HPS Research Group

Slides from Selected Talks

"Improving the Performance of Object-Oriented Languages with Dynamic Predication of Indirect Jumps,"

"Profile-Assisted Compiler Support for Dynamic Predication in Diverge-Merge Processors,"

"Diverge-Merge Processor,"

"2D-Profiling: Detecting Input-Dependent Branches with a Single Input Data Set,"

"Wish Branches: Combining Conditional Branching and Predication for Adaptive Predicated Execution,"

"Address-Value Delta (AVD) Prediction,"

"Techniques for Efficient Processing in Runahead Execution Engines,"

"Wrong Path Events: Exploiting Illegal and Unusual Program Behavior for Early Misprediction Detection and Recovery,"

"Cache Filtering Techniques to Reduce the Negative Impact of Useless Speculative Memory References on Processor Performance,"

"Demand-Only Broadcast: Reducing Register File and Bypass Power in Clustered Execution Cores,"

"Runahead Execution: An Alternative to Very Large Instruction Windows for Out-of-order Processors,"

"Using Internal Redundant Representations and Limited Bypass to Support Pipelined Adders and Register Files,"

"Select-Free Instruction Scheduling Logic,"

"On Pipelining Dynamic Instruction Scheduling Logic,"

"Variable Length Path Branch Prediction,"

"Analysis of Correlation and Predictability: What Makes Two-Level Branch Predictors Work,"

"Improving Trace Cache Effectiveness with Branch Promotion and Trace Packing,"

"The Trace Cache, One Year Later,"

"Out-of-Order Issue,"