“…Designs targeting very large scale applications usually implement a large number of neurocores to maximize parallelization at chip level [15,38,49,122,148,160]. A large amount of publications report various neurocore organizations with designs optimized in accordance with the characteristics of the network topology to be mapped to the hardware [28,91,130,164,193], or with a targeted application [34,38,103,148,153,192,194,201].…”