Flexible Datapath Synthesis through Arithmetically Optimized Operation Chaining

Datapath synthesis incorporating complex operation templates has been proven extremely efficient especially for the digital signal processing (DSP) application domain.However, only architectural level optimizations have been reported for the specification and implementation of the operation templates. This paper introduces the consideration of arithmetic level optimizations for template based datapath synthesis. A high performance architecture for the implementation of DSP kernels is presented. It is based on flexible and arithmetically optimized components able to perform a large set of operation templates. A synthesis methodology for optimized mapping of DSP kernels onto the proposed architecture is also presented. Experimental results are reported showing significant gains in execution time, active chip area and power dissipation in comparison to previously published flexible template-based data paths.