The Viability of Using Online Prediction to Perform Extra Work while Executing BSP Applications

Abstract

A fundamental problem in parallel processing is the difficulty in efficiently partitioning work: the result is that much of a parallel program's execution time is often spent idle or performing overhead operations. We propose to improve the efficiency of system resource utilization by having idle processes execute extra work. We develop a method whereby the execution of extra work is optimized through performance prediction and the setting of limits (a deadline) on the duration of the extra work execution. In our preliminary experiments of proxy BSP applications on a production supercomputer we find that this approach is promising with all five applications benefiting from this approach, with an average of 12 % improvement.