On the Design and Performance of Pipelined Architectures

Pipelining is a widely used technique for implementing architectures which have inherent temporal parallelism when there is an operational requirement for high throughput. Many variations on the basic theme have been proposed, with varying degrees of success. The aims of this paper are twofold. The first is to present a critical review of conventional pipelined architectures, and put some well known problems in sharp relief. It is argued that conventional pipelined architectures have underlying limitations which can only be dealt with by adopting a different view of pipelining. These limitations are explained in terms of discontinuities in the fiow of instructions and data, and representative machines are examined in support of this argument. The second aim is to introduce an alternative theory of pipelining, which we call Context Flow, and show how it can be used to construct efficient parallel systems.