FPGA based emulated-digital CNN-UM implementation with GAPU

The paper addresses the issue of implementing a GAPU (global analogic programming unit) on the emulated-digital CNN-UM (cellular neural/nonlinear networks universal machine) architecture. It has been embedded with a flexible Xilinx MicroBlaze soft-core processor to take full advantage of the joint computing power of high-speed arithmetics and programmability. The GAPU implementation accelerates the processing performance of the Falcon architecture by decreasing the I/O communication and it also provides a stand-alone operation, which is capable of controlling complex sophisticated analogic CNN algorithms similar to various visual microprocessors, such as the ACE16k and the Q-Eye in the Bi-i, and eye-RIS cellular vision systems. Our primary aim was to implement an FPGA-based emulated-digital CNN-UM with embedded GAPU for computation intensive, real image-processing tasks.