Harnessing Aspect Oriented Programming on GPU: Application to Warp-Level Parallelism (WLP)

International audienceStochastic simulations involve multiple replications in order to build confidenceintervals for their results, and Designs Of Experiments (DOEs) to explore their parameters set. Inthis paper, we propose Warp-Level Parallelism (WLP), a GPU-enabled solution to compute MultipleReplications In Parallel (MRIP) on GPUs (Graphics Processing Units). GPUs are intrinsicallytuned to process efficiently the same operation on several data, which is not suited to parallelizeMRIP or DOEs. Our approach proposes to rely on small thread groups, called warps, to performindependent computations such as replications. This approach has proved to be efficient on threeclassical simulation models, but originally lacked the transparency users might expect. In thiswork, we enhance WLP using Aspect Oriented Programming (AOP). Our work describes the wayto combine CUDA and AOP, and brings forward the techniques available to exploit AOP in aCUDA-enabled development