The computational infrastructure of analogic CNN computing - Part I: The CNN-UM chip prototyping system

A new computational paradigm is emerging for spatio-temporal problems: anal ogic cellular neural/nonlinear network (CNN) array-computing. It has all th e software and hardware ingredients of the stored programmable computer (hi gh-level language, compiler, operating system, assembly and machine code, a nalogic central processing unit (CPU), analog and digital memory, periphera ls, etc.). The elementary instructions and programming techniques, however, are drastically different from any other computers. These elementary instr uctions represent complex spatio-temporal nonlinear dynamic phenomena, incl uding all the standard and exotic properties of simple image processing ope rators, as well as waves, patterns, and evolving systems, Meanwhile, a comp utational infrastructure has also emerged [6] interfacing this revolutionar y computing technology to digital systems as well as enabling the developme nt of high-level software, The main goal was to provide easy-to-use tools a nd hardware interfacing elements and putting most of the sophistication in the chips and chip sets.