Merging Path and GShare Indexing in Perception Branch PredictionReport
We introduce the hashed perceptron predictor, which merges the concepts behind the gshare, path-based and perceptron branch predictors. This predictor can achieve superior accuracy to a path-based and a global perceptron predictor, previously the most accurate dynamic branch predictors known in the literature. We also show how such a predictor can be ahead pipelined to yield one cycle effective latency. On 11 programs from the SPECint2000 set of benchmarks, the hashed perceptron predictor improves accuracy by up to 22% over a path-based perceptron and improves IPC by up to 6.5%.
All rights reserved (no additional license for public reuse)
Tarjan, David, and Kevin Skadron. "Merging Path and GShare Indexing in Perception Branch Prediction." University of Virginia Dept. of Computer Science Tech Report (2004).
University of Virginia, Department of Computer Science