Using scheduling entropy amplification in CUDA/OpenMP code to exhibit non-reproducibility issues

Abstract

Rounding error or cancellation that appears with each floating-point operations, combined with the lack of control over execution order in parallel code leads to numerical issues such as numerical reproducibility. In order to enhance the possibility to discover such numerical issue, in this article we propose a simple solution base on an index interposer and an index scrambler to amplify the possible combination of execution order.