* another round of dnn optimization:
* increased malloc alignment across OpenCV from 16 to 64 bytes to make it AVX2 and even AVX-512 friendly
* improved SIMD optimization of pooling layer, optimized average pooling
* cleaned up convolution layer implementation
* made activation layer "attacheable" to all other layers, including fully connected and addition layer.
* fixed bug in the fusion algorithm: "LayerData::consumers" should not be cleared, because it desctibes the topology.
* greatly optimized permutation layer, which improved SSD performance
* parallelized element-wise binary/ternary/... ops (sum, prod, max)
* also, added missing copyrights to many of the layer implementation files
* temporarily disabled (again) the check for intermediate blobs consistency; fixed warnings from various builders
Removed IPP port for tiny arithm.cpp functions
Additional warnings fix on various platforms.
Build without OPENCL and GCC warnings fixed
Fixed warnings, trailing spaces and removed unused secure_cpy.
IPP code refactored.
IPP code path implemented as separate static functions to simplify future work with IPP code and make it more readable.
IPP can be switched on and off on runtime;
Optional implementation collector was added (switched off by default in CMake). Gathers data of implementation used in functions and report this info through performance TS;
TS modifications for implementations control;
Example: img of size 10x10 and templ of size 11x9.
In subsequent code this will results in either width or height of
corrSize to be zero (0).
Line 261 will call crossCorr which will then have a zero size of either
blocksize.width or blocksize.height resulting in a division by zero
crach in lines 137 or 138.