Helper thread to monitor processor events for scheduling of sibling threads

This paper proposes and evaluates the helper thread for Time Aggregation Scheduler (TAS) intended to enhance the performance and energy efficiency. TAS is a kernel-level thread scheduler to enhance performances of multi-threaded programs by focusing on the affinity of sibling threads, which have the same parent process and share the context. TAS may change the scheduling order of threads so that we can reduce the number of occurrences of avoidable events such as cache misses. The helper thread for TAS monitors performance counters of the processor and adjusts the strength of aggregation in scheduling sibling threads. We have implemented the helper thread augmented with R for statistical computing to speculate the strength of aggregation. The results using DaCapo Java benchmark suites indicate our scheme is effective in reducing execution time while we need to consider the overhead of the helper thread.