Abstract

This work studies the performance impact of return value prediction in a system that supports speculative method-level parallelism (SMLP). A SMLP system creates a speculative thread at each method call, allowing the method and the code from which it is called to be executed in parallel. To improve performance, the return values of methods are predicted in hardware so that no method has to wait for its sub-method to complete before continuing to execute. For Java programs, we find that two-thirds of methods have a non-void return type, and perfect return value prediction improves performance by an average of 44% compared with a system with no return value prediction. However, the performance of realistic predictors is limited by poor prediction accuracy on integer return values and undesirable update characteristics due to the SMLP environment. A Parameter Stride (PS) return value predictor is proposed to address some of the deficiencies of the standard predictors by predicting based on method arguments. Combining the PS predictor with previous predictors results in 7% speedup on average versus a system with hybrid return value prediction, and 21% speedup versus a system with no return value prediction.

Citations