We propose a retargetable architecture, based on a multicluster VLIW processor, that can exploit either instruction level parallelism (ILP) or ILP and data level parallelism (DLP) jointly in a SIMD fashion. Simulation results show that performances may increase significantly when the application is compiled for the proposed architecture.
Citation:
Domenico Barretta, William Fornaciari, Mariagiovanna Sami, Danilo Pau, "SIMD Extension to VLIW Multicluster Processors for Embedded Applications," iccd, pp.523, 2002 IEEE International Conference on Computer Design (ICCD'02), 2002