Efficient Software-based Online Phase Classification
- Speaker
- Date and Time
Thursday, October 27th, 2011 at 13:30
- Location
Polacksbacken, room 1145
- Abstract
-
Many programs exhibit execution phases with time-varying behavior. Phase detection has been used extensively to find short and representative simulation points, used to quickly get representative simulation results for long-running applications. Several proposals for hardware-assisted phase detection have also been proposed to guide various forms of optimizations and hardware configurations.
This paper explores the feasibility of low overhead general phase detection at runtime based entirely on existing features found in modern processors. If successful, such a technology would be useful for cache management, frequency adjustments, runtime scheduling and profiling techniques.
The paper evaluates several existing and new alternatives for efficient runtime data collection and online phase detection. ScarPhase, a new online phase detection library, is presented. It makes extensive usage of the new hardware counter features, introduces a new phase classification heuristic and suggests a way to dynamically adjust the sample rate. ScarPhase exhibits runtime overhead below 2%.