Field programmable gate arrays (FPGAs) have wider potential than application-specific integrated circuits (ASICs) because they can be programmed in the field even after customer installation, allowing for future upgrades and enhancements. Implementing designs on an FPGA, however, requires tight integration among several teams. Typically, DSP designers are unfamiliar with FPGA design tools, and FPGA designers are unfamiliar with DSP algorithms.
Sandia National Laboratories have increased efficiency by designing and simulating DSP systems with MATLAB® and Simulink®. They then use Xilinx Virtex-II FPGAs and DSP modeling and implementation tools to test and verify the hardware.
"Having MATLAB and Simulink so tightly integrated with the Xilinx toolset is a real asset for Sandia," says Dale Dubbert, digital radar development project lead at Sandia. "We are so impressed with the tools and the direction in which MathWorks and Xilinx are going that we plan to make this our mainstream DSP design flow."
This environment is enabling Sandia to save time in developing a digital IF receiver for a high-performance Synthetic Aperture Radar (SAR) system.