fix in MatAllocator::upload
Minor fix in MatAllocator::copy
Minor fix in setSize function
Minor fix in Mat::Mat
Minor fix in cvMatNDToMat function
Minor fix in _InputArray::getMatVector
Minor fix in _InputArray::getUMatVector
Minor fix in cv::hconcat
Minor fix in cv::vconcat
Minor fix in cv::setIdentity
Minor fix in cv::trace
Minor fix in transposeI_ template function
Minor fix in reduceC_ template function
Minor fix in sort_ template function
Minor fix in sortIdx_ template function
Minor fix in cvRange function
Minor fix in MatConstIterator::seek
Minor fix in SparseMat::create
Minor fix in SparseMat::copyTo
Minor fix in SparseMat::convertTo
Minor fix in SparseMat::convertTo
Minor fix in SparseMat::ptr
Minor fix in SparseMat::resizeHashTab
Fixes indentation
* use v_float16x4 (universal intrinsic) instead of raw SSE/NEON implementation
* define v_load_f16/v_store_f16 since v_load can't be distinguished when short pointer passed
* brush up implementation on old compiler (guard correctly)
* add test for v_load_f16 and round trip conversion of v_float16x4
* fix conversion error
* use universal intrinsic for accumulate series using float/double
* accumulate, accumulateSquare, accumulateProduct and accumulateWeighted
* add v_cvt_f64_high in both SSE/NEON
* add test for conversion v_cvt_f64_high in test_intrin.cpp
* improve some existing universal intrinsic by using new instructions in Aarch64
* add workaround for Android build in intrin_neon.hpp
* Added 2-channel ops to match existing 3-channel and 4-channel ops
* v_load_deinterleave() and v_store_interleave()
* Implements float32x4 only on SSE (but all types on NEON and CPP)
* Includes tests
* Will be used to vectorize 2D functions, such as estimateAffine2D()
