The MUSE Machine -- an Architecture for Structured Data Flow Computation

Computers employing some degree of data flow organisation are now well established as providing a possible vehicle for concurrent computation. Although data-driven computation frees the architecture from the constraints of the single program counter, processor and global memory, inherent in the classic von Neumann computer, there can still be problems with the unconstrained generation of fresh result tokens if a pure data flow approach is adopted. The advantages of allowing serial processing for those parts of a program which are inherently serial, and of permitting a demand-driven, as well as data-driven, mode of operation are identified and described. The MUSE machine described here is a structured architecture supporting both serial and parallel processing which allows the abstract structure of a program to be mapped onto the machine in a logical way.

Two-dimensional Stokes flow driven by elliptical paddles

A fast and accurate numerical technique is developed for solving the biharmonic equation in a multiply connected domain, in two dimensions. We apply the technique to the computation of slow viscous flow (Stokes flow) driven by multiple stirring rods. Previously, the technique has been restricted to stirring rods of circular cross section; we show here how the prior method fails for noncircular rods and how it may be adapted to accommodate general rod cross sections, provided only that for each there exists a conformal mapping to a circle. Corresponding simulations of the flow are described, and their stirring properties and energy requirements are discussed briefly. In particular the method allows an accurate calculation of the flow when flat paddles are used to stir a fluid chaotically.