A compiler for optimized arithmetic datapaths

The authors present GAD, a compiler for arithmetic datapaths, i.e. systems characterized by the absence of conditional branches and abundance of arithmetic operations. GAD´s inputs are the functional specification of the datapath in the form of a signal flow graph, as well as the required throughput rate. A netlist is generated for the synthesized datapath, which is optimized for the number of gates used. The synthesis problem is formulated into two parts: (1) pipeline design, where machine cycles are organized into pipeline stages according to operator delays; and (2) scheduling, where operators are assigned to cycles to maximize resource sharing. Heuristics have been developed for these problems; using the characteristics of arithmetic datapaths, they explore systematically and efficiently a large part of the design space