Performance analysis of VLIW compilation techniques

VLIW machines derive their performance advantage from the parallel executio n of independent instructions that have been scheduled by the compiler. The paper evaluates the performance impact of a set of important VLIW compilat ion techniques on non-numerical integer programs. In particular, several ke y scheduling approaches, including software pipelining versus loop unrollin g, DAG-based versus trace-based global scheduling, all-path versus profiled speculation, and restricted versus unrestricted speculative loads, are com pared. The evaluation is performed on a uniform VLIW testbed where a relati vely fair comparison of these scheduling approaches can be made. The result provides a meaningful insight into the relative benefits of each approach.