Predicate-based transformations to eliminate control and data-irrelevant cache misses

The performance of modern processors is increasingly de-pendent on their ability to execute multiple instructions per cycle. Explicitly Parallel Instruction Computing (EPIC) ar-chitectures can achieve high performance by using the com-piler to express program instruction level parallelism (ILP) directly to the hardware. The predicated execution fea-ture is critical to the success of the EPIC architecture ap-proach because it allows the compiler to explicitly overlap the execution of independent control paths. An advantage of predicated execution is the elimination of hard-to-predict branches by executing both paths of a branch in a single code sequence. However, there are a number of advantages to predicated execution support other than simply reducing branch mispredictions and enabling the parallel execution of multiple control flow paths. To date, very little research has been performed to investigate radical changes to a pro-gram’s original data flow and control flow. This paper out-lines methods of using predicated execution to substantially improve the efficiency of EPIC memory accesses. Value lo-cality, the repetition of computation values serve as a key attribute to reduce unnecessary memory operations of a pro-gram. 1