One of the chronic problems of computer science is that researchers do not keep up with the literature. As a result, repetition is common. In this paper the author designs a stream-based dataflow language almost exactly like Lucid [1] (of which he appears unaware) and a static dataflow architecture almost exactly like Dennis’s [2].
In order to allow fixed buffering between stages, only one set of stream elements is allowed into each part of the dataflow graph at a time. This effectively removes the opportunity for pipelining and its associated performance gains. Hence this architecture can be expected to perform quite poorly. A prototype processing element has been built, but the author essentially presents a paper design.