Synthesis of pipelined DSP accelerators with dynamic scheduling

To construct complete systems on silicon, application specific DSP accelerators are needed to speed up the execution of high throughput DSP algorithms. In this paper, a methodology is presented to synthesize high throughput DSP functions into accelerator processors containing a datapath of highly pipelined, bit-parallel hardware units. Emphasis is put on the definition of a controller architecture that allows efficient run-time schedules of these DSP algorithms on such highly pipelined data paths. The methodology is illustrated by means of an FFT butterfly accelerator block.