Functional decomposition for FPGA based designs: a weighted graph approach for encoding of compatible classes

Functional decomposition plays an important role in the design of FPGA-based circuits because their structure only imposes constraints on the number of inputs. Several decomposition techniques have been developed, and they show better area and level optimization. In a multi-level decomposition method, the coding of the decomposed function is an important factor that influences further decomposition at lower levels. It is particularly important for real-life functions that have a lot of "don't cares". In this paper, we propose a coding strategy that retains as many "don't cares" as possible. The resulting truth table is smaller in size.