Dynamic feature selection for hardware prediction

It is often possible to greatly improve the performance of a hardware system via the use of predictive (speculative) techniques. For example, the performance of out-of-order microprocessors is greatly enhanced by predicting the outcomes of conditional branch instructions. Most hardware predictors are table based (e.g., two-level branch predictors)--maintaining predictive information for each combination of values of a set of features (e.g., a set of previous branch outcomes). Table-based approaches suffer from the fact that the predictor sizes grow exponentially in the number of features considered by the predictor--this severely limits the amount of predictive information that can be effectively utilized by tablebased predictors. For example, most table-based branch predictors use a feature set containing only a small number of recent branch outcomes, despite the fact that other bits of processor state contain predictive information (e.g., register values and target addresses). In th...

• Type: Journal
• Year: 2006
• Where: JSA
• Authors: Alan Fern, Robert Givan, Babak Falsafi, T. N. Vijaykumar
• Keywords: Dynamic Feature Selection, Hardware Predictors, JSA 2006, Predictive Information