XGRID: A Scalable Many-Core Embedded Processor

The demand for compute cycles needed by embedded systems is rapidly increasing. Due to the limitations of single-core processors, a move towards multi-core architectures is unavoidable. In this paper, we introduce the XGRID embedded many-core system-on-chip architecture. XGRID makes use of a novel, FPGA-like, programmable interconnect infrastructure, offering scalability and deterministic communication using hardware supported message passing among cores. We have developed a simulation framework for the XGRID architecture, which provides system performance information. Our experiments with XGRID are very encouraging. A number of parallel benchmarks are evaluated on the XGRID processor using the application mapping technique described in this work. Results show an average of 5X speedup, a maximum of 14X speedup, and a minimum of 2X speedup across all benchmarks. We have validated our scalability claim by running our benchmarks on XGRID varying in core count. We have also validated our assertions on XGRI