Computing, Approximately

Abstract

Computation today brings with it an expectation of preciseness – preciseness in the definition of the architecture, preciseness in the implementation of the architecture, and preciseness in the program designed to solve problems of interest. But is such preciseness important when the program itself encodes an approximate solution to a problem and is not sacrosanct? Is such preciseness important when an instruction executed by a program does not need all the restrictions indicated by its definition in the architecture, and hence does not make use of all the hardware associated with executing the instruction? Is such preciseness important when it is perfectly acceptable for an implementation to generate a result for a set of instructions that is close enough to one produced by a precise implementation? It is clear that the preciseness of today’s computational model comes at a cost – a cost in the complexity of programming a solution, a cost in the verification of complex behavior specification, and a cost in the energy expended beyond the minimum needed to solve the problem.