A HW/SW design methodology for embedded SIMD vector signal processors

摘要

The trend of using SIMD processors in embedded systems has been driven by signal processing applications with large computational requirements. In this paper, we report a HW/SW methodology in order to design DSP cores and algorithms that exploit SIMD parallelism. Starting point is a novel hardware architectural template called STA. We introduce an approach for automatic generation of simulation and hardware models of DSP cores with a scalable level of SIMD parallelism. Software development is based on an algebraic model that captures the SIMD computational model. We explain how algorithms can be designed independent of the available SIMD parallelism.