FPGA and multi-core CPU make embedded design more flexible

    The explosive growth of embedded devices over the past few decades has resulted in significant improvements in hardware components and software tools. Despite this growth and innovation, traditional embedded system design methods have rarely improved and are becoming an obstacle. Given the rapid development of new standards and protocols, as well as the increasing pressure to get products to market, embedded system design is about to undergo a disruptive paradigm shift.

    As advances in hardware technology and software tools accelerate, integration challenges are beginning to emerge. Failure to properly address these challenges will make end products more expensive and hinder the experimentation, growth, and launch of more innovative designs.

    Standard embedded architecture

    In the general computing market, standardization has resulted in more robust and durable operating systems, more refined end applications, and advances in underlying hardware components. The lesson learned is that the time saved from avoiding the effort of customizing hardware architectures and related software components will result in better solutions that can accelerate time to market.

    In the embedded world, a standard architecture should be flexible enough to accommodate different use cases while providing a path for updating. Given these constraints, the most robust and durable architecture in the embedded world is a microprocessor and FPGA that work together as one (Figure A). Together, these two enable significant design flexibility.

    Figure A: In the standard hardware architecture shown in the figure, the combination of processor and FPGA enables flexibility and also allows standardization to take advantage of higher-level tools to achieve significant benefits in the design process. The processor allows the reuse of existing code libraries, while the FPGA allows for flexible implementation of customized algorithms.

    FPGAs bring the benefits of hardware determinism and reliability without the cost and lack of flexibility that characterizes ASIC designs. In addition, loading new logic and redefining links in the FPGA structure allows engineers to achieve future-proof designs with a more robust update path without requiring major hardware modifications.

    The combination of processors and FPGAs in embedded system design is becoming more and more popular in many industries. Engineers who design and develop embedded systems are using designs based on multiple processors and FPGAs. Among them, FPGAs are used to perform accurate and high-speed measurements or run time-critical algorithms. At the same time, processors are used to execute real-time operating systems to handle low-frequency control loops and provide Ethernet network communications to other distributed nodes and facilitate remote data access, system management and diagnosis.

    Advanced Tools

    A key benefit of standard architectures is that more powerful and optimized high-level tools can be developed and used for design. Higher-level tools allow experts in a certain field to delve deeper into embedded system design with smaller and more efficient design teams. As a result, smaller design teams can bring more complex products to market.

    efficiency

    General-purpose computing can demonstrate the efficiencies gained by using higher-level design tools and languages ​​for application development. Not surprisingly, the embedded market will begin to see the growth of high-level design tools, including the Xilinx AutoESL C-to-Gates high-level synthesis tool, the Mentor Graphics Catapult C synthesis tool, and the NI LabVIEW final system design software.