Date of this Version
We present a receiver for a scalable multiple-access inter-chip link that communicates binary activity between two-dimensional arrays fabricated in deep submicron CMOS. Recipients are identified by row and column addresses but these addresses are not communicated simultaneously. The row address is followed sequentially by a column address for each active cell in that row; this cuts pad count in half without sacrificing communication capacity. Column addresses are decoded as they are received but cells are not written individually. An entire burst is written to a row in parallel; this increases communication capacity with integration density. Rows are written one by one but bursts are not processed one at a time. The next burst is decoded while the last one is being written; this increases capacity further. We synthesized an asynchronous implementation by performing a series of program decompositions, starting from a high-level description. Links using this design have been implemented successfully in three generations of submicron CMOS technology.
asynchronous logic synthesis, event-driven communication, neuromorphic systems, pipelining, pixel-level quantization, serial-to-parallel conversion
Date Posted: 28 October 2004
This document has been peer reviewed.