Created by: mozga-intel

This PR contains changes required to support MKLDNN memory layouts improving performance of MKLDNN computations.

This implementation differs from the proposed one in #10291. It is based mainly on Brian Liu implementation, which is simplified version of what I proposed previously.

The latest version of the pull request is splits into a few part of code (information).

This pull request contains:

• Implementation of the layout as a supports for mkldnn's operators.

Pull-request is related to:

• MKLDNN layout: Support for sum operator #11102
• MKLDNN layout: Support for pool operator #11101
• MKLDNN layout: Support for convolution operator #11099
• MKLDNN layout: Support for batch norm operator #11098
• MKLDNN layout: Support for activation operator #11124