Efficient code generation for horizontal architectures

Abstract

A horizontal architecture consists of a number of resources that can operate in parallel, each of which is controlled by a field in the wide instruction word. Such architectures offer the potential for high performance scientific computing at a modest cost. If this potential performance is to be realized, the multiple resources of a horizontal processor must be scheduled effectively. The scheduling task for conventional horizontal processors is quite complex and the construction of highly optimizing compilers for them is a difficult and expensive project. The polycyclic architecture is a horizontal architecture with architectural support for the scheduling task. The complexity of scheduling conventional horizontal processors and the ease of scheduling polycyclic processors is demonstrated by means of an example.