Decoupled Value Prediction on Trace Processors

Value prediction is a technique that breaks true data dependences by predicting the outcome of an instruction, and executes speculatively its data-dependent instructions based on the predicted outcome. In this paper, we address several implementation issues for value prediction which are important on wide-issue superscalar architectures, and present a value prediction scheme based on the trace processor [18]. The scheme decouples the value prediction from the instruction fetch stage and use a hybrid predictor with dynamic classification. We use execution-driven simulation to study the performance of such a scheme using SPECint95 benchmarks.

• Type: Conference
• Year: 2000
• Where: HPCA
• Authors: Sang Jeong Lee, Yuan Wang, Pen-Chung Yew
• Keywords: Distributed And Parallel Computing, HPCA 2000, Value Prediction, Value Prediction Scheme, Wide-issue Superscalar Architectures