AN INTEGER PROGRAMMING APPROACH TO INSTRUCTION SET SELECTION PROBLEM

The performance of ASIPs (Application Specific Integrated Processors) is heavily affected by the design of their instruction set architectur e. In order to maximize the performance of ASIP, it is essential to de sign an architecture that has an optimum instruction set. This paper d escribes a new method that automates the design of optimum instruction set of ASIP. This method solves the Instruction set implementation Me thod Selection Problem (IMSP). IMSP is to be solved in the instruction set architecture design. First, the IMSP is formalized as an integer programming problem, which is to maximize the performance of the CPU u nder the constraints of chip area and power consumption. Then, a branc h-and-bound algorithm to solve IMSP is described. According to the exp erimental results, the proposed algorithm is quite effective and effic ient in solving the IMSP. The presented method automates a complex par t of the ASIP chip design and is also a good design tool that enables designer to predict the performance of their design before completion.