Design Methodology for Signal Processing

Lee这项研究涉及信号处理系统的异类实现的设计方法。一些信号处理算法包括对具有硬实时约束的样本流进行高度重复、可预测的计算，并且服从同步数据流表示和静态(编译时)调度。其他算法涉及一些决策或运行时控制流，并且可以通过包括运行时流控制的更广泛的数据流模型来有效地适应。当这样的算法组合成完整的系统时，必须支持更多的动态，并且必须包括离散事件原理或实时操作系统。这项研究正在寻找结合不同语义的方法，并正在寻求联合模拟技术，并理解每个计算模型中可用的正式方法之间的相互作用。一个单独或组合支持所有这些模型的设计框架(称为托勒密)正在开发中，作为试验床。

Lee This research deals with design methodology for heterogeneous implementations of signal processing systems. Some signal processing algorithms consist of highly repetitive, predictable computations on streams of samples with hard real- time constraints, and are amenable to synchronous dataflow representations and static (compile-time) scheduling. Other algorithms involve some decision making or run-time control flow, and can be accommodated efficiently by a broader dataflow model that includes run-time flow control. When such algorithms are combined into complete systems, more dynamics must be supported, and discrete-event principles, or real-time operating systems must be included. This research is looking at ways to combine diverse semantics, and is pursuing co-simulation techniques and understanding of the interaction between what formal methods are available within each model of computation. A design framework (called Ptolemy) that supports all these models, individually or in combination, is being developed as a testbed.